Crawler Report for docs.together.ai

Summary

Website Quality Score

7.0 Good
Performance
9.2
SEO
6.2
Security
8.5
Accessibility
5.0
Best Practices
5.0
  • ⛔ Skipped URLs - 254 skipped URLs found.
  • ⛔ Redirects - 15 redirects found.
  • ⛔ 6 page(s) with multiple <h1> headings.
  • ⚠️ The description '' exceeds the allowed 10% duplicity. 11% of pages have this same description.
  • ⚠️ 223 page(s) do not support Brotli compression.
  • ⚠️ No WebP image found on the website.
  • ⚠️ No AVIF image found on the website.
  • ⚠️ 1 page(s) with large inline SVGs (> 5120 bytes).
  • ⚠️ 222 page(s) with skipped heading levels.
  • ⚠️ 33 page(s) with deep DOM (> 30 levels).
  • ⚠️ 5 page(s) with non-clickable (non-interactive) phone numbers.
  • ⚠️ 32 page(s) without image alt attributes.
  • ⚠️ 223 page(s) without form labels.
  • ⚠️ 223 page(s) without aria labels.
  • ⚠️ 223 page(s) without role attributes.
  • ⚠️ Security - 892 pages(s) with warning(s).
  • ⏩ Loaded robots.txt for domain 'docs.together.ai': status code 200, size 79 B and took 210 ms.
  • ⏩ External URLs - 253 external URL(s) found.
  • ⏩ Performance NOTICE - 1 slow non-media URL(s) found (slower than 3 seconds).
  • ✅ 404 OK - all pages exists, no non-existent pages found.
  • ✅ SSL/TLS certificate is valid until May 31 00:06:38 2026 GMT. Issued by C = US, O = Google Trust Services, CN = WE1. Subject is CN = together.ai.
  • ✅ SSL/TLS certificate issued by 'C = US, O = Google Trust Services, CN = WE1'.
  • ✅ HTTP headers - found 29 unique headers.
  • ✅ All 218 unique title(s) are within the allowed 10% duplicity. Highest duplicity title has 0%.
  • ✅ All pages have quoted attributes.
  • ✅ All pages have inline SVGs with less than 5 duplicates.
  • ✅ All pages have valid or none inline SVGs.
  • ✅ All pages have <h1> heading.
  • ✅ All pages have valid HTML.
  • ✅ All pages have lang attribute.
  • ✅ DNS IPv4 OK: domain docs.together.ai resolved to 172.64.150.175, 104.18.37.81 (DNS server: 127.0.0.53).
  • ✅ DNS IPv6 OK: domain docs.together.ai resolved to 2a06:98c1:3105::ac40:96af, 2606:4700:4401::6812:2551 (DNS server: 127.0.0.53).

Visited URLs

Found 240 row(s).
URLStatusTypeTime (s)SizeCache
/308 Redirect316 ms77 B0 s
/intro200 HTML118 ms441 kB0 s
/docs/function-calling200 HTML207 ms3 MB0 s
/docs/mcp200 HTML260 ms407 kB0 s
/docs/quickstart200 HTML122 ms436 kB0 s
/docs/videos-overview200 HTML171 ms1 MB0 s
/reference/chat-completions200 HTML177 ms564 kB0 s
/docs/batch-inference200 HTML149 ms761 kB0 s
/docs/guides200 HTML166 ms386 kB0 s
/docs/vision-overview200 HTML118 ms889 kB0 s
/docs/integrations200 HTML158 ms1 MB0 s
/examples200 HTML350 ms409 kB0 s
/docs/chat-overview200 HTML163 ms729 kB0 s
/docs/openai-api-compatibility200 HTML156 ms1 MB0 s
/docs/serverless-models200 HTML188 ms645 kB0 s
/docs/json-mode200 HTML133 ms947 kB0 s
/docs/reasoning-overview200 HTML188 ms964 kB0 s
/docs/rate-limits200 HTML157 ms383 kB0 s
/docs/changelog200 HTML127 ms580 kB0 s
/docs/recommended-models200 HTML144 ms367 kB0 s
/docs/quickstart-flux-lora200 HTML162 ms446 kB0 s
/reference/cli/getting-started200 HTML112 ms370 kB0 s
/reference/cli/finetune200 HTML359 ms481 kB0 s
/reference/cli/endpoints200 HTML460 ms503 kB0 s
/reference/authentication200 HTML144 ms354 kB0 s
/docs/inference-models308 Redirect376 ms111 B0 s
/reference/post-images-generations200 HTML156 ms428 kB0 s
/reference/cli/models200 HTML197 ms389 kB0 s
/reference/cli/evals200 HTML254 ms394 kB0 s
/reference/cli/files200 HTML211 ms482 kB0 s
/docs/ai-evaluations200 HTML209 ms2 MB0 s
/docs/ai-tutor200 HTML179 ms2 MB0 s
/docs/parallel-workflows200 HTML165 ms1 MB0 s
/docs/using-together-with-mastra200 HTML189 ms456 kB0 s
/docs/nextjs-chat-quickstart200 HTML144 ms1 MB0 s
/docs/how-to-use-openclaw200 HTML131 ms392 kB0 s
/docs/how-to-build-real-time-audio-transcription-app200 HTML138 ms897 kB0 s
/docs/quickstart-retrieval-augmented-generation-rag200 HTML130 ms596 kB0 s
/docs/dedicated_containers_video200 HTML163 ms916 kB0 s
/docs/how-to-use-opencode200 HTML173 ms428 kB0 s
/docs/building-a-rag-workflow200 HTML144 ms661 kB0 s
/docs/how-to-implement-contextual-rag-from-anthropic200 HTML128 ms865 kB0 s
/docs/data-analyst-agent200 HTML126 ms708 kB0 s
/docs/sequential-agent-workflow200 HTML124 ms584 kB0 s
/docs/how-to-build-coding-agents200 HTML151 ms1 MB0 s
/docs/how-to-use-cline200 HTML135 ms354 kB0 s
/docs/how-to-build-phone-voice-agent200 HTML342 ms5 MB0 s
/docs/ai-search-engine200 HTML140 ms1 MB0 s
/docs/how-to-use-qwen-code200 HTML281 ms438 kB0 s
/docs/workflows200 HTML168 ms334 kB0 s
/docs/iterative-workflow200 HTML216 ms924 kB0 s
/docs/how-to-build-a-lovable-clone-with-kimi-k2200 HTML196 ms986 kB0 s
/docs/conditional-workflows200 HTML160 ms704 kB0 s
/docs/nanochat-on-instant-clusters200 HTML131 ms652 kB0 s
/docs/quickstart-using-hugging-face-inference200 HTML115 ms514 kB0 s
/docs/mixture-of-agents200 HTML141 ms614 kB0 s
/docs/logprobs200 HTML124 ms557 kB0 s
/docs/dedicated_containers_image200 HTML124 ms932 kB0 s
/docs/pythonv2-migration-guide200 HTML153 ms1 MB0 s
/docs/how-to-improve-search-with-rerankers200 HTML157 ms590 kB0 s
/docs/using-together-with-vercels-ai-sdk200 HTML104 ms598 kB0 s
/docs/integrations-2308 Redirect273 ms113 B0 s
/docs/quickstart-how-to-do-ocr200 HTML167 ms729 kB0 s
/docs/open-notebooklm-pdf-to-podcast200 HTML127 ms664 kB0 s
/docs/speech-to-text200 HTML146 ms2 MB0 s
/docs/dspy200 HTML187 ms431 kB0 s
/docs/embeddings-rag200 HTML101 ms325 kB0 s
/docs/crewai200 HTML142 ms435 kB0 s
/docs/pydanticai200 HTML102 ms397 kB0 s
/docs/rerank-overview200 HTML128 ms890 kB0 s
/docs/autogen200 HTML102 ms458 kB0 s
/docs/langgraph200 HTML207 ms452 kB0 s
/docs/composio200 HTML161 ms509 kB0 s
/docs/agno200 HTML147 ms381 kB0 s
/docs/gpu-clusters-api200 HTML122 ms741 kB0 s
/docs/deprecations200 HTML113 ms653 kB0 s
/reference/completions-1308 Redirect283 ms109 B0 s
/reference/audio-translations200 HTML223 ms410 kB0 s
/reference/audio-speech200 HTML205 ms404 kB0 s
/docs/dedicated-inference200 HTML161 ms612 kB0 s
/reference/audio-transcriptions200 HTML109 ms423 kB0 s
/docs/images-overview200 HTML129 ms935 kB0 s
/docs/glm-5-quickstart200 HTML127 ms761 kB0 s
/docs/kimi-k2-quickstart200 HTML145 ms409 kB0 s
/docs/llama4-quickstart200 HTML169 ms664 kB0 s
/docs/deployment-options200 HTML104 ms364 kB0 s
/docs/sso200 HTML277 ms364 kB0 s
/docs/inference-web-interface200 HTML111 ms323 kB0 s
/docs/dedicated-endpoints200 HTML112 ms363 kB0 s
/docs/create-tickets-in-slack200 HTML100 ms316 kB0 s
/docs/billing-payment-methods200 HTML104 ms362 kB0 s
/docs/organizations200 HTML98 ms 344 kB0 s
/docs/billing-troubleshooting200 HTML114 ms338 kB0 s
/docs/billing-usage-limits200 HTML108 ms376 kB0 s
/docs/support-ticket-portal200 HTML257 ms342 kB0 s
/docs/inference-faqs200 HTML117 ms417 kB0 s
/docs/identity-access-management200 HTML132 ms354 kB0 s
/docs/api-keys-authentication200 HTML115 ms378 kB0 s
/docs/projects200 HTML105 ms372 kB0 s
/docs/billing-credits200 HTML108 ms331 kB0 s
/docs/fine-tuning-faqs200 HTML108 ms399 kB0 s
/docs/dedicated-endpoints-ui200 HTML115 ms362 kB0 s
/docs/error-codes200 HTML116 ms322 kB0 s
/docs/roles-permissions200 HTML248 ms385 kB0 s
/reference/chat-completions-1308 Redirect245 ms119 B0 s
/docs/containers-quickstart200 HTML229 ms604 kB0 s
/docs/text-to-speech200 HTML188 ms2 MB0 s
/docs/lora-inference308 Redirect269 ms131 B0 s
/docs/dedicated-container-inference200 HTML173 ms359 kB0 s
/docs/quickstart-flux-kontext200 HTML133 ms410 kB0 s
/docs/dedicated-models200 HTML94 ms 335 kB0 s
/docs/deepseek-r1200 HTML111 ms441 kB0 s
/docs/reasoning-models-guide200 HTML97 ms 341 kB0 s
/reference/embeddings-2308 Redirect462 ms107 B0 s
/docs/quickstart-flux200 HTML142 ms1 MB0 s
/reference/queue-metrics200 HTML250 ms382 kB0 s
/docs/fine-tuning-models200 HTML153 ms668 kB0 s
/docs/fine-tuning-lora-supported-modules200 HTML308 ms521 kB0 s
/typescript-library307 Redirect256 ms175 B0 s
/docs/custom-models200 HTML157 ms514 kB0 s
/reference/cli/beta-intro200 HTML213 ms317 kB0 s
/reference/upload-file200 HTML153 ms417 kB0 s
/reference/create-evaluation200 HTML169 ms407 kB0 s
/docs/evaluations-supported-models200 HTML114 ms477 kB0 s
/docs/ai-evaluations-ui200 HTML161 ms438 kB0 s
/docs308 Redirect313 ms77 B0 s
/reference/deployments-list200 HTML255 ms401 kB0 s
/reference/dci-reference-sprocket200 HTML138 ms685 kB0 s
/reference/dci-reference-jig200 HTML300 ms990 kB0 s
/external-link-02307 Redirect229 ms339 B0 s
/docs/agent-integrations200 HTML154 ms341 kB0 s
/reference/clusters-create200 HTML129 ms467 kB0 s
/docs/instant-clusters308 Redirect291 ms119 B0 s
/docs/embeddings-overview200 HTML107 ms490 kB0 s
/docs/gpu-clusters-billing200 HTML106 ms392 kB0 s
/docs/gpu-clusters-management200 HTML146 ms835 kB0 s
/docs/cluster-storage200 HTML117 ms333 kB0 s
/docs/gpu-clusters-quickstart200 HTML274 ms435 kB0 s
/docs/gpu-clusters-overview200 HTML141 ms399 kB0 s
/docs/health-checks200 HTML243 ms522 kB0 s
/reference/audio-speech-websocket200 HTML132 ms480 kB0 s
/reference/rerank-1308 Redirect1 s 99 B0 s
/reference/completions200 HTML267 ms493 kB0 s
/reference/audio-transcriptions-realtime200 HTML172 ms442 kB0 s
/docs/adapter-upload200 HTML181 ms540 kB0 s
/docs/gpt-oss200 HTML111 ms505 kB0 s
/reference/listendpoints200 HTML298 ms391 kB0 s
/docs/kimi-k2-thinking-quickstart200 HTML154 ms464 kB0 s
/docs/deepseek-3-1-quickstart200 HTML207 ms504 kB0 s
/docs/fine-tuning-quickstart200 HTML158 ms1 MB0 s
/docs/inference-parameters200 HTML123 ms407 kB0 s
/reference/inference200 HTML122 ms452 kB0 s
/docs/deployments-jig200 HTML117 ms542 kB0 s
/docs/inference-rest308 Redirect282 ms77 B0 s
/docs/together-deployments200 HTML110 ms582 kB0 s
/docs/deployments-sprocket200 HTML124 ms522 kB0 s
/docs/lora-training-and-inference200 HTML124 ms598 kB0 s
/docs/deployments-queue200 HTML123 ms650 kB0 s
/docs/deepseek-faqs200 HTML113 ms397 kB0 s
/docs/prompting-deepseek-r1200 HTML140 ms329 kB0 s
/reference/embeddings200 HTML130 ms404 kB0 s
/reference/queue-cancel200 HTML219 ms386 kB0 s
/reference/queue-submit200 HTML199 ms396 kB0 s
/reference/queue-status200 HTML242 ms420 kB0 s
/docs/preference-fine-tuning200 HTML123 ms445 kB0 s
/docs/fine-tuning-function-calling200 HTML254 ms748 kB0 s
/docs/deploying-a-fine-tuned-model200 HTML149 ms682 kB0 s
/docs/fine-tuning-reasoning200 HTML250 ms626 kB0 s
/docs/fine-tuning-data-preparation200 HTML276 ms824 kB0 s
/docs/fine-tuning-byom200 HTML245 ms815 kB0 s
/docs/fine-tuning-pricing200 HTML126 ms346 kB0 s
/docs/fine-tuning-vlm200 HTML203 ms801 kB0 s
/reference/cli/clusters200 HTML128 ms485 kB0 s
/reference/cli/jig-redirect-stub200 HTML214 ms316 kB0 s
/reference/get-files200 HTML247 ms367 kB0 s
/reference/get-files-id-content200 HTML249 ms365 kB0 s
https://github.com/togethercomputer/together-typescript200 HTML759 ms468 kB0 s
/reference/list-evaluations200 HTML100 ms424 kB0 s
/reference/get-files-id200 HTML228 ms391 kB0 s
/reference/delete-files-id200 HTML373 ms364 kB0 s
/reference/get-evaluation200 HTML132 ms419 kB0 s
/reference/delete-fine-tunes-id200 HTML202 ms377 kB0 s
/reference/list-evaluation-models200 HTML169 ms368 kB0 s
/reference/get-evaluation-status200 HTML105 ms388 kB0 s
/docs/together-code-interpreter200 HTML131 ms1 MB0 s
/reference/deployments-create200 HTML249 ms513 kB0 s
/reference/deployments-get200 HTML214 ms470 kB0 s
/reference/deployments-delete200 HTML210 ms371 kB0 s
/reference/deployments-logs200 HTML226 ms378 kB0 s
/reference/clusters-list-regions200 HTML107 ms365 kB0 s
/reference/deployments-update200 HTML241 ms534 kB0 s
/reference/clusters-list200 HTML104 ms390 kB0 s
/reference/clusters-delete200 HTML255 ms366 kB0 s
/reference/clusters-update200 HTML105 ms435 kB0 s
/reference/clusters-get200 HTML246 ms408 kB0 s
/docs/gpu-clusters-capacity-types308 Redirect235 ms119 B0 s
/docs/slurm200 HTML97 ms 338 kB0 s
/docs/slurm-configuration200 HTML244 ms616 kB0 s
/reference/rerank200 HTML108 ms464 kB0 s
/reference/models200 HTML115 ms415 kB0 s
/reference/create-videos200 HTML217 ms442 kB0 s
/reference/upload-model200 HTML245 ms393 kB0 s
/reference/listhardware200 HTML218 ms390 kB0 s
/reference/deleteendpoint200 HTML234 ms373 kB0 s
/reference/updateendpoint200 HTML237 ms441 kB0 s
/reference/getendpoint200 HTML206 ms422 kB0 s
/reference/deployments-storage-volumes-delete200 HTML232 ms369 kB0 s
/reference/createendpoint200 HTML375 ms455 kB0 s
/docs/finetuning308 Redirect281 ms121 B0 s
/reference/get-fine-tunes-id-events200 HTML215 ms378 kB0 s
/reference/get-finetune-download200 HTML351 ms373 kB0 s
/reference/post-fine-tunes200 HTML499 ms574 kB0 s
/reference/get-fine-tunes-id200 HTML255 ms515 kB0 s
/reference/get-fine-tunes-id-checkpoint200 HTML288 ms370 kB0 s
/reference/post-fine-tunes-id-cancel200 HTML239 ms483 kB0 s
/docs/together-code-sandbox200 HTML125 ms742 kB0 s
/reference/get-fine-tunes200 HTML374 ms389 kB0 s
/reference/tci-execute200 HTML309 ms397 kB0 s
/reference/deployments-secrets-list200 HTML248 ms378 kB0 s
/reference/clusters_storages-delete200 HTML214 ms372 kB0 s
/reference/clusters_storages-create200 HTML259 ms395 kB0 s
/reference/tci-sessions200 HTML249 ms365 kB0 s
/reference/get-videos-id200 HTML247 ms397 kB0 s
/reference/batch-list200 HTML239 ms413 kB0 s
/reference/deployments-storage-volumes-get200 HTML272 ms395 kB0 s
/reference/deployments-storage-volumes-update200 HTML425 ms405 kB0 s
/reference/deployments-storage-volumes-create200 HTML313 ms408 kB0 s
/reference/deployments-storage-volumes-list200 HTML334 ms381 kB0 s
/reference/batch-cancel200 HTML132 ms423 kB0 s
/reference/deployments-storage-get200 HTML412 ms371 kB0 s
/reference/deployments-secrets-create200 HTML263 ms408 kB0 s
/reference/deployments-secrets-update200 HTML243 ms413 kB0 s
https://www.together.ai/blog/how-to-build-a-real-time-…xMTcxNDI4OS4xNzQyOTc3MTMx200 HTML4.5 s 369 kBLast-Mod-only
/reference/clusters_storages-list200 HTML113 ms371 kB0 s
/reference/deployments-secrets-delete200 HTML238 ms369 kB0 s
/reference/deployments-secrets-get200 HTML403 ms398 kB0 s
/reference/clusters_storages-get200 HTML217 ms382 kB0 s
/reference/clusters_storages-update200 HTML294 ms387 kB0 s
/reference/batch-create200 HTML269 ms403 kB0 s
/reference/batch-get200 HTML264 ms423 kB0 s
No rows found, please edit your search term.

Best practices

Found 11 row(s).
Analysis nameOKNoticeWarningCritical
DOM depth (> 30)1920330
Heading structure22803076
Non-clickable phone numbers11030
Invalid inline SVGs220000
Large inline SVGs (> 5120 B)219010
Duplicate inline SVGs (> 5 and > 1024 B)220000
Title uniqueness (> 10%)218000
Description uniqueness (> 10%)198010
Brotli support002230
WebP support0010
AVIF support0010
No rows found, please edit your search term.

Large inline SVGs

SeverityOccursDetailAffected URLs (max 5)
warning1<svg xmlns="http://www.w3.org/2000/svg" width="100%" viewBox="0 0 119 26" fill="none" class="nav-logo"> ...https://www.together.ai/blog/how-to-buil…DI4OS4xNzQyOTc3MTMx

Duplicate inline SVGs

No problems found.


Invalid inline SVGs

No problems found.


Missing quotes on attributes

No problems found.


DOM depth

SeverityOccursDetailAffected URLs (max 5)
warning31The DOM depth exceeds the warning limit: 30. Found depth: 30.URL 1, URL 2, URL 3, URL 4, URL 5
warning1The DOM depth exceeds the warning limit: 30. Found depth: 33./reference/list-evaluations
warning1The DOM depth exceeds the warning limit: 30. Found depth: 36.https://github.com/togethercomputer/together-typescript

Heading structure

SeverityOccursDetailAffected URLs (max 5)
critical13Multiple <h1> headings found.URL 1, URL 2, URL 3, URL 4, URL 5
warning221Heading structure is skipping levels: found an <h5> without a previous higher heading.URL 1, URL 2, URL 3, URL 4, URL 5
warning77Heading structure is skipping levels: found an <h4> after an <h1>.URL 1, URL 2, URL 3, URL 4, URL 5
warning8Heading structure is skipping levels: found an <h3> after an <h1>.URL 1, URL 2, URL 3, URL 4, URL 5
warning3Heading structure is skipping levels: found an <h4> after an <h2>.URL 1, URL 2
warning1Heading structure is skipping levels: found an <h2> without a previous higher heading.https://github.com/togethercomputer/together-typescript

Non-clickable phone numbers

SeverityOccursDetailAffected URLs (max 5)
warning3(847) 851-4323URL 1, URL 2, URL 3
warning18-3778-6328/reference/rerank
warning1310-657-5111/docs/quickstart-how-to-do-ocr

Title uniqueness

No problems found.


Description uniqueness

No problems found.

Accessibility

Analysis nameOKNoticeWarningCritical
Missing image alt attributes4901120
Missing aria labels8502561
Missing html lang attribute1000
Missing roles0030
Missing form labels0010

Valid HTML

No problems found.


Missing image alt attributes

SeverityOccursDetailAffected URLs (max 5)
warning99<img class="object-*" *** >URL 1, URL 2, URL 3, URL 4, URL 5
warning12<img class="" *** >/docs/quickstart-flux
warning1<img class="rounded" *** >/docs/create-tickets-in-slack

Missing form labels

SeverityOccursDetailAffected URLs (max 5)
warning223<input class="hidden" *** >URL 1, URL 2, URL 3, URL 4, URL 5

Missing aria labels

Found 119 row(s).
SeverityOccursDetailAffected URLs (max 5)
critical223<input class="hidden" *** >URL 1, URL 2, URL 3, URL 4, URL 5
warning3603<a class="group flex items-* pr-* py-* cursor-* gap-* text-* rounded-* w-* outline-* hover:bg-* dark:hover:bg-* text-* hover:text-* dark:text-* dark:hover:text-*" *** >URL 1, URL 2, URL 3, URL 4, URL 5
warning1332<a class="text-* max-* whitespace-* md:truncate text-* dark:text-* hover:text-* dark:hover:text-*" *** >URL 1, URL 2, URL 3, URL 4, URL 5
warning1115<a class="link nav-* group relative h-* gap-* flex items-* font-* text-* dark:text-* hover:text-* dark:hover:text-*" *** >URL 1, URL 2, URL 3, URL 4, URL 5
warning850<a class="link" *** >URL 1, URL 2, URL 3, URL 4, URL 5
warning752<a class="group flex items-* pr-* py-* cursor-* gap-* text-* break-* hyphens-* rounded-* w-* outline-* hover:bg-* dark:hover:bg-* text-* hover:text-* dark:text-* dark:hover:text-*" *** >URL 1, URL 2, URL 3, URL 4, URL 5
warning555<a class="group flex items-* break-* py-* whitespace-* text-* hover:text-* dark:text-* dark:hover:text-*" *** >URL 1, URL 2, URL 3, URL 4, URL 5
warning480<a class="break-* py-* block font-* border-* pl-* border-* dark:border-* hover:border-* dark:hover:border-* hover:text-* dark:text-* dark:hover:text-*" *** >URL 1, URL 2, URL 3, URL 4, URL 5
warning446<button class="group hover:bg-* dark:hover:bg-* p-* rounded-*">URL 1, URL 2, URL 3, URL 4, URL 5
warning445<a class="select-*" *** >URL 1, URL 2, URL 3, URL 4, URL 5
warning428<a class="pagination-* border border-* dark:border-* group flex items-* rounded-* py-* px-* hover:border-* dark:hover:border-* justify-*" *** >URL 1, URL 2, URL 3, URL 4, URL 5
warning393<a class="break-* py-* block border-* pl-* border-* dark:border-* hover:border-* dark:hover:border-* hover:text-* dark:text-* dark:hover:text-*" *** >URL 1, URL 2, URL 3, URL 4, URL 5
warning236<button class="group disabled:pointer-* [& *** >URL 1, URL 2, URL 3, URL 4, URL 5
warning223<button id="assistant-entry-mobile">URL 1, URL 2, URL 3, URL 4, URL 5
warning223<a class="link nav-* group relative h-* gap-* flex items-* font-* hover:text-* dark:hover:text-* text-* dark:text-* [text-*" *** >URL 1, URL 2, URL 3, URL 4, URL 5
warning223<button class="flex items-* h-* py-* px-* lg:hidden focus:outline-* w-* text-*" *** >URL 1, URL 2, URL 3, URL 4, URL 5
warning223<a class="sr-* focus:not-* focus:fixed focus:top-* focus:left-* focus:z-* focus:p-* focus:text-* focus:bg-* dark:focus:bg-* focus:rounded-* focus:outline-* dark:focus:outline-*" *** >URL 1, URL 2, URL 3, URL 4, URL 5
warning222<a class="group flex items-* gap-* text-* text-* dark:text-* hover:text-* dark:hover:text-*" *** >URL 1, URL 2, URL 3, URL 4, URL 5
warning222<button class="px-* py-* flex flex-* gap-* items-* border-* rounded-* text-* dark:text-* hover:text-* dark:hover:text-* bg-* dark:bg-* hover:border-* hover:dark:border-*" id="feedback-thumbs-down">URL 1, URL 2, URL 3, URL 4, URL 5
warning222<button class="px-* py-* flex flex-* gap-* items-* border-* rounded-* text-* dark:text-* hover:text-* dark:hover:text-* bg-* dark:bg-* hover:border-* hover:dark:border-*" id="feedback-thumbs-up">URL 1, URL 2, URL 3, URL 4, URL 5
warning216<button class="group flex items-* relative gap-* my-* mb-* outline-* whitespace-* font-* !ml-* first:!ml-* focus:outline-* text-* dark:text-*" id="radix-_R_2islubracf99absnpfdb_-trigger-***" *** >URL 1, URL 2, URL 3, URL 4, URL 5
warning216<button class="group flex items-* relative gap-* my-* mb-* outline-* whitespace-* font-* !ml-* first:!ml-* focus:outline-* text-* dark:text-*" id="radix-_R_kl4slubracf99absnpfdb_-trigger-***" *** >URL 1, URL 2, URL 3, URL 4, URL 5
warning184<a class="group flex items-* pr-* py-* cursor-* gap-* text-* rounded-* w-* outline-* bg-* text-* [text-* dark:text-* dark:bg-*" *** >URL 1, URL 2, URL 3, URL 4, URL 5
warning136<button class="text-* dark:text-* font-* flex items-* space-* hover:text-* dark:hover:text-* transition-* cursor-*">URL 1, URL 2, URL 3, URL 4, URL 5
warning102<button class="group group overflow-* rounded-* disabled:pointer-* [& *** >URL 1, URL 2, URL 3, URL 4, URL 5
warning35<a class="group flex items-* pr-* py-* cursor-* gap-* text-* break-* hyphens-* rounded-* w-* outline-* bg-* text-* [text-* dark:text-* dark:bg-*" *** >URL 1, URL 2, URL 3, URL 4, URL 5
warning35<button class="group flex items-* relative gap-* my-* mb-* outline-* whitespace-* font-* !ml-* first:!ml-* focus:outline-* text-* dark:text-*" id="radix-_R_4lcslubracf99absnpfdb_-trigger-***" *** >URL 1, URL 2, URL 3, URL 4, URL 5
warning32<a class="_*" *** >URL 1, URL 2, URL 3, URL 4, URL 5
warning28<a class="link mint-* underline-* mint-* mint-*" *** >/docs/guides
warning27<button class="group flex items-* relative gap-* my-* mb-* outline-* whitespace-* font-* !ml-* first:!ml-* focus:outline-* text-* dark:text-*" id="radix-_R_7lcslubracf99absnpfdb_-trigger-***" *** >URL 1, URL 2, URL 3, URL 4, URL 5
warning27<button class="group flex items-* relative gap-* my-* mb-* outline-* whitespace-* font-* !ml-* first:!ml-* focus:outline-* text-* dark:text-*" id="radix-_R_6lcslubracf99absnpfdb_-trigger-***" *** >URL 1, URL 2, URL 3, URL 4, URL 5
warning24<button class="group flex items-* relative gap-* my-* mb-* outline-* whitespace-* font-* !ml-* first:!ml-* focus:outline-* text-* dark:text-*" id="radix-_R_tlcslubracf99absnpfdb_-trigger-***" *** >URL 1, URL 2, URL 3, URL 4, URL 5
warning21<button class="group flex items-* relative gap-* my-* mb-* outline-* whitespace-* font-* !ml-* first:!ml-* focus:outline-* text-* dark:text-*" id="radix-_R_glcslubracf99absnpfdb_-trigger-***" *** >URL 1, URL 2, URL 3, URL 4, URL 5
warning20<button class="group flex items-* relative gap-* my-* mb-* outline-* whitespace-* font-* !ml-* first:!ml-* focus:outline-* text-* dark:text-*" id="radix-_R_plcslubracf99absnpfdb_-trigger-***" *** >URL 1, URL 2, URL 3, URL 4, URL 5
warning20<button class="group flex items-* relative gap-* my-* mb-* outline-* whitespace-* font-* !ml-* first:!ml-* focus:outline-* text-* dark:text-*" id="radix-_R_blcslubracf99absnpfdb_-trigger-***" *** >URL 1, URL 2, URL 3, URL 4, URL 5
warning19<button class="group flex items-* relative gap-* my-* mb-* outline-* whitespace-* font-* !ml-* first:!ml-* focus:outline-* text-* dark:text-*" id="radix-_R_8lcslubracf99absnpfdb_-trigger-***" *** >URL 1, URL 2, URL 3, URL 4, URL 5
warning18<button class="group flex items-* relative gap-* my-* mb-* outline-* whitespace-* font-* !ml-* first:!ml-* focus:outline-* text-* dark:text-*" id="radix-_R_llcslubracf99absnpfdb_-trigger-***" *** >URL 1, URL 2, URL 3, URL 4, URL 5
warning14<a class="link mint-* mint-* mint-* mint-* mint-* dark:mint-* hover:mint-* dark:hover:mint-*" *** >/examples
warning14<button class="group flex items-* relative gap-* my-* mb-* outline-* whitespace-* font-* !ml-* first:!ml-* focus:outline-* text-* dark:text-*" id="radix-_R_alcslubracf99absnpfdb_-trigger-***" *** >URL 1, URL 2, URL 3, URL 4, URL 5
warning14<button class="group flex items-* relative gap-* my-* mb-* outline-* whitespace-* font-* !ml-* first:!ml-* focus:outline-* text-* dark:text-*" id="radix-_R_jlcslubracf99absnpfdb_-trigger-***" *** >URL 1, URL 2, URL 3, URL 4, URL 5
warning13<button class="group flex items-* relative gap-* my-* mb-* outline-* whitespace-* font-* !ml-* first:!ml-* focus:outline-* text-* dark:text-*" id="radix-_R_dlcslubracf99absnpfdb_-trigger-***" *** >URL 1, URL 2, URL 3, URL 4, URL 5
warning13<button class="group flex items-* relative gap-* my-* mb-* outline-* whitespace-* font-* !ml-* first:!ml-* focus:outline-* text-* dark:text-*" id="radix-_R_flcslubracf99absnpfdb_-trigger-***" *** >URL 1, URL 2, URL 3, URL 4, URL 5
warning13<button class="group flex items-* relative gap-* my-* mb-* outline-* whitespace-* font-* !ml-* first:!ml-* focus:outline-* text-* dark:text-*" id="radix-_R_mlcslubracf99absnpfdb_-trigger-***" *** >URL 1, URL 2, URL 3, URL 4, URL 5
warning13<button class="group flex items-* relative gap-* my-* mb-* outline-* whitespace-* font-* !ml-* first:!ml-* focus:outline-* text-* dark:text-*" id="radix-_R_15lcslubracf99absnpfdb_-trigger-***" *** >URL 1, URL 2, URL 3, URL 4, URL 5
warning13<button class="group flex items-* relative gap-* my-* mb-* outline-* whitespace-* font-* !ml-* first:!ml-* focus:outline-* text-* dark:text-*" id="radix-_R_klcslubracf99absnpfdb_-trigger-***" *** >URL 1, URL 2, URL 3, URL 4, URL 5
warning11<button class="group flex items-* relative gap-* my-* mb-* outline-* whitespace-* font-* !ml-* first:!ml-* focus:outline-* text-* dark:text-*" id="radix-_R_3lcslubracf99absnpfdb_-trigger-***" *** >URL 1, URL 2, URL 3, URL 4, URL 5
warning11<button class="group flex items-* relative gap-* my-* mb-* outline-* whitespace-* font-* !ml-* first:!ml-* focus:outline-* text-* dark:text-*" id="radix-_R_9lcslubracf99absnpfdb_-trigger-***" *** >URL 1, URL 2, URL 3, URL 4, URL 5
warning11<a class="link mint-* mint-* mint-* mint-* dark:mint-* dark:hover:mint-* mint-* mint-* dark:mint-* mint-* hover:mint-* mint-*" *** >/examples
warning11<button class="group flex items-* relative gap-* my-* mb-* outline-* whitespace-* font-* !ml-* first:!ml-* focus:outline-* text-* dark:text-*" id="radix-_R_rlcslubracf99absnpfdb_-trigger-***" *** >URL 1, URL 2, URL 3, URL 4, URL 5
warning10<button class="group flex items-* relative gap-* my-* mb-* outline-* whitespace-* font-* !ml-* first:!ml-* focus:outline-* text-* dark:text-*" id="radix-_R_2lcslubracf99absnpfdb_-trigger-***" *** >URL 1, URL 2, URL 3, URL 4, URL 5
warning10<button class="group flex items-* relative gap-* my-* mb-* outline-* whitespace-* font-* !ml-* first:!ml-* focus:outline-* text-* dark:text-*" id="radix-_R_ulcslubracf99absnpfdb_-trigger-***" *** >URL 1, URL 2, URL 3, URL 4, URL 5
warning10<button class="group flex items-* relative gap-* my-* mb-* outline-* whitespace-* font-* !ml-* first:!ml-* focus:outline-* text-* dark:text-*" id="radix-_R_elcslubracf99absnpfdb_-trigger-***" *** >URL 1, URL 2, URL 3, URL 4, URL 5
warning9<button class="group flex items-* relative gap-* my-* mb-* outline-* whitespace-* font-* !ml-* first:!ml-* focus:outline-* text-* dark:text-*" id="radix-_R_1clcslubracf99absnpfdb_-trigger-***" *** >URL 1, URL 2, URL 3, URL 4, URL 5
warning8<button class="group flex items-* relative gap-* my-* mb-* outline-* whitespace-* font-* !ml-* first:!ml-* focus:outline-* text-* dark:text-*" id="radix-_R_16lcslubracf99absnpfdb_-trigger-***" *** >URL 1, URL 2, URL 3, URL 4
warning8<button class="group flex items-* relative gap-* my-* mb-* outline-* whitespace-* font-* !ml-* first:!ml-* focus:outline-* text-* dark:text-*" id="radix-_R_ilcslubracf99absnpfdb_-trigger-***" *** >URL 1, URL 2, URL 3, URL 4, URL 5
warning8<button class="group flex items-* relative gap-* my-* mb-* outline-* whitespace-* font-* !ml-* first:!ml-* focus:outline-* text-* dark:text-*" id="radix-_R_nlcslubracf99absnpfdb_-trigger-***" *** >URL 1, URL 2, URL 3, URL 4
warning8<button class="group flex items-* relative gap-* my-* mb-* outline-* whitespace-* font-* !ml-* first:!ml-* focus:outline-* text-* dark:text-*" id="radix-_R_1plcslubracf99absnpfdb_-trigger-***" *** >URL 1, URL 2, URL 3
warning8<button class="group flex items-* relative gap-* my-* mb-* outline-* whitespace-* font-* !ml-* first:!ml-* focus:outline-* text-* dark:text-*" id="radix-_R_clcslubracf99absnpfdb_-trigger-***" *** >URL 1, URL 2, URL 3, URL 4, URL 5
warning8<button class="group flex items-* relative gap-* my-* mb-* outline-* whitespace-* font-* !ml-* first:!ml-* focus:outline-* text-* dark:text-*" id="radix-_R_2flcslubracf99absnpfdb_-trigger-***" *** >URL 1, URL 2, URL 3
warning7<button class="group flex items-* relative gap-* my-* mb-* outline-* whitespace-* font-* !ml-* first:!ml-* focus:outline-* text-* dark:text-*" id="radix-_R_17lcslubracf99absnpfdb_-trigger-***" *** >URL 1, URL 2, URL 3, URL 4
warning7<button class="group flex items-* relative gap-* my-* mb-* outline-* whitespace-* font-* !ml-* first:!ml-* focus:outline-* text-* dark:text-*" id="radix-_R_olcslubracf99absnpfdb_-trigger-***" *** >URL 1, URL 2, URL 3, URL 4
warning7<button class="group flex items-* relative gap-* my-* mb-* outline-* whitespace-* font-* !ml-* first:!ml-* focus:outline-* text-* dark:text-*" id="radix-_R_1rlcslubracf99absnpfdb_-trigger-***" *** >URL 1, URL 2, URL 3, URL 4
warning7<button class="group flex items-* relative gap-* my-* mb-* outline-* whitespace-* font-* !ml-* first:!ml-* focus:outline-* text-* dark:text-*" id="radix-_R_13lcslubracf99absnpfdb_-trigger-***" *** >URL 1, URL 2, URL 3, URL 4, URL 5
warning6<button class="group flex items-* relative gap-* my-* mb-* outline-* whitespace-* font-* !ml-* first:!ml-* focus:outline-* text-* dark:text-*" id="radix-_R_5lcslubracf99absnpfdb_-trigger-***" *** >URL 1, URL 2, URL 3, URL 4
warning6<button class="group flex items-* relative gap-* my-* mb-* outline-* whitespace-* font-* !ml-* first:!ml-* focus:outline-* text-* dark:text-*" id="radix-_R_qlcslubracf99absnpfdb_-trigger-***" *** >URL 1, URL 2, URL 3, URL 4
warning6<button class="group flex items-* relative gap-* my-* mb-* outline-* whitespace-* font-* !ml-* first:!ml-* focus:outline-* text-* dark:text-*" id="radix-_R_12lcslubracf99absnpfdb_-trigger-***" *** >URL 1, URL 2, URL 3
warning6<button class="group flex items-* relative gap-* my-* mb-* outline-* whitespace-* font-* !ml-* first:!ml-* focus:outline-* text-* dark:text-*" id="radix-_R_14lcslubracf99absnpfdb_-trigger-***" *** >URL 1, URL 2, URL 3, URL 4
warning6<button class="group flex items-* relative gap-* my-* mb-* outline-* whitespace-* font-* !ml-* first:!ml-* focus:outline-* text-* dark:text-*" id="radix-_R_1ulcslubracf99absnpfdb_-trigger-***" *** >URL 1, URL 2, URL 3
warning6<button class="group flex items-* relative gap-* my-* mb-* outline-* whitespace-* font-* !ml-* first:!ml-* focus:outline-* text-* dark:text-*" id="radix-_R_hlcslubracf99absnpfdb_-trigger-***" *** >URL 1, URL 2, URL 3, URL 4, URL 5
warning6<button class="group flex items-* relative gap-* my-* mb-* outline-* whitespace-* font-* !ml-* first:!ml-* focus:outline-* text-* dark:text-*" id="radix-_R_23lcslubracf99absnpfdb_-trigger-***" *** >URL 1, URL 2, URL 3
warning5<button class="group flex items-* relative gap-* my-* mb-* outline-* whitespace-* font-* !ml-* first:!ml-* focus:outline-* text-* dark:text-*" id="radix-_R_11lcslubracf99absnpfdb_-trigger-***" *** >URL 1, URL 2, URL 3, URL 4
warning5<button class="group flex items-* relative gap-* my-* mb-* outline-* whitespace-* font-* !ml-* first:!ml-* focus:outline-* text-* dark:text-*" id="radix-_R_1alcslubracf99absnpfdb_-trigger-***" *** >URL 1, URL 2, URL 3
warning5<button class="group flex items-* relative gap-* my-* mb-* outline-* whitespace-* font-* !ml-* first:!ml-* focus:outline-* text-* dark:text-*" id="radix-_R_1flcslubracf99absnpfdb_-trigger-***" *** >URL 1, URL 2, URL 3, URL 4
warning5<button class="group flex items-* relative gap-* my-* mb-* outline-* whitespace-* font-* !ml-* first:!ml-* focus:outline-* text-* dark:text-*" id="radix-_R_18lcslubracf99absnpfdb_-trigger-***" *** >URL 1, URL 2, URL 3, URL 4, URL 5
warning5<button class="group flex items-* relative gap-* my-* mb-* outline-* whitespace-* font-* !ml-* first:!ml-* focus:outline-* text-* dark:text-*" id="radix-_R_1llcslubracf99absnpfdb_-trigger-***" *** >URL 1, URL 2
warning5<button class="group flex items-* relative gap-* my-* mb-* outline-* whitespace-* font-* !ml-* first:!ml-* focus:outline-* text-* dark:text-*" id="radix-_R_1vlcslubracf99absnpfdb_-trigger-***" *** >URL 1, URL 2
warning4<button class="group flex items-* relative gap-* my-* mb-* outline-* whitespace-* font-* !ml-* first:!ml-* focus:outline-* text-* dark:text-*" id="radix-_R_2llcslubracf99absnpfdb_-trigger-***" *** >/docs/text-to-speech
warning4<button class="group flex items-* relative gap-* my-* mb-* outline-* whitespace-* font-* !ml-* first:!ml-* focus:outline-* text-* dark:text-*" id="radix-_R_1tlcslubracf99absnpfdb_-trigger-***" *** >URL 1, URL 2, URL 3
warning4<button class="group flex items-* relative gap-* my-* mb-* outline-* whitespace-* font-* !ml-* first:!ml-* focus:outline-* text-* dark:text-*" id="radix-_R_slcslubracf99absnpfdb_-trigger-***" *** >URL 1, URL 2, URL 3
warning4<button class="group flex items-* relative gap-* my-* mb-* outline-* whitespace-* font-* !ml-* first:!ml-* focus:outline-* text-* dark:text-*" id="radix-_R_1jlcslubracf99absnpfdb_-trigger-***" *** >URL 1, URL 2, URL 3
warning4<button class="group flex items-* relative gap-* my-* mb-* outline-* whitespace-* font-* !ml-* first:!ml-* focus:outline-* text-* dark:text-*" id="radix-_R_1klcslubracf99absnpfdb_-trigger-***" *** >URL 1, URL 2
warning4<button class="group flex items-* relative gap-* my-* mb-* outline-* whitespace-* font-* !ml-* first:!ml-* focus:outline-* text-* dark:text-*" id="radix-_R_2olcslubracf99absnpfdb_-trigger-***" *** >URL 1, URL 2
warning3<button class="group flex items-* relative gap-* my-* mb-* outline-* whitespace-* font-* !ml-* first:!ml-* focus:outline-* text-* dark:text-*" id="radix-_R_1hlcslubracf99absnpfdb_-trigger-***" *** >URL 1, URL 2
warning3<button class="group flex items-* relative gap-* my-* mb-* outline-* whitespace-* font-* !ml-* first:!ml-* focus:outline-* text-* dark:text-*" id="radix-_R_20lcslubracf99absnpfdb_-trigger-***" *** >URL 1, URL 2
warning3<button class="group flex items-* relative gap-* my-* mb-* outline-* whitespace-* font-* !ml-* first:!ml-* focus:outline-* text-* dark:text-*" id="radix-_R_p2lcslubracf99absnpfdb_-trigger-***" *** >/docs/using-together-with-mastra
warning3<button class="group flex items-* relative gap-* my-* mb-* outline-* whitespace-* font-* !ml-* first:!ml-* focus:outline-* text-* dark:text-*" id="radix-_R_1qlcslubracf99absnpfdb_-trigger-***" *** >URL 1, URL 2
warning3<button class="group flex items-* relative gap-* my-* mb-* outline-* whitespace-* font-* !ml-* first:!ml-* focus:outline-* text-* dark:text-*" id="radix-_R_1olcslubracf99absnpfdb_-trigger-***" *** >URL 1, URL 2
warning3<button class="group flex items-* relative gap-* my-* mb-* outline-* whitespace-* font-* !ml-* first:!ml-* focus:outline-* text-* dark:text-*" id="radix-_R_2clcslubracf99absnpfdb_-trigger-***" *** >/docs/speech-to-text
warning3<button class="group flex items-* relative gap-* my-* mb-* outline-* whitespace-* font-* !ml-* first:!ml-* focus:outline-* text-* dark:text-*" id="radix-_R_2ilcslubracf99absnpfdb_-trigger-***" *** >/docs/speech-to-text
warning3<button class="group flex items-* relative gap-* my-* mb-* outline-* whitespace-* font-* !ml-* first:!ml-* focus:outline-* text-* dark:text-*" id="radix-_R_24lcslubracf99absnpfdb_-trigger-***" *** >/docs/text-to-speech
warning3<button class="group flex items-* relative gap-* my-* mb-* outline-* whitespace-* font-* !ml-* first:!ml-* focus:outline-* text-* dark:text-*" id="radix-_R_1elcslubracf99absnpfdb_-trigger-***" *** >/docs/function-calling
warning3<button class="group flex items-* relative gap-* my-* mb-* outline-* whitespace-* font-* !ml-* first:!ml-* focus:outline-* text-* dark:text-*" id="radix-_R_qilcslubracf99absnpfdb_-trigger-***" *** >/docs/using-together-with-mastra
warning3<a class="link lg:mint-* mint-* mint-* mint-* dark:mint-* dark:hover:mint-* mint-* mint-* dark:mint-* mint-* mint-* hover:mint-* mint-* mint-* md:mint-*" *** >/examples
warning3<button class="group flex items-* relative gap-* my-* mb-* outline-* whitespace-* font-* !ml-* first:!ml-* focus:outline-* text-* dark:text-*" id="radix-_R_lcslubracf99absnpfdb_-trigger-***" *** >/intro
warning3<button class="group flex items-* relative gap-* my-* mb-* outline-* whitespace-* font-* !ml-* first:!ml-* focus:outline-* text-* dark:text-*" id="radix-_R_1mlcslubracf99absnpfdb_-trigger-***" *** >URL 1, URL 2
warning3<button class="group flex items-* relative gap-* my-* mb-* outline-* whitespace-* font-* !ml-* first:!ml-* focus:outline-* text-* dark:text-*" id="radix-_R_2mlcslubracf99absnpfdb_-trigger-***" *** >URL 1, URL 2
warning2<button class="group flex items-* relative gap-* my-* mb-* outline-* whitespace-* font-* !ml-* first:!ml-* focus:outline-* text-* dark:text-*" id="radix-_R_25lcslubracf99absnpfdb_-trigger-***" *** >/docs/fine-tuning-quickstart
warning2<button class="group flex items-* relative gap-* my-* mb-* outline-* whitespace-* font-* !ml-* first:!ml-* focus:outline-* text-* dark:text-*" id="radix-_R_1lcslubracf99absnpfdb_-trigger-***" *** >/reference/dci-reference-jig
warning2<button class="group flex items-* relative gap-* my-* mb-* outline-* whitespace-* font-* !ml-* first:!ml-* focus:outline-* text-* dark:text-*" id="radix-_R_19lcslubracf99absnpfdb_-trigger-***" *** >/docs/ai-evaluations
warning2<a ***>URL 1, URL 2
You have reached the limit of 100 rows as a protection against very large output or exhausted memory.
No rows found, please edit your search term.

Missing roles

SeverityOccursDetailAffected URLs (max 5)
warning223<nav class="text-*">URL 1, URL 2, URL 3, URL 4, URL 5
warning222<header class="relative leading-*" id="header">URL 1, URL 2, URL 3, URL 4, URL 5
warning222<footer class="advanced-* flex flex-* items-* mx-* border-* border-* dark:border-*" id="footer">URL 1, URL 2, URL 3, URL 4, URL 5

Missing html lang attribute

No problems found.

Security

HeaderOKNoticeWarningCriticalRecommendation
Strict-Transport-Security002230Strict-Transport-Security header is set to max-age=2592000 which is less than 31 days. This can be a security risk.
Referrer-Policy002230Referrer-Policy header is not set. It controls referrer header sharing and enhances privacy and security.
Feature-Policy002230Feature-Policy header is not set. It allows enabling/disabling browser APIs and features for security. Not important if Permissions-Policy is set.
Permissions-Policy002230Permissions-Policy header is not set. It allows enabling/disabling browser APIs and features for security.
Server022300Server header is set to 'cloudflare'. It is better not to reveal used technologies.
X-Frame-Options223000
X-XSS-Protection223000
X-Content-Type-Options223000
Content-Security-Policy223000

Security headers

SeverityOccursDetailAffected URLs (max 5)
warning223Strict-Transport-Security header is set to max-age=2592000 which is less than 31 days. This can be a security risk.URL 1, URL 2, URL 3, URL 4, URL 5
warning223Feature-Policy header is not set. It allows enabling/disabling browser APIs and features for security. Not important if Permissions-Policy is set.URL 1, URL 2, URL 3, URL 4, URL 5
warning223Permissions-Policy header is not set. It allows enabling/disabling browser APIs and features for security.URL 1, URL 2, URL 3, URL 4, URL 5
warning223Referrer-Policy header is not set. It controls referrer header sharing and enhances privacy and security.URL 1, URL 2, URL 3, URL 4, URL 5
notice223Server header is set to 'cloudflare'. It is better not to reveal used technologies.URL 1, URL 2, URL 3, URL 4, URL 5

TOP non-unique titles

Count 🔽Title
2Supported Models - Together AI Docs
2Jig CLI - Together AI Docs
2Quickstart - Together AI Docs
2Sprocket SDK - Together AI Docs
2Introduction - Together AI Docs

TOP non-unique descriptions

Count 🔽Description
25

SEO metadata

Found 200 row(s).
URL 🔼IndexingTitleH1DescriptionKeywords
/docs/adapter-uploadAllowedUpload a LoRA Adapter - Together AI DocsUpload a LoRA AdapterBring Your Own Adapter: Upload your own LoRA adapter and run inference on Together AI
/docs/agent-integrationsAllowedAgent Integrations - Together AI DocsAgent IntegrationsUsing OSS agent frameworks with Together AI
/docs/agnoAllowedAgno - Together AI DocsAgnoUsing Agno with Together AI
/docs/ai-evaluationsAllowedLLM Evaluations - Together AI DocsLLM EvaluationsLearn how to run LLM-as-a-Judge evaluations
/docs/ai-evaluations-uiAllowedAI Evaluations UI - Together AI DocsAI Evaluations UIGuide to using the AI Evaluations UI for model assessment
/docs/ai-search-engineAllowedHow To Build An AI Search Engine (OSS Perplexity Clone) - Together AI DocsHow To Build An AI Search Engine (OSS Perplexity Clone)How to build an AI search engine inspired by Perplexity with Next.js and Together AI
/docs/ai-tutorAllowedHow To Build An Interactive AI Tutor With Llama 3.1 - Together AI DocsHow To Build An Interactive AI Tutor With Llama 3.1Learn we built LlamaTutor from scratch – an open source AI tutor with 90k users.
/docs/api-keys-authenticationAllowedAPI Keys & Authentication - Together AI DocsAPI Keys & AuthenticationCreate, manage, and authenticate with Project-scoped API keys
/docs/autogenAllowedAutoGen(AG2) - Together AI DocsAutoGen(AG2)Using AutoGen(AG2) with Together AI
/docs/batch-inferenceAllowedBatch - Together AI DocsBatchProcess jobs asynchronously with the Batch API.
/docs/billing-creditsAllowedCredits - Together AI DocsCreditsUnderstanding credits and billing basics on Together AI.
/docs/billing-payment-methodsAllowedPayment Methods & Invoices - Together AI DocsPayment Methods & InvoicesManaging payment cards, ACH transfers, viewing invoices, and updating billing details.
/docs/billing-troubleshootingAllowedBilling Troubleshooting - Together AI DocsBilling TroubleshootingResolving payment issues, understanding charges, and managing billing problems.
/docs/billing-usage-limitsAllowedUsage Limits & Analytics - Together AI DocsUsage Limits & AnalyticsUnderstanding account tiers, rate limits, model access, and cost analytics on Together AI.
/docs/building-a-rag-workflowAllowedBuilding a RAG Workflow - Together AI DocsBuilding a RAG WorkflowLearn how to build a RAG workflow with Together AI embedding and chat endpoints!
/docs/changelogAllowedChangelog - Together AI DocsChangelog
/docs/chat-overviewAllowedChat - Together AI DocsChatLearn how to query our open-source chat models.
/docs/cluster-storageAllowedCluster Storage - Together AI DocsCluster Storage
/docs/composioAllowedComposio - Together AI DocsComposioUsing Composio With Together AI
/docs/conditional-workflowsAllowedConditional Workflow - Together AI DocsConditional WorkflowAdapt to different tasks by conditionally navigating to various LLMs and tools.
/docs/containers-quickstartAllowedQuickstart - Together AI DocsQuickstartDeploy your first container in 20 minutes.
/docs/create-tickets-in-slackAllowedCreate Tickets In Slack - Together AI DocsCreate Tickets In SlackFor customers who have a shared Slack channel with us
/docs/crewaiAllowedCrewAI - Together AI DocsCrewAIUsing CrewAI with Together
/docs/custom-modelsAllowedUpload a Model - Together AI DocsUpload a ModelRun inference on your custom or fine-tuned models
/docs/data-analyst-agentAllowedBuilding An AI Data Analyst - Together AI DocsBuilding An AI Data AnalystLearn how to use code interpreter to build an AI data analyst with E2B and Together AI.
/docs/dedicated-container-inferenceAllowedIntroduction - Together AI DocsIntroductionDeploy custom containers on Together's managed GPU infrastructure with automatic scaling, job queues, and built-in observability.
/docs/dedicated-endpointsAllowedDedicated Endpoints FAQs - Together AI DocsDedicated Endpoints FAQs
/docs/dedicated-endpoints-uiAllowedDeploying Dedicated Endpoints - Together AI DocsDeploying Dedicated EndpointsGuide to creating dedicated endpoints via the web UI.
/docs/dedicated-inferenceAllowedDedicated Inference - Together AI DocsDedicated InferenceDeploy models on your own custom endpoints for improved reliability at scale
/docs/dedicated-modelsAllowedDedicated Models - Together AI DocsDedicated Models
/docs/dedicated_containers_imageAllowedImage Generation with Flux2 - Together AI DocsImage Generation with Flux2Deploy a Flux2 image generation model on Together's managed GPU infrastructure using Dedicated Containers.
/docs/dedicated_containers_videoAllowedVideo Generation with Wan 2.1 - Together AI DocsVideo Generation with Wan 2.1Deploy a multi-GPU video generation model on Together's managed GPU infrastructure using Dedicated Containers.
/docs/deepseek-3-1-quickstartAllowedDeepSeek V3.1 QuickStart - Together AI DocsDeepSeek V3.1 QuickStartHow to get started with DeepSeek V3.1
/docs/deepseek-faqsAllowedDeepSeek FAQs - Together AI DocsDeepSeek FAQs
/docs/deepseek-r1AllowedDeepSeek R1 Quickstart - Together AI DocsDeepSeek R1 QuickstartHow to get the most out of reasoning models like DeepSeek-R1.
/docs/deploying-a-fine-tuned-modelAllowedDeploying a Fine-tuned Model - Together AI DocsDeploying a Fine-tuned ModelOnce your fine-tune job completes, you should see your new model in your models dashboard.
/docs/deployment-optionsAllowedDeployment Options Overview - Together AI DocsDeployment Options OverviewCompare Together AI's deployment options: fully-managed cloud service vs. secure VPC deployment for enterprises.
/docs/deployments-jigAllowedJig CLI - Together AI DocsJig CLIBuild, push, and deploy containers to Together's managed GPU infrastructure.
/docs/deployments-queueAllowedQueue API - Together AI DocsQueue APISubmit, monitor, and manage asynchronous jobs for your Dedicated Container deployments.
/docs/deployments-sprocketAllowedSprocket SDK - Together AI DocsSprocket SDKA Python SDK for building inference workers that support both synchronous and asynchronous requests via Together's platform.
/docs/deprecationsAllowedDeprecations - Together AI DocsDeprecations
/docs/dspyAllowedDSPy - Together AI DocsDSPyUsing DSPy with Together AI
/docs/embeddings-overviewAllowedEmbeddings - Together AI DocsEmbeddingsLearn how to get an embedding vector for a given text input.
/docs/embeddings-ragAllowedRAG Integrations - Together AI DocsRAG Integrations
/docs/error-codesAllowedError Codes - Together AI DocsError CodesAn overview on error status codes, causes, and quick fix solutions
/docs/evaluations-supported-modelsAllowedSupported Models - Together AI DocsSupported ModelsSupported models for Evaluations
/docs/fine-tuning-byomAllowedFine-tuning BYOM - Together AI DocsFine-tuning BYOMBring Your Own Model: Fine-tune Custom Models from the Hugging Face Hub
/docs/fine-tuning-data-preparationAllowedData Preparation - Together AI DocsData PreparationTogether Fine-tuning API accepts two data formats for training dataset files: text data and tokenized data (in the form of Parquet files). Below, you can learn about different types of those formats and the scenarios in which they can be most useful.
/docs/fine-tuning-faqsAllowedFine Tuning FAQs - Together AI DocsFine Tuning FAQs
/docs/fine-tuning-function-callingAllowedFunction Calling Fine-tuning - Together AI DocsFunction Calling Fine-tuningLearn how to fine-tune models with function calling capabilities using Together AI.
/docs/fine-tuning-lora-supported-modulesAllowedLoRA Supported Modules - Together AI DocsLoRA Supported ModulesSupported target modules for LoRA fine-tuning by model
/docs/fine-tuning-modelsAllowedSupported Models - Together AI DocsSupported ModelsA list of all the models available for fine-tuning.
/docs/fine-tuning-pricingAllowedPricing - Together AI DocsPricingFine-tuning pricing at Together AI is based on the total number of tokens processed during your job.
/docs/fine-tuning-quickstartAllowedFine-tuning Guide - Together AI DocsFine-tuning GuideLearn the basics and best practices of fine-tuning large language models.
/docs/fine-tuning-reasoningAllowedReasoning Fine-tuning - Together AI DocsReasoning Fine-tuningLearn how to fine-tune reasoning models with chain-of-thought data using Together AI.
/docs/fine-tuning-vlmAllowedVision-Language Fine-tuning - Together AI DocsVision-Language Fine-tuningLearn how to fine-tune Vision-Language Models (VLMs) on image+text data using Together AI.
/docs/function-callingAllowedFunction Calling - Together AI DocsFunction CallingLearn how to get LLMs to respond to queries with named functions and structured arguments.
/docs/glm-5-quickstartAllowedGLM-5 Quickstart - Together AI DocsGLM-5 QuickstartHow to get the most out of GLM-5 for reasoning and agentic tasks.
/docs/gpt-ossAllowedOpenAI GPT-OSS Quickstart - Together AI DocsOpenAI GPT-OSS QuickstartGet started with OpenAI's GPT-OSS, open-source reasoning model duo.
/docs/gpu-clusters-apiAllowedAPI & Integrations - Together AI DocsAPI & IntegrationsManage clusters programmatically with CLI, REST API, Terraform, and third-party tools
/docs/gpu-clusters-billingAllowedBilling & Pricing - Together AI DocsBilling & PricingUnderstand billing, pricing, and lifecycle policies for GPU Clusters
/docs/gpu-clusters-managementAllowedCluster Management - Together AI DocsCluster ManagementManage, scale, and operate your GPU clusters
/docs/gpu-clusters-overviewAllowedGPU Clusters Overview - Together AI DocsGPU Clusters OverviewHigh-performance GPU clusters for training, fine-tuning, and large-scale AI workloads
/docs/gpu-clusters-quickstartAllowedQuickstart: Create Your First Cluster - Together AI DocsQuickstart: Create Your First ClusterGet started with GPU Clusters in minutes
/docs/guidesAllowedGuides Homepage - Together AI DocsGuides HomepageQuickstarts and step-by-step guides for building with Together AI.
/docs/health-checksAllowedHealth Checks and Node Repair - Together AI DocsHealth Checks and Node RepairProactively validate GPU node health and trigger repair actions for issues
/docs/how-to-build-a-lovable-clone-with-kimi-k2AllowedHow to build a Lovable clone with Kimi K2 - Together AI DocsHow to build a Lovable clone with Kimi K2Learn how to build a full-stack Next.js app that can generate React apps with a single prompt.
/docs/how-to-build-coding-agentsAllowedHow to Build Coding Agents - Together AI DocsHow to Build Coding AgentsHow to build your own simple code editing agent from scratch in 400 lines of code!
/docs/how-to-build-phone-voice-agentAllowedBuild a Phone Voice Agent with Together AI - Together AI DocsBuild a Phone Voice Agent with Together AIBuild a real-time phone voice agent from scratch with Twilio Media Streams, Together AI realtime STT, chat completions, realtime TTS, and local voice activity detection.
/docs/how-to-build-real-time-audio-transcription-appAllowedHow to build an AI audio transcription app with Whisper - Together AI DocsHow to build an AI audio transcription app with WhisperLearn how to build a real-time AI audio transcription app with Whisper, Next.js, and Together AI.
/docs/how-to-implement-contextual-rag-from-anthropicAllowedHow To Implement Contextual RAG From Anthropic - Together AI DocsHow To Implement Contextual RAG From AnthropicAn open source line-by-line implementation and explanation of Contextual RAG from Anthropic!
/docs/how-to-improve-search-with-rerankersAllowedHow To Improve Search With Rerankers - Together AI DocsHow To Improve Search With RerankersLearn how you can improve semantic search quality with reranker models!
/docs/how-to-use-clineAllowedHow to use Cline with DeepSeek V3 to build faster - Together AI DocsHow to use Cline with DeepSeek V3 to build fasterUse Cline (an AI coding agent) with DeepSeek V3 (a powerful open source model) to code faster.
/docs/how-to-use-openclawAllowedQuickstart: How to Use OpenClaw with Together AI - Together AI DocsQuickstart: How to Use OpenClaw with Together AILearn how to pair OpenClaw, a powerful autonomous agent, with frontier OSS models on Together AI like Kimi K2.5 and GLM 4.7.
/docs/how-to-use-opencodeAllowedHow to use OpenCode with Together AI to build faster - Together AI DocsHow to use OpenCode with Together AI to build fasterLearn how to combine OpenCode, a powerful terminal-based AI coding agent, with Together AI models like DeepSeek V3 to supercharge your development workflow.
/docs/how-to-use-qwen-codeAllowedHow to use Qwen Code with Together AI for enhanced development workflow - Together AI DocsHow to use Qwen Code with Together AI for enhanced development workflowLearn how to configure Qwen Code, a powerful AI-powered command-line workflow tool, with Together AI models to supercharge your coding workflow with advanced code understanding and automation.
/docs/identity-access-managementAllowedTogether's IAM Model - Together AI DocsTogether's IAM ModelHow users, credentials, and resources are organized across the Together platform
/docs/images-overviewAllowedImage Generation - Together AI DocsImage GenerationGenerate high-quality images from text + image prompts.
/docs/inference-faqsAllowedInference FAQs - Together AI DocsInference FAQs
/docs/inference-parametersAllowedParameters - Together AI DocsParametersLearn more about the parameters you can configure when running inference.
/docs/inference-web-interfaceAllowedPlayground - Together AI DocsPlaygroundGuide to using Together AI's web playground for interactive AI model inference across chat, image, video, audio, and transcribe models.
/docs/integrationsAllowedIntegrations - Together AI DocsIntegrationsUse Together AI models through partner integrations.
/docs/iterative-workflowAllowedIterative Workflow - Together AI DocsIterative WorkflowIteratively call LLMs to optimize task performance.
/docs/json-modeAllowedStructured Outputs - Together AI DocsStructured OutputsLearn how to use JSON mode to get structured outputs from LLMs like DeepSeek V3 & Llama 3.3.
/docs/kimi-k2-quickstartAllowedKimi K2 QuickStart - Together AI DocsKimi K2 QuickStartHow to get the most out of models like Kimi K2.
/docs/kimi-k2-thinking-quickstartAllowedKimi K2 Thinking QuickStart - Together AI DocsKimi K2 Thinking QuickStartHow to get the most out of reasoning models like Kimi K2 Thinking.
/docs/langgraphAllowedLangGraph - Together AI DocsLangGraphUsing LangGraph with Together AI
/docs/llama4-quickstartAllowedLlama 4 Quickstart - Together AI DocsLlama 4 QuickstartHow to get the most out of the new Llama 4 models.
/docs/logprobsAllowedGetting Started with Logprobs - Together AI DocsGetting Started with LogprobsLearn how to return log probabilities for your output tokens & build better classifiers.
/docs/lora-training-and-inferenceAllowedLoRA Fine-Tuning and Inference - Together AI DocsLoRA Fine-Tuning and InferenceFine-tune and run inference for a model with LoRA adapters
/docs/mcpAllowedTogether AI MCP Server - Together AI DocsTogether AI MCP ServerInstall our MCP server in Cursor, Claude Code, or OpenCode in 1 click.
/docs/mixture-of-agentsAllowedTogether Mixture Of Agents (MoA) - Together AI DocsTogether Mixture Of Agents (MoA)
/docs/nanochat-on-instant-clustersAllowedHow to run nanochat on Instant Clusters⚡️ - Together AI DocsHow to run nanochat on Instant Clusters⚡️Learn how to train Andrej Karpathy's end-to-end ChatGPT clone on Together's on-demand GPU clusters
/docs/nextjs-chat-quickstartAllowedQuickstart: Next.Js - Together AI DocsQuickstart: Next.JsBuild an app that can ask a single question or chat with an LLM using Next.js and Together AI.
/docs/open-notebooklm-pdf-to-podcastAllowedHow To Build An Open Source NotebookLM: PDF To Podcast - Together AI DocsHow To Build An Open Source NotebookLM: PDF To PodcastIn this guide we will see how to create a podcast like the one below from a PDF input!
/docs/openai-api-compatibilityAllowedOpenAI Compatibility - Together AI DocsOpenAI CompatibilityTogether's API is compatible with OpenAI's libraries, making it easy to try out our open-source models on existing applications.
/docs/organizationsAllowedOrganizations - Together AI DocsOrganizationsCreate and manage your Together Organization, invite Members, and configure billing
/docs/parallel-workflowsAllowedParallel Workflow - Together AI DocsParallel WorkflowExecute multiple LLM calls in parallel and aggregate afterwards.
/docs/preference-fine-tuningAllowedPreference Fine-Tuning - Together AI DocsPreference Fine-TuningLearn how to use preference fine-tuning on Together Fine-Tuning Platform
/docs/projectsAllowedProjects - Together AI DocsProjectsCreate isolated workspaces to organize resources, manage team access, and scope API keys
/docs/prompting-deepseek-r1AllowedPrompting DeepSeek R1 - Together AI DocsPrompting DeepSeek R1Prompt engineering for DeepSeek-R1.
/docs/pydanticaiAllowedPydanticAI - Together AI DocsPydanticAIUsing PydanticAI with Together
/docs/pythonv2-migration-guideAllowedPython v2 SDK Migration Guide - Together AI DocsPython v2 SDK Migration GuideMigrate from Together Python v1 to v2 - the new Together AI Python SDK with improved type safety and modern architecture.
/docs/quickstartAllowedQuickstart - Together AI DocsQuickstartGet up to speed with our API in one minute.
/docs/quickstart-fluxAllowedQuickstart: FLUX.2 - Together AI DocsQuickstart: FLUX.2Learn how to use FLUX.2, the next generation image model with advanced prompting capabilities
/docs/quickstart-flux-kontextAllowedQuickstart: Flux Kontext - Together AI DocsQuickstart: Flux KontextLearn how to use Flux's new in-context image generation models
/docs/quickstart-flux-loraAllowedQuickstart: Flux LoRA Inference - Together AI DocsQuickstart: Flux LoRA Inference
/docs/quickstart-how-to-do-ocrAllowedQuickstart: How to do OCR - Together AI DocsQuickstart: How to do OCRA step by step guide on how to do OCR with Together AI's vision models with structured outputs
/docs/quickstart-retrieval-augmented-generation-ragAllowedQuickstart: Retrieval Augmented Generation (RAG) - Together AI DocsQuickstart: Retrieval Augmented Generation (RAG)How to build a RAG workflow in under 5 mins!
/docs/quickstart-using-hugging-face-inferenceAllowedQuickstart: Using Hugging Face Inference With Together - Together AI DocsQuickstart: Using Hugging Face Inference With TogetherThis guide will walk you through how to use Together models with Hugging Face Inference.
/docs/rate-limitsAllowedInference Rate Limits - Together AI DocsInference Rate LimitsRate limits restrict how often a user or client can access our API within a set timeframe.
/docs/reasoning-models-guideAllowedReasoning Models Guide - Together AI DocsReasoning Models GuideHow reasoning models like DeepSeek-R1 work.
/docs/reasoning-overviewAllowedReasoning - Together AI DocsReasoningLearn how to use reasoning models that think step-by-step before answering.
/docs/recommended-modelsAllowedRecommended Models - Together AI DocsRecommended ModelsFind the right models for your use case
/docs/rerank-overviewAllowedRerank - Together AI DocsRerankLearn how to improve the relevance of your search and RAG systems with reranking.
/docs/roles-permissionsAllowedRoles & Permissions (RBAC) - Together AI DocsRoles & Permissions (RBAC)Understand Organization and Project role-based access control (RBAC) including Admin and Member roles and what each can do across the Together platform
/docs/sequential-agent-workflowAllowedSequential Workflow - Together AI DocsSequential WorkflowCoordinating a chain of LLM calls to solve a complex task.
/docs/serverless-modelsAllowedServerless Models - Together AI DocsServerless Models
/docs/slurmAllowedSlurm Management System - Together AI DocsSlurm Management System
/docs/slurm-configurationAllowedSlurm Configuration - Together AI DocsSlurm ConfigurationCustomize Slurm cluster settings to match your workload requirements
/docs/speech-to-textAllowedSpeech-to-Text - Together AI DocsSpeech-to-TextLearn how to transcribe and translate audio into text!
/docs/ssoAllowedSingle Sign-On (SSO) - Together AI DocsSingle Sign-On (SSO)Connect your Identity Provider for secure, automated team access to Together
/docs/support-ticket-portalAllowedCustomer Ticket Portal - Together AI DocsCustomer Ticket Portal
/docs/text-to-speechAllowedText-to-Speech - Together AI DocsText-to-SpeechLearn how to use the text-to-speech functionality supported by Together AI.
/docs/together-code-interpreterAllowedTogether Code Interpreter - Together AI DocsTogether Code InterpreterExecute LLM-generated code seamlessly with a simple API call.
/docs/together-code-sandboxAllowedTogether Code Sandbox - Together AI DocsTogether Code SandboxLevel-up generative code tooling with fast, secure code sandboxes at scale
/docs/together-deploymentsAllowedPlatform Overview - Together AI DocsPlatform OverviewArchitecture, deployment lifecycle, and core concepts for Dedicated Container Inference.
/docs/using-together-with-mastraAllowedQuickstart: Using Mastra with Together AI - Together AI DocsQuickstart: Using Mastra with Together AIThis guide will walk you through how to use Together models with Mastra.
/docs/using-together-with-vercels-ai-sdkAllowedQuickstart: Using Vercel AI SDK With Together AI - Together AI DocsQuickstart: Using Vercel AI SDK With Together AIThis guide will walk you through how to use Together models with the Vercel AI SDK.
/docs/videos-overviewAllowedVideo Generation - Together AI DocsVideo GenerationGenerate high-quality videos from text and image prompts.
/docs/vision-overviewAllowedVision LLMs - Together AI DocsVision LLMsLearn how to use the vision models supported by Together AI.
/docs/workflowsAllowedAgent Workflows - Together AI DocsAgent WorkflowsOrchestrating together multiple language model calls to solve complex tasks.
/examplesAllowedTogether Cookbooks & Example Apps - Together AI DocsTogether cookbooks & example appsExplore our vast library of open-source cookbooks & example apps
/introAllowedOverview - Together AI DocsOverviewWelcome to Together AI’s docs! Together makes it easy to run, finetune, and train open source AI models with transparency and privacy.
/reference/audio-speechAllowedCreate Audio Generation Request - Together AI DocsCreate Audio Generation RequestGenerate audio from input text
/reference/audio-speech-websocketAllowedCreate realtime text-to-speech - Together AI DocsCreate realtime text-to-speechEstablishes a WebSocket connection for real-time text-to-speech generation. This endpoint uses WebSocket protocol (wss://api.together.ai/v1/audio/speech/websocket) for bidirectional streaming communication. Connection Setup: - Protocol: WebSocket (wss://) - Authentication: Pass API key as Bearer token in Authorization header - Parameters: Sent as query parameters (model, voice, max_partial_length) Client Events: - tts_session.updated: Update session parameters like voice json { "type": "tts_session.updated", "session": { "voice": "tara" } } - input_text_buffer.append: Send text chunks for TTS generation json { "type": "input_text_buffer.append", "text": "Hello, this is a test." } - input_text_buffer.clear: Clear the buffered text json { "type": "input_text_buffer.clear" } - input_text_buffer.commit: Signal end of text input and process remaining text json { "type": "input_text_buffer.commit" } Server Events: - session.created: Initial session confirmation (sent first) json { "event_id": "evt_123456", "type": "session.created", "session": { "id": "session-id", "object": "realtime.tts.session", "modalities": ["text", "audio"], "model": "hexgrad/Kokoro-82M", "voice": "tara" } } - conversation.item.input_text.received: Acknowledgment that text was received json { "type": "conversation.item.input_text.received", "text": "Hello, this is a test." } - conversation.item.audio_output.delta: Audio chunks as base64-encoded data json { "type": "conversation.item.audio_output.delta", "item_id": "tts_1", "delta": "" } - conversation.item.audio_output.done: Audio generation complete for an item json { "type": "conversation.item.audio_output.done", "item_id": "tts_1" } - conversation.item.tts.failed: Error occurred json { "type": "conversation.item.tts.failed", "error": { "message": "Error description", "type": "invalid_request_error", "param": null, "code": "invalid_api_key" } } Text Processing: - Partial text (no sentence ending) is held in buffer until: - We believe that the text is complete enough to be processed for TTS generation - The partial text exceeds max_partial_length characters (default: 250) - The input_text_buffer.commit event is received Audio Format: - Format: WAV (PCM s16le) - Sample Rate: 24000 Hz - Encoding: Base64 - Delivered via conversation.item.audio_output.delta events Error Codes: - invalid_api_key: Invalid API key provided (401) - missing_api_key: Authorization header missing (401) - model_not_available: Invalid or unavailable model (400) - Invalid text format errors (400)
/reference/audio-transcriptionsAllowedCreate an Audio Transcription - Together AI DocsCreate an Audio TranscriptionTranscribes audio into text
/reference/audio-transcriptions-realtimeAllowedCreate a realtime audio transcription - Together AI DocsCreate a realtime audio transcriptionEstablishes a WebSocket connection for real-time audio transcription. This endpoint uses WebSocket protocol (wss://api.together.ai/v1/realtime) for bidirectional streaming communication. Connection Setup: - Protocol: WebSocket (wss://) - Authentication: Pass API key as Bearer token in Authorization header - Parameters: Sent as query parameters (model, input_audio_format) Client Events: - input_audio_buffer.append: Send audio chunks as base64-encoded data json { "type": "input_audio_buffer.append", "audio": "" } - input_audio_buffer.commit: Signal end of audio stream json { "type": "input_audio_buffer.commit" } Server Events: - session.created: Initial session confirmation (sent first) json { "type": "session.created", "session": { "id": "session-id", "object": "realtime.session", "modalities": ["audio"], "model": "openai/whisper-large-v3" } } - conversation.item.input_audio_transcription.delta: Partial transcription results json { "type": "conversation.item.input_audio_transcription.delta", "delta": "The quick brown" } - conversation.item.input_audio_transcription.completed: Final transcription json { "type": "conversation.item.input_audio_transcription.completed", "transcript": "The quick brown fox jumps over the lazy dog" } - conversation.item.input_audio_transcription.failed: Error occurred json { "type": "conversation.item.input_audio_transcription.failed", "error": { "message": "Error description", "type": "invalid_request_error", "param": null, "code": "invalid_api_key" } } Error Codes: - invalid_api_key: Invalid API key provided (401) - missing_api_key: Authorization header missing (401) - model_not_available: Invalid or unavailable model (400) - Unsupported audio format errors (400)
/reference/audio-translationsAllowedCreate an Audio Translation - Together AI DocsCreate an Audio TranslationTranslates audio into English
/reference/authenticationAllowedAuthentication - Together AI DocsAuthentication
/reference/batch-cancelAllowedCancel a batch job - Together AI DocsCancel a batch jobCancel a batch job by ID
/reference/batch-createAllowedCreate a batch job - Together AI DocsCreate a batch jobCreate a new batch job with the given input file and endpoint
/reference/batch-getAllowedGet a batch job - Together AI DocsGet a batch jobGet details of a batch job by ID
/reference/batch-listAllowedList all batch jobs - Together AI DocsList all batch jobsList all batch jobs for the authenticated user
/reference/chat-completionsAllowedCreate Chat Completion - Together AI DocsCreate Chat CompletionGenerate a model response for a given chat conversation. Supports single queries and multi-turn conversations with system, user, and assistant messages.
/reference/cli/beta-introAllowedIntroduction - Together AI DocsIntroductionDocumentation for using beta features with the Together Python SDK / CLI.
/reference/cli/clustersAllowedClusters - Together AI DocsClusters
/reference/cli/endpointsAllowedEndpoints - Together AI DocsEndpointsCreate, update and delete endpoints via the CLI
/reference/cli/evalsAllowedEvals - Together AI DocsEvalsManage model evaluation jobs
/reference/cli/filesAllowedFiles - Together AI DocsFiles
/reference/cli/finetuneAllowedFine Tuning - Together AI DocsFine Tuning
/reference/cli/getting-startedAllowedGetting Started - Together AI DocsGetting StartedGet started with Together's Python CLI (together).
/reference/cli/jig-redirect-stubAllowedContainers (Jig) - Together AI DocsContainers (Jig)CLI commands and configuration for Dedicated Containers.
/reference/cli/modelsAllowedModels - Together AI DocsModels
/reference/clusters-createAllowedCreate a Cluster - Together AI DocsCreate a ClusterCreate an Instant Cluster on Together's high-performance GPU clusters. With features like on-demand scaling, long-lived resizable high-bandwidth shared DC-local storage, Kubernetes and Slurm cluster flavors, a REST API, and Terraform support, you can run workloads flexibly without complex infrastructure management.
/reference/clusters-deleteAllowedDelete a Cluster - Together AI DocsDelete a ClusterDelete a GPU cluster by cluster ID.
/reference/clusters-getAllowedRetrieve Cluster - Together AI DocsRetrieve ClusterRetrieve information about a specific GPU cluster.
/reference/clusters-listAllowedList all Clusters - Together AI DocsList all ClustersList all GPU clusters.
/reference/clusters-list-regionsAllowedList compute region capabilities - Together AI DocsList compute region capabilities
/reference/clusters-updateAllowedUpdate or Scale GPU Cluster - Together AI DocsUpdate or Scale GPU ClusterUpdate the configuration of an existing GPU cluster.
/reference/clusters_storages-createAllowedCreate a shared volume - Together AI DocsCreate a shared volumeInstant Clusters supports long-lived, resizable in-DC shared storage with user data persistence. You can dynamically create and attach volumes to your cluster at cluster creation time, and resize as your data grows. All shared storage is backed by multi-NIC bare metal paths, ensuring high-throughput and low-latency performance for shared storage.
/reference/clusters_storages-deleteAllowedDelete a shared volume - Together AI DocsDelete a shared volumeDelete a shared volume. Note that if this volume is attached to a cluster, deleting will fail.
/reference/clusters_storages-getAllowedRetrieve a shared volumes - Together AI DocsRetrieve a shared volumesRetrieve information about a specific shared volume.
/reference/clusters_storages-listAllowedList shared volumes - Together AI DocsList shared volumesList all shared volumes.
/reference/clusters_storages-updateAllowedUpdate a shared volume - Together AI DocsUpdate a shared volumeUpdate the configuration of an existing shared volume.
/reference/completionsAllowedCreate Completion - Together AI DocsCreate CompletionGenerate text completions for a given prompt using a language, code, or image model.
/reference/create-evaluationAllowedCreate Evaluation - Together AI DocsCreate Evaluation
/reference/create-videosAllowedCreate Video - Together AI DocsCreate VideoCreate a video
/reference/createendpointAllowedCreate A Dedicated Endpoint - Together AI DocsCreate A Dedicated EndpointCreates a new dedicated endpoint for serving models. The endpoint will automatically start after creation. You can deploy any supported model on hardware configurations that meet the model's requirements.
/reference/dci-reference-jigAllowedJig CLI - Together AI DocsJig CLICLI commands, pyproject.toml configuration, environment variables, and Python SDK for Dedicated Containers.
/reference/dci-reference-sprocketAllowedSprocket SDK - Together AI DocsSprocket SDKAPI reference for Sprocket classes, functions, and configuration.
/reference/delete-files-idAllowedDelete A File - Together AI DocsDelete A FileDelete a previously uploaded data file.
/reference/delete-fine-tunes-idAllowedDelete A Fine-tuning Event - Together AI DocsDelete A Fine-tuning EventDelete a fine-tuning job.
/reference/deleteendpointAllowedDelete Endpoint - Together AI DocsDelete EndpointPermanently deletes an endpoint. This action cannot be undone.
/reference/deployments-createAllowedCreate Deployment - Together AI DocsCreate DeploymentCreate a new deployment with specified configuration
/reference/deployments-deleteAllowedDelete Deployment - Together AI DocsDelete DeploymentDelete an existing deployment
/reference/deployments-getAllowedGet Deployment - Together AI DocsGet DeploymentRetrieve details of a specific deployment by its ID or name
/reference/deployments-listAllowedList Deployments - Together AI DocsList DeploymentsGet a list of all deployments in your project
/reference/deployments-logsAllowedGet Deployment Logs - Together AI DocsGet Deployment LogsRetrieve logs from a deployment, optionally filtered by replica ID.
/reference/deployments-secrets-createAllowedCreate Secret - Together AI DocsCreate SecretCreate a new secret to store sensitive configuration values
/reference/deployments-secrets-deleteAllowedDelete Secret - Together AI DocsDelete SecretDelete an existing secret
/reference/deployments-secrets-getAllowedGet Secret - Together AI DocsGet SecretRetrieve details of a specific secret by its ID or name
/reference/deployments-secrets-listAllowedList Secrets - Together AI DocsList SecretsRetrieve all secrets in your project
/reference/deployments-secrets-updateAllowedUpdate Secret - Together AI DocsUpdate SecretUpdate an existing secret's value or metadata
/reference/deployments-storage-getAllowedGet Storage File - Together AI DocsGet Storage FileDownload a file by redirecting to a signed URL
/reference/deployments-storage-volumes-createAllowedCreate Storage Volume - Together AI DocsCreate Storage VolumeCreate a new volume to preload files in deployments
/reference/deployments-storage-volumes-deleteAllowedDelete Storage Volume - Together AI DocsDelete Storage VolumeDelete an existing volume
/reference/deployments-storage-volumes-getAllowedGet Storage Volume - Together AI DocsGet Storage VolumeRetrieve details of a specific volume by its ID or name
/reference/deployments-storage-volumes-listAllowedList Storage Volumes - Together AI DocsList Storage VolumesRetrieve all volumes in your project
/reference/deployments-storage-volumes-updateAllowedUpdate Storage Volume - Together AI DocsUpdate Storage VolumeUpdate an existing volume's configuration or contents
/reference/deployments-updateAllowedUpdate Deployment - Together AI DocsUpdate DeploymentUpdate an existing deployment configuration
/reference/embeddingsAllowedCreate Embedding - Together AI DocsCreate EmbeddingGenerate vector embeddings for one or more text inputs. Returns numerical arrays representing semantic meaning, useful for search, classification, and retrieval.
/reference/get-evaluationAllowedGet Evaluation - Together AI DocsGet Evaluation
/reference/get-evaluation-statusAllowedGet Evaluation Status - Together AI DocsGet Evaluation Status
/reference/get-filesAllowedList All Files - Together AI DocsList All FilesList the metadata for all uploaded data files.
/reference/get-files-idAllowedList File - Together AI DocsList FileRetrieve the metadata for a single uploaded data file.
/reference/get-files-id-contentAllowedGet File Contents - Together AI DocsGet File ContentsGet the contents of a single uploaded data file.
/reference/get-fine-tunesAllowedList All Jobs - Together AI DocsList All JobsList the metadata for all fine-tuning jobs. Returns a list of FinetuneResponseTruncated objects.
/reference/get-fine-tunes-idAllowedList Job - Together AI DocsList JobList the metadata for a single fine-tuning job.
/reference/get-fine-tunes-id-checkpointAllowedList checkpoints - Together AI DocsList checkpointsList the checkpoints for a single fine-tuning job.
You have reached the hard limit of 200 rows as a protection against very large output or exhausted memory. You can change this with --rows-limit.
No rows found, please edit your search term.

OpenGraph metadata

Found 200 row(s).
URL 🔼OG TitleOG DescriptionOG ImageTwitter TitleTwitter DescriptionTwitter Image
/docs/adapter-uploadUpload a LoRA Adapter - Together AI DocsBring Your Own Adapter: Upload your own LoRA adapter and run inference on Together AIhttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Upload a LoRA Adapter - Together AI DocsBring Your Own Adapter: Upload your own LoRA adapter and run inference on Together AIhttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/agent-integrationsAgent Integrations - Together AI DocsUsing OSS agent frameworks with Together AIhttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Agent Integrations - Together AI DocsUsing OSS agent frameworks with Together AIhttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/agnoAgno - Together AI DocsUsing Agno with Together AIhttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Agno - Together AI DocsUsing Agno with Together AIhttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/ai-evaluationsLLM Evaluations - Together AI DocsLearn how to run LLM-as-a-Judge evaluationshttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100LLM Evaluations - Together AI DocsLearn how to run LLM-as-a-Judge evaluationshttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/ai-evaluations-uiAI Evaluations UI - Together AI DocsGuide to using the AI Evaluations UI for model assessmenthttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100AI Evaluations UI - Together AI DocsGuide to using the AI Evaluations UI for model assessmenthttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/ai-search-engineHow To Build An AI Search Engine (OSS Perplexity Clone) - Together AI DocsHow to build an AI search engine inspired by Perplexity with Next.js and Together AIhttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100How To Build An AI Search Engine (OSS Perplexity Clone) - Together AI DocsHow to build an AI search engine inspired by Perplexity with Next.js and Together AIhttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/ai-tutorHow To Build An Interactive AI Tutor With Llama 3.1 - Together AI DocsLearn we built LlamaTutor from scratch – an open source AI tutor with 90k users.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100How To Build An Interactive AI Tutor With Llama 3.1 - Together AI DocsLearn we built LlamaTutor from scratch – an open source AI tutor with 90k users.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/api-keys-authenticationAPI Keys & Authentication - Together AI DocsCreate, manage, and authenticate with Project-scoped API keyshttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100API Keys & Authentication - Together AI DocsCreate, manage, and authenticate with Project-scoped API keyshttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/autogenAutoGen(AG2) - Together AI DocsUsing AutoGen(AG2) with Together AIhttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100AutoGen(AG2) - Together AI DocsUsing AutoGen(AG2) with Together AIhttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/batch-inferenceBatch - Together AI DocsProcess jobs asynchronously with the Batch API.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Batch - Together AI DocsProcess jobs asynchronously with the Batch API.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/billing-creditsCredits - Together AI DocsUnderstanding credits and billing basics on Together AI.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Credits - Together AI DocsUnderstanding credits and billing basics on Together AI.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/billing-payment-methodsPayment Methods & Invoices - Together AI DocsManaging payment cards, ACH transfers, viewing invoices, and updating billing details.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Payment Methods & Invoices - Together AI DocsManaging payment cards, ACH transfers, viewing invoices, and updating billing details.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/billing-troubleshootingBilling Troubleshooting - Together AI DocsResolving payment issues, understanding charges, and managing billing problems.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Billing Troubleshooting - Together AI DocsResolving payment issues, understanding charges, and managing billing problems.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/billing-usage-limitsUsage Limits & Analytics - Together AI DocsUnderstanding account tiers, rate limits, model access, and cost analytics on Together AI.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Usage Limits & Analytics - Together AI DocsUnderstanding account tiers, rate limits, model access, and cost analytics on Together AI.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/building-a-rag-workflowBuilding a RAG Workflow - Together AI DocsLearn how to build a RAG workflow with Together AI embedding and chat endpoints!https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Building a RAG Workflow - Together AI DocsLearn how to build a RAG workflow with Together AI embedding and chat endpoints!https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/changelogChangelog - Together AI Docshttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Changelog - Together AI Docshttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/chat-overviewChat - Together AI DocsLearn how to query our open-source chat models.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Chat - Together AI DocsLearn how to query our open-source chat models.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/cluster-storageCluster Storage - Together AI Docshttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Cluster Storage - Together AI Docshttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/composioComposio - Together AI DocsUsing Composio With Together AIhttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Composio - Together AI DocsUsing Composio With Together AIhttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/conditional-workflowsConditional Workflow - Together AI DocsAdapt to different tasks by conditionally navigating to various LLMs and tools.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Conditional Workflow - Together AI DocsAdapt to different tasks by conditionally navigating to various LLMs and tools.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/containers-quickstartQuickstart - Together AI DocsDeploy your first container in 20 minutes.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Quickstart - Together AI DocsDeploy your first container in 20 minutes.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/create-tickets-in-slackCreate Tickets In Slack - Together AI DocsFor customers who have a shared Slack channel with ushttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Create Tickets In Slack - Together AI DocsFor customers who have a shared Slack channel with ushttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/crewaiCrewAI - Together AI DocsUsing CrewAI with Togetherhttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100CrewAI - Together AI DocsUsing CrewAI with Togetherhttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/custom-modelsUpload a Model - Together AI DocsRun inference on your custom or fine-tuned modelshttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Upload a Model - Together AI DocsRun inference on your custom or fine-tuned modelshttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/data-analyst-agentBuilding An AI Data Analyst - Together AI DocsLearn how to use code interpreter to build an AI data analyst with E2B and Together AI.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Building An AI Data Analyst - Together AI DocsLearn how to use code interpreter to build an AI data analyst with E2B and Together AI.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/dedicated-container-inferenceIntroduction - Together AI DocsDeploy custom containers on Together's managed GPU infrastructure with automatic scaling, job queues, and built-in observability.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Introduction - Together AI DocsDeploy custom containers on Together's managed GPU infrastructure with automatic scaling, job queues, and built-in observability.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/dedicated-endpointsDedicated Endpoints FAQs - Together AI Docshttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Dedicated Endpoints FAQs - Together AI Docshttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/dedicated-endpoints-uiDeploying Dedicated Endpoints - Together AI DocsGuide to creating dedicated endpoints via the web UI.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Deploying Dedicated Endpoints - Together AI DocsGuide to creating dedicated endpoints via the web UI.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/dedicated-inferenceDedicated Inference - Together AI DocsDeploy models on your own custom endpoints for improved reliability at scalehttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Dedicated Inference - Together AI DocsDeploy models on your own custom endpoints for improved reliability at scalehttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/dedicated-modelsDedicated Models - Together AI Docshttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Dedicated Models - Together AI Docshttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/dedicated_containers_imageImage Generation with Flux2 - Together AI DocsDeploy a Flux2 image generation model on Together's managed GPU infrastructure using Dedicated Containers.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Image Generation with Flux2 - Together AI DocsDeploy a Flux2 image generation model on Together's managed GPU infrastructure using Dedicated Containers.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/dedicated_containers_videoVideo Generation with Wan 2.1 - Together AI DocsDeploy a multi-GPU video generation model on Together's managed GPU infrastructure using Dedicated Containers.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Video Generation with Wan 2.1 - Together AI DocsDeploy a multi-GPU video generation model on Together's managed GPU infrastructure using Dedicated Containers.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/deepseek-3-1-quickstartDeepSeek V3.1 QuickStart - Together AI DocsHow to get started with DeepSeek V3.1https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100DeepSeek V3.1 QuickStart - Together AI DocsHow to get started with DeepSeek V3.1https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/deepseek-faqsDeepSeek FAQs - Together AI Docshttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100DeepSeek FAQs - Together AI Docshttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/deepseek-r1DeepSeek R1 Quickstart - Together AI DocsHow to get the most out of reasoning models like DeepSeek-R1.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100DeepSeek R1 Quickstart - Together AI DocsHow to get the most out of reasoning models like DeepSeek-R1.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/deploying-a-fine-tuned-modelDeploying a Fine-tuned Model - Together AI DocsOnce your fine-tune job completes, you should see your new model in your models dashboard.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Deploying a Fine-tuned Model - Together AI DocsOnce your fine-tune job completes, you should see your new model in your models dashboard.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/deployment-optionsDeployment Options Overview - Together AI DocsCompare Together AI's deployment options: fully-managed cloud service vs. secure VPC deployment for enterprises.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Deployment Options Overview - Together AI DocsCompare Together AI's deployment options: fully-managed cloud service vs. secure VPC deployment for enterprises.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/deployments-jigJig CLI - Together AI DocsBuild, push, and deploy containers to Together's managed GPU infrastructure.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Jig CLI - Together AI DocsBuild, push, and deploy containers to Together's managed GPU infrastructure.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/deployments-queueQueue API - Together AI DocsSubmit, monitor, and manage asynchronous jobs for your Dedicated Container deployments.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Queue API - Together AI DocsSubmit, monitor, and manage asynchronous jobs for your Dedicated Container deployments.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/deployments-sprocketSprocket SDK - Together AI DocsA Python SDK for building inference workers that support both synchronous and asynchronous requests via Together's platform.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Sprocket SDK - Together AI DocsA Python SDK for building inference workers that support both synchronous and asynchronous requests via Together's platform.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/deprecationsDeprecations - Together AI Docshttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Deprecations - Together AI Docshttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/dspyDSPy - Together AI DocsUsing DSPy with Together AIhttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100DSPy - Together AI DocsUsing DSPy with Together AIhttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/embeddings-overviewEmbeddings - Together AI DocsLearn how to get an embedding vector for a given text input.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Embeddings - Together AI DocsLearn how to get an embedding vector for a given text input.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/embeddings-ragRAG Integrations - Together AI Docshttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100RAG Integrations - Together AI Docshttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/error-codesError Codes - Together AI DocsAn overview on error status codes, causes, and quick fix solutionshttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Error Codes - Together AI DocsAn overview on error status codes, causes, and quick fix solutionshttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/evaluations-supported-modelsSupported Models - Together AI DocsSupported models for Evaluationshttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Supported Models - Together AI DocsSupported models for Evaluationshttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/fine-tuning-byomFine-tuning BYOM - Together AI DocsBring Your Own Model: Fine-tune Custom Models from the Hugging Face Hubhttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Fine-tuning BYOM - Together AI DocsBring Your Own Model: Fine-tune Custom Models from the Hugging Face Hubhttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/fine-tuning-data-preparationData Preparation - Together AI DocsTogether Fine-tuning API accepts two data formats for training dataset files: text data and tokenized data (in the form of Parquet files). Below, you can learn about different types of those formats and the scenarios in which they can be most useful.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Data Preparation - Together AI DocsTogether Fine-tuning API accepts two data formats for training dataset files: text data and tokenized data (in the form of Parquet files). Below, you can learn about different types of those formats and the scenarios in which they can be most useful.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/fine-tuning-faqsFine Tuning FAQs - Together AI Docshttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Fine Tuning FAQs - Together AI Docshttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/fine-tuning-function-callingFunction Calling Fine-tuning - Together AI DocsLearn how to fine-tune models with function calling capabilities using Together AI.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Function Calling Fine-tuning - Together AI DocsLearn how to fine-tune models with function calling capabilities using Together AI.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/fine-tuning-lora-supported-modulesLoRA Supported Modules - Together AI DocsSupported target modules for LoRA fine-tuning by modelhttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100LoRA Supported Modules - Together AI DocsSupported target modules for LoRA fine-tuning by modelhttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/fine-tuning-modelsSupported Models - Together AI DocsA list of all the models available for fine-tuning.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Supported Models - Together AI DocsA list of all the models available for fine-tuning.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/fine-tuning-pricingPricing - Together AI DocsFine-tuning pricing at Together AI is based on the total number of tokens processed during your job.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Pricing - Together AI DocsFine-tuning pricing at Together AI is based on the total number of tokens processed during your job.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/fine-tuning-quickstartFine-tuning Guide - Together AI DocsLearn the basics and best practices of fine-tuning large language models.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Fine-tuning Guide - Together AI DocsLearn the basics and best practices of fine-tuning large language models.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/fine-tuning-reasoningReasoning Fine-tuning - Together AI DocsLearn how to fine-tune reasoning models with chain-of-thought data using Together AI.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Reasoning Fine-tuning - Together AI DocsLearn how to fine-tune reasoning models with chain-of-thought data using Together AI.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/fine-tuning-vlmVision-Language Fine-tuning - Together AI DocsLearn how to fine-tune Vision-Language Models (VLMs) on image+text data using Together AI.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Vision-Language Fine-tuning - Together AI DocsLearn how to fine-tune Vision-Language Models (VLMs) on image+text data using Together AI.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/function-callingFunction Calling - Together AI DocsLearn how to get LLMs to respond to queries with named functions and structured arguments.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Function Calling - Together AI DocsLearn how to get LLMs to respond to queries with named functions and structured arguments.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/glm-5-quickstartGLM-5 Quickstart - Together AI DocsHow to get the most out of GLM-5 for reasoning and agentic tasks.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100GLM-5 Quickstart - Together AI DocsHow to get the most out of GLM-5 for reasoning and agentic tasks.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/gpt-ossOpenAI GPT-OSS Quickstart - Together AI DocsGet started with OpenAI's GPT-OSS, open-source reasoning model duo.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100OpenAI GPT-OSS Quickstart - Together AI DocsGet started with OpenAI's GPT-OSS, open-source reasoning model duo.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/gpu-clusters-apiAPI & Integrations - Together AI DocsManage clusters programmatically with CLI, REST API, Terraform, and third-party toolshttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100API & Integrations - Together AI DocsManage clusters programmatically with CLI, REST API, Terraform, and third-party toolshttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/gpu-clusters-billingBilling & Pricing - Together AI DocsUnderstand billing, pricing, and lifecycle policies for GPU Clustershttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Billing & Pricing - Together AI DocsUnderstand billing, pricing, and lifecycle policies for GPU Clustershttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/gpu-clusters-managementCluster Management - Together AI DocsManage, scale, and operate your GPU clustershttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Cluster Management - Together AI DocsManage, scale, and operate your GPU clustershttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/gpu-clusters-overviewGPU Clusters Overview - Together AI DocsHigh-performance GPU clusters for training, fine-tuning, and large-scale AI workloadshttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100GPU Clusters Overview - Together AI DocsHigh-performance GPU clusters for training, fine-tuning, and large-scale AI workloadshttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/gpu-clusters-quickstartQuickstart: Create Your First Cluster - Together AI DocsGet started with GPU Clusters in minuteshttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Quickstart: Create Your First Cluster - Together AI DocsGet started with GPU Clusters in minuteshttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/guidesGuides Homepage - Together AI DocsQuickstarts and step-by-step guides for building with Together AI.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Guides Homepage - Together AI DocsQuickstarts and step-by-step guides for building with Together AI.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/health-checksHealth Checks and Node Repair - Together AI DocsProactively validate GPU node health and trigger repair actions for issueshttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Health Checks and Node Repair - Together AI DocsProactively validate GPU node health and trigger repair actions for issueshttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/how-to-build-a-lovable-clone-with-kimi-k2How to build a Lovable clone with Kimi K2 - Together AI DocsLearn how to build a full-stack Next.js app that can generate React apps with a single prompt.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100How to build a Lovable clone with Kimi K2 - Together AI DocsLearn how to build a full-stack Next.js app that can generate React apps with a single prompt.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/how-to-build-coding-agentsHow to Build Coding Agents - Together AI DocsHow to build your own simple code editing agent from scratch in 400 lines of code!https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100How to Build Coding Agents - Together AI DocsHow to build your own simple code editing agent from scratch in 400 lines of code!https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/how-to-build-phone-voice-agentBuild a Phone Voice Agent with Together AI - Together AI DocsBuild a real-time phone voice agent from scratch with Twilio Media Streams, Together AI realtime STT, chat completions, realtime TTS, and local voice activity detection.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Build a Phone Voice Agent with Together AI - Together AI DocsBuild a real-time phone voice agent from scratch with Twilio Media Streams, Together AI realtime STT, chat completions, realtime TTS, and local voice activity detection.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/how-to-build-real-time-audio-transcription-appHow to build an AI audio transcription app with Whisper - Together AI DocsLearn how to build a real-time AI audio transcription app with Whisper, Next.js, and Together AI.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100How to build an AI audio transcription app with Whisper - Together AI DocsLearn how to build a real-time AI audio transcription app with Whisper, Next.js, and Together AI.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/how-to-implement-contextual-rag-from-anthropicHow To Implement Contextual RAG From Anthropic - Together AI DocsAn open source line-by-line implementation and explanation of Contextual RAG from Anthropic!https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100How To Implement Contextual RAG From Anthropic - Together AI DocsAn open source line-by-line implementation and explanation of Contextual RAG from Anthropic!https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/how-to-improve-search-with-rerankersHow To Improve Search With Rerankers - Together AI DocsLearn how you can improve semantic search quality with reranker models!https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100How To Improve Search With Rerankers - Together AI DocsLearn how you can improve semantic search quality with reranker models!https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/how-to-use-clineHow to use Cline with DeepSeek V3 to build faster - Together AI DocsUse Cline (an AI coding agent) with DeepSeek V3 (a powerful open source model) to code faster.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100How to use Cline with DeepSeek V3 to build faster - Together AI DocsUse Cline (an AI coding agent) with DeepSeek V3 (a powerful open source model) to code faster.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/how-to-use-openclawQuickstart: How to Use OpenClaw with Together AI - Together AI DocsLearn how to pair OpenClaw, a powerful autonomous agent, with frontier OSS models on Together AI like Kimi K2.5 and GLM 4.7.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Quickstart: How to Use OpenClaw with Together AI - Together AI DocsLearn how to pair OpenClaw, a powerful autonomous agent, with frontier OSS models on Together AI like Kimi K2.5 and GLM 4.7.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/how-to-use-opencodeHow to use OpenCode with Together AI to build faster - Together AI DocsLearn how to combine OpenCode, a powerful terminal-based AI coding agent, with Together AI models like DeepSeek V3 to supercharge your development workflow.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100How to use OpenCode with Together AI to build faster - Together AI DocsLearn how to combine OpenCode, a powerful terminal-based AI coding agent, with Together AI models like DeepSeek V3 to supercharge your development workflow.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/how-to-use-qwen-codeHow to use Qwen Code with Together AI for enhanced development workflow - Together AI DocsLearn how to configure Qwen Code, a powerful AI-powered command-line workflow tool, with Together AI models to supercharge your coding workflow with advanced code understanding and automation.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100How to use Qwen Code with Together AI for enhanced development workflow - Together AI DocsLearn how to configure Qwen Code, a powerful AI-powered command-line workflow tool, with Together AI models to supercharge your coding workflow with advanced code understanding and automation.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/identity-access-managementTogether's IAM Model - Together AI DocsHow users, credentials, and resources are organized across the Together platformhttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Together's IAM Model - Together AI DocsHow users, credentials, and resources are organized across the Together platformhttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/images-overviewImage Generation - Together AI DocsGenerate high-quality images from text + image prompts.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Image Generation - Together AI DocsGenerate high-quality images from text + image prompts.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/inference-faqsInference FAQs - Together AI Docshttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Inference FAQs - Together AI Docshttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/inference-parametersParameters - Together AI DocsLearn more about the parameters you can configure when running inference.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Parameters - Together AI DocsLearn more about the parameters you can configure when running inference.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/inference-web-interfacePlayground - Together AI DocsGuide to using Together AI's web playground for interactive AI model inference across chat, image, video, audio, and transcribe models.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Playground - Together AI DocsGuide to using Together AI's web playground for interactive AI model inference across chat, image, video, audio, and transcribe models.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/integrationsIntegrations - Together AI DocsUse Together AI models through partner integrations.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Integrations - Together AI DocsUse Together AI models through partner integrations.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/iterative-workflowIterative Workflow - Together AI DocsIteratively call LLMs to optimize task performance.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Iterative Workflow - Together AI DocsIteratively call LLMs to optimize task performance.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/json-modeStructured Outputs - Together AI DocsLearn how to use JSON mode to get structured outputs from LLMs like DeepSeek V3 & Llama 3.3.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Structured Outputs - Together AI DocsLearn how to use JSON mode to get structured outputs from LLMs like DeepSeek V3 & Llama 3.3.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/kimi-k2-quickstartKimi K2 QuickStart - Together AI DocsHow to get the most out of models like Kimi K2.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Kimi K2 QuickStart - Together AI DocsHow to get the most out of models like Kimi K2.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/kimi-k2-thinking-quickstartKimi K2 Thinking QuickStart - Together AI DocsHow to get the most out of reasoning models like Kimi K2 Thinking.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Kimi K2 Thinking QuickStart - Together AI DocsHow to get the most out of reasoning models like Kimi K2 Thinking.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/langgraphLangGraph - Together AI DocsUsing LangGraph with Together AIhttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100LangGraph - Together AI DocsUsing LangGraph with Together AIhttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/llama4-quickstartLlama 4 Quickstart - Together AI DocsHow to get the most out of the new Llama 4 models.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Llama 4 Quickstart - Together AI DocsHow to get the most out of the new Llama 4 models.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/logprobsGetting Started with Logprobs - Together AI DocsLearn how to return log probabilities for your output tokens & build better classifiers.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Getting Started with Logprobs - Together AI DocsLearn how to return log probabilities for your output tokens & build better classifiers.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/lora-training-and-inferenceLoRA Fine-Tuning and Inference - Together AI DocsFine-tune and run inference for a model with LoRA adaptershttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100LoRA Fine-Tuning and Inference - Together AI DocsFine-tune and run inference for a model with LoRA adaptershttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/mcpTogether AI MCP Server - Together AI DocsInstall our MCP server in Cursor, Claude Code, or OpenCode in 1 click.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Together AI MCP Server - Together AI DocsInstall our MCP server in Cursor, Claude Code, or OpenCode in 1 click.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/mixture-of-agentsTogether Mixture Of Agents (MoA) - Together AI Docshttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Together Mixture Of Agents (MoA) - Together AI Docshttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/nanochat-on-instant-clustersHow to run nanochat on Instant Clusters⚡️ - Together AI DocsLearn how to train Andrej Karpathy's end-to-end ChatGPT clone on Together's on-demand GPU clustershttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100How to run nanochat on Instant Clusters⚡️ - Together AI DocsLearn how to train Andrej Karpathy's end-to-end ChatGPT clone on Together's on-demand GPU clustershttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/nextjs-chat-quickstartQuickstart: Next.Js - Together AI DocsBuild an app that can ask a single question or chat with an LLM using Next.js and Together AI.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Quickstart: Next.Js - Together AI DocsBuild an app that can ask a single question or chat with an LLM using Next.js and Together AI.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/open-notebooklm-pdf-to-podcastHow To Build An Open Source NotebookLM: PDF To Podcast - Together AI DocsIn this guide we will see how to create a podcast like the one below from a PDF input!https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100How To Build An Open Source NotebookLM: PDF To Podcast - Together AI DocsIn this guide we will see how to create a podcast like the one below from a PDF input!https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/openai-api-compatibilityOpenAI Compatibility - Together AI DocsTogether's API is compatible with OpenAI's libraries, making it easy to try out our open-source models on existing applications.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100OpenAI Compatibility - Together AI DocsTogether's API is compatible with OpenAI's libraries, making it easy to try out our open-source models on existing applications.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/organizationsOrganizations - Together AI DocsCreate and manage your Together Organization, invite Members, and configure billinghttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Organizations - Together AI DocsCreate and manage your Together Organization, invite Members, and configure billinghttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/parallel-workflowsParallel Workflow - Together AI DocsExecute multiple LLM calls in parallel and aggregate afterwards.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Parallel Workflow - Together AI DocsExecute multiple LLM calls in parallel and aggregate afterwards.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/preference-fine-tuningPreference Fine-Tuning - Together AI DocsLearn how to use preference fine-tuning on Together Fine-Tuning Platformhttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Preference Fine-Tuning - Together AI DocsLearn how to use preference fine-tuning on Together Fine-Tuning Platformhttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/projectsProjects - Together AI DocsCreate isolated workspaces to organize resources, manage team access, and scope API keyshttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Projects - Together AI DocsCreate isolated workspaces to organize resources, manage team access, and scope API keyshttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/prompting-deepseek-r1Prompting DeepSeek R1 - Together AI DocsPrompt engineering for DeepSeek-R1.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Prompting DeepSeek R1 - Together AI DocsPrompt engineering for DeepSeek-R1.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/pydanticaiPydanticAI - Together AI DocsUsing PydanticAI with Togetherhttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100PydanticAI - Together AI DocsUsing PydanticAI with Togetherhttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/pythonv2-migration-guidePython v2 SDK Migration Guide - Together AI DocsMigrate from Together Python v1 to v2 - the new Together AI Python SDK with improved type safety and modern architecture.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Python v2 SDK Migration Guide - Together AI DocsMigrate from Together Python v1 to v2 - the new Together AI Python SDK with improved type safety and modern architecture.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/quickstartQuickstart - Together AI DocsGet up to speed with our API in one minute.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Quickstart - Together AI DocsGet up to speed with our API in one minute.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/quickstart-fluxQuickstart: FLUX.2 - Together AI DocsLearn how to use FLUX.2, the next generation image model with advanced prompting capabilitieshttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Quickstart: FLUX.2 - Together AI DocsLearn how to use FLUX.2, the next generation image model with advanced prompting capabilitieshttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/quickstart-flux-kontextQuickstart: Flux Kontext - Together AI DocsLearn how to use Flux's new in-context image generation modelshttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Quickstart: Flux Kontext - Together AI DocsLearn how to use Flux's new in-context image generation modelshttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/quickstart-flux-loraQuickstart: Flux LoRA Inference - Together AI Docshttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Quickstart: Flux LoRA Inference - Together AI Docshttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/quickstart-how-to-do-ocrQuickstart: How to do OCR - Together AI DocsA step by step guide on how to do OCR with Together AI's vision models with structured outputshttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Quickstart: How to do OCR - Together AI DocsA step by step guide on how to do OCR with Together AI's vision models with structured outputshttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/quickstart-retrieval-augmented-generation-ragQuickstart: Retrieval Augmented Generation (RAG) - Together AI DocsHow to build a RAG workflow in under 5 mins!https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Quickstart: Retrieval Augmented Generation (RAG) - Together AI DocsHow to build a RAG workflow in under 5 mins!https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/quickstart-using-hugging-face-inferenceQuickstart: Using Hugging Face Inference With Together - Together AI DocsThis guide will walk you through how to use Together models with Hugging Face Inference.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Quickstart: Using Hugging Face Inference With Together - Together AI DocsThis guide will walk you through how to use Together models with Hugging Face Inference.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/rate-limitsInference Rate Limits - Together AI DocsRate limits restrict how often a user or client can access our API within a set timeframe.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Inference Rate Limits - Together AI DocsRate limits restrict how often a user or client can access our API within a set timeframe.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/reasoning-models-guideReasoning Models Guide - Together AI DocsHow reasoning models like DeepSeek-R1 work.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Reasoning Models Guide - Together AI DocsHow reasoning models like DeepSeek-R1 work.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/reasoning-overviewReasoning - Together AI DocsLearn how to use reasoning models that think step-by-step before answering.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Reasoning - Together AI DocsLearn how to use reasoning models that think step-by-step before answering.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/recommended-modelsRecommended Models - Together AI DocsFind the right models for your use casehttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Recommended Models - Together AI DocsFind the right models for your use casehttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/rerank-overviewRerank - Together AI DocsLearn how to improve the relevance of your search and RAG systems with reranking.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Rerank - Together AI DocsLearn how to improve the relevance of your search and RAG systems with reranking.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/roles-permissionsRoles & Permissions (RBAC) - Together AI DocsUnderstand Organization and Project role-based access control (RBAC) including Admin and Member roles and what each can do across the Together platformhttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Roles & Permissions (RBAC) - Together AI DocsUnderstand Organization and Project role-based access control (RBAC) including Admin and Member roles and what each can do across the Together platformhttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/sequential-agent-workflowSequential Workflow - Together AI DocsCoordinating a chain of LLM calls to solve a complex task.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Sequential Workflow - Together AI DocsCoordinating a chain of LLM calls to solve a complex task.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/serverless-modelsServerless Models - Together AI Docshttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Serverless Models - Together AI Docshttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/slurmSlurm Management System - Together AI Docshttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Slurm Management System - Together AI Docshttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/slurm-configurationSlurm Configuration - Together AI DocsCustomize Slurm cluster settings to match your workload requirementshttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Slurm Configuration - Together AI DocsCustomize Slurm cluster settings to match your workload requirementshttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/speech-to-textSpeech-to-Text - Together AI DocsLearn how to transcribe and translate audio into text!https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Speech-to-Text - Together AI DocsLearn how to transcribe and translate audio into text!https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/ssoSingle Sign-On (SSO) - Together AI DocsConnect your Identity Provider for secure, automated team access to Togetherhttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Single Sign-On (SSO) - Together AI DocsConnect your Identity Provider for secure, automated team access to Togetherhttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/support-ticket-portalCustomer Ticket Portal - Together AI Docshttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Customer Ticket Portal - Together AI Docshttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/text-to-speechText-to-Speech - Together AI DocsLearn how to use the text-to-speech functionality supported by Together AI.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Text-to-Speech - Together AI DocsLearn how to use the text-to-speech functionality supported by Together AI.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/together-code-interpreterTogether Code Interpreter - Together AI DocsExecute LLM-generated code seamlessly with a simple API call.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Together Code Interpreter - Together AI DocsExecute LLM-generated code seamlessly with a simple API call.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/together-code-sandboxTogether Code Sandbox - Together AI DocsLevel-up generative code tooling with fast, secure code sandboxes at scalehttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Together Code Sandbox - Together AI DocsLevel-up generative code tooling with fast, secure code sandboxes at scalehttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/together-deploymentsPlatform Overview - Together AI DocsArchitecture, deployment lifecycle, and core concepts for Dedicated Container Inference.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Platform Overview - Together AI DocsArchitecture, deployment lifecycle, and core concepts for Dedicated Container Inference.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/using-together-with-mastraQuickstart: Using Mastra with Together AI - Together AI DocsThis guide will walk you through how to use Together models with Mastra.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Quickstart: Using Mastra with Together AI - Together AI DocsThis guide will walk you through how to use Together models with Mastra.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/using-together-with-vercels-ai-sdkQuickstart: Using Vercel AI SDK With Together AI - Together AI DocsThis guide will walk you through how to use Together models with the Vercel AI SDK.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Quickstart: Using Vercel AI SDK With Together AI - Together AI DocsThis guide will walk you through how to use Together models with the Vercel AI SDK.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/videos-overviewVideo Generation - Together AI DocsGenerate high-quality videos from text and image prompts.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Video Generation - Together AI DocsGenerate high-quality videos from text and image prompts.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/vision-overviewVision LLMs - Together AI DocsLearn how to use the vision models supported by Together AI.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Vision LLMs - Together AI DocsLearn how to use the vision models supported by Together AI.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/docs/workflowsAgent Workflows - Together AI DocsOrchestrating together multiple language model calls to solve complex tasks.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Agent Workflows - Together AI DocsOrchestrating together multiple language model calls to solve complex tasks.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/examplesTogether Cookbooks & Example Apps - Together AI DocsExplore our vast library of open-source cookbooks & example appshttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Together Cookbooks & Example Apps - Together AI DocsExplore our vast library of open-source cookbooks & example appshttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/introOverview - Together AI DocsWelcome to Together AI’s docs! Together makes it easy to run, finetune, and train open source AI models with transparency and privacy.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Overview - Together AI DocsWelcome to Together AI’s docs! Together makes it easy to run, finetune, and train open source AI models with transparency and privacy.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/reference/audio-speechCreate Audio Generation Request - Together AI DocsGenerate audio from input texthttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Create Audio Generation Request - Together AI DocsGenerate audio from input texthttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/reference/audio-speech-websocketCreate realtime text-to-speech - Together AI DocsEstablishes a WebSocket connection for real-time text-to-speech generation. This endpoint uses WebSocket protocol (wss://api.together.ai/v1/audio/speech/websocket) for bidirectional streaming communication. Connection Setup: - Protocol: WebSocket (wss://) - Authentication: Pass API key as Bearer token in Authorization header - Parameters: Sent as query parameters (model, voice, max_partial_length) Client Events: - tts_session.updated: Update session parameters like voice json { "type": "tts_session.updated", "session": { "voice": "tara" } } - input_text_buffer.append: Send text chunks for TTS generation json { "type": "input_text_buffer.append", "text": "Hello, this is a test." } - input_text_buffer.clear: Clear the buffered text json { "type": "input_text_buffer.clear" } - input_text_buffer.commit: Signal end of text input and process remaining text json { "type": "input_text_buffer.commit" } Server Events: - session.created: Initial session confirmation (sent first) json { "event_id": "evt_123456", "type": "session.created", "session": { "id": "session-id", "object": "realtime.tts.session", "modalities": ["text", "audio"], "model": "hexgrad/Kokoro-82M", "voice": "tara" } } - conversation.item.input_text.received: Acknowledgment that text was received json { "type": "conversation.item.input_text.received", "text": "Hello, this is a test." } - conversation.item.audio_output.delta: Audio chunks as base64-encoded data json { "type": "conversation.item.audio_output.delta", "item_id": "tts_1", "delta": "" } - conversation.item.audio_output.done: Audio generation complete for an item json { "type": "conversation.item.audio_output.done", "item_id": "tts_1" } - conversation.item.tts.failed: Error occurred json { "type": "conversation.item.tts.failed", "error": { "message": "Error description", "type": "invalid_request_error", "param": null, "code": "invalid_api_key" } } Text Processing: - Partial text (no sentence ending) is held in buffer until: - We believe that the text is complete enough to be processed for TTS generation - The partial text exceeds max_partial_length characters (default: 250) - The input_text_buffer.commit event is received Audio Format: - Format: WAV (PCM s16le) - Sample Rate: 24000 Hz - Encoding: Base64 - Delivered via conversation.item.audio_output.delta events Error Codes: - invalid_api_key: Invalid API key provided (401) - missing_api_key: Authorization header missing (401) - model_not_available: Invalid or unavailable model (400) - Invalid text format errors (400)https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Create realtime text-to-speech - Together AI DocsEstablishes a WebSocket connection for real-time text-to-speech generation. This endpoint uses WebSocket protocol (wss://api.together.ai/v1/audio/speech/websocket) for bidirectional streaming communication. Connection Setup: - Protocol: WebSocket (wss://) - Authentication: Pass API key as Bearer token in Authorization header - Parameters: Sent as query parameters (model, voice, max_partial_length) Client Events: - tts_session.updated: Update session parameters like voice json { "type": "tts_session.updated", "session": { "voice": "tara" } } - input_text_buffer.append: Send text chunks for TTS generation json { "type": "input_text_buffer.append", "text": "Hello, this is a test." } - input_text_buffer.clear: Clear the buffered text json { "type": "input_text_buffer.clear" } - input_text_buffer.commit: Signal end of text input and process remaining text json { "type": "input_text_buffer.commit" } Server Events: - session.created: Initial session confirmation (sent first) json { "event_id": "evt_123456", "type": "session.created", "session": { "id": "session-id", "object": "realtime.tts.session", "modalities": ["text", "audio"], "model": "hexgrad/Kokoro-82M", "voice": "tara" } } - conversation.item.input_text.received: Acknowledgment that text was received json { "type": "conversation.item.input_text.received", "text": "Hello, this is a test." } - conversation.item.audio_output.delta: Audio chunks as base64-encoded data json { "type": "conversation.item.audio_output.delta", "item_id": "tts_1", "delta": "" } - conversation.item.audio_output.done: Audio generation complete for an item json { "type": "conversation.item.audio_output.done", "item_id": "tts_1" } - conversation.item.tts.failed: Error occurred json { "type": "conversation.item.tts.failed", "error": { "message": "Error description", "type": "invalid_request_error", "param": null, "code": "invalid_api_key" } } Text Processing: - Partial text (no sentence ending) is held in buffer until: - We believe that the text is complete enough to be processed for TTS generation - The partial text exceeds max_partial_length characters (default: 250) - The input_text_buffer.commit event is received Audio Format: - Format: WAV (PCM s16le) - Sample Rate: 24000 Hz - Encoding: Base64 - Delivered via conversation.item.audio_output.delta events Error Codes: - invalid_api_key: Invalid API key provided (401) - missing_api_key: Authorization header missing (401) - model_not_available: Invalid or unavailable model (400) - Invalid text format errors (400)https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/reference/audio-transcriptionsCreate an Audio Transcription - Together AI DocsTranscribes audio into texthttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Create an Audio Transcription - Together AI DocsTranscribes audio into texthttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/reference/audio-transcriptions-realtimeCreate a realtime audio transcription - Together AI DocsEstablishes a WebSocket connection for real-time audio transcription. This endpoint uses WebSocket protocol (wss://api.together.ai/v1/realtime) for bidirectional streaming communication. Connection Setup: - Protocol: WebSocket (wss://) - Authentication: Pass API key as Bearer token in Authorization header - Parameters: Sent as query parameters (model, input_audio_format) Client Events: - input_audio_buffer.append: Send audio chunks as base64-encoded data json { "type": "input_audio_buffer.append", "audio": "" } - input_audio_buffer.commit: Signal end of audio stream json { "type": "input_audio_buffer.commit" } Server Events: - session.created: Initial session confirmation (sent first) json { "type": "session.created", "session": { "id": "session-id", "object": "realtime.session", "modalities": ["audio"], "model": "openai/whisper-large-v3" } } - conversation.item.input_audio_transcription.delta: Partial transcription results json { "type": "conversation.item.input_audio_transcription.delta", "delta": "The quick brown" } - conversation.item.input_audio_transcription.completed: Final transcription json { "type": "conversation.item.input_audio_transcription.completed", "transcript": "The quick brown fox jumps over the lazy dog" } - conversation.item.input_audio_transcription.failed: Error occurred json { "type": "conversation.item.input_audio_transcription.failed", "error": { "message": "Error description", "type": "invalid_request_error", "param": null, "code": "invalid_api_key" } } Error Codes: - invalid_api_key: Invalid API key provided (401) - missing_api_key: Authorization header missing (401) - model_not_available: Invalid or unavailable model (400) - Unsupported audio format errors (400)https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Create a realtime audio transcription - Together AI DocsEstablishes a WebSocket connection for real-time audio transcription. This endpoint uses WebSocket protocol (wss://api.together.ai/v1/realtime) for bidirectional streaming communication. Connection Setup: - Protocol: WebSocket (wss://) - Authentication: Pass API key as Bearer token in Authorization header - Parameters: Sent as query parameters (model, input_audio_format) Client Events: - input_audio_buffer.append: Send audio chunks as base64-encoded data json { "type": "input_audio_buffer.append", "audio": "" } - input_audio_buffer.commit: Signal end of audio stream json { "type": "input_audio_buffer.commit" } Server Events: - session.created: Initial session confirmation (sent first) json { "type": "session.created", "session": { "id": "session-id", "object": "realtime.session", "modalities": ["audio"], "model": "openai/whisper-large-v3" } } - conversation.item.input_audio_transcription.delta: Partial transcription results json { "type": "conversation.item.input_audio_transcription.delta", "delta": "The quick brown" } - conversation.item.input_audio_transcription.completed: Final transcription json { "type": "conversation.item.input_audio_transcription.completed", "transcript": "The quick brown fox jumps over the lazy dog" } - conversation.item.input_audio_transcription.failed: Error occurred json { "type": "conversation.item.input_audio_transcription.failed", "error": { "message": "Error description", "type": "invalid_request_error", "param": null, "code": "invalid_api_key" } } Error Codes: - invalid_api_key: Invalid API key provided (401) - missing_api_key: Authorization header missing (401) - model_not_available: Invalid or unavailable model (400) - Unsupported audio format errors (400)https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/reference/audio-translationsCreate an Audio Translation - Together AI DocsTranslates audio into Englishhttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Create an Audio Translation - Together AI DocsTranslates audio into Englishhttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/reference/authenticationAuthentication - Together AI Docshttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Authentication - Together AI Docshttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/reference/batch-cancelCancel a batch job - Together AI DocsCancel a batch job by IDhttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Cancel a batch job - Together AI DocsCancel a batch job by IDhttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/reference/batch-createCreate a batch job - Together AI DocsCreate a new batch job with the given input file and endpointhttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Create a batch job - Together AI DocsCreate a new batch job with the given input file and endpointhttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/reference/batch-getGet a batch job - Together AI DocsGet details of a batch job by IDhttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Get a batch job - Together AI DocsGet details of a batch job by IDhttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/reference/batch-listList all batch jobs - Together AI DocsList all batch jobs for the authenticated userhttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100List all batch jobs - Together AI DocsList all batch jobs for the authenticated userhttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/reference/chat-completionsCreate Chat Completion - Together AI DocsGenerate a model response for a given chat conversation. Supports single queries and multi-turn conversations with system, user, and assistant messages.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Create Chat Completion - Together AI DocsGenerate a model response for a given chat conversation. Supports single queries and multi-turn conversations with system, user, and assistant messages.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/reference/cli/beta-introIntroduction - Together AI DocsDocumentation for using beta features with the Together Python SDK / CLI.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Introduction - Together AI DocsDocumentation for using beta features with the Together Python SDK / CLI.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/reference/cli/clustersClusters - Together AI Docshttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Clusters - Together AI Docshttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/reference/cli/endpointsEndpoints - Together AI DocsCreate, update and delete endpoints via the CLIhttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Endpoints - Together AI DocsCreate, update and delete endpoints via the CLIhttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/reference/cli/evalsEvals - Together AI DocsManage model evaluation jobshttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Evals - Together AI DocsManage model evaluation jobshttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/reference/cli/filesFiles - Together AI Docshttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Files - Together AI Docshttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/reference/cli/finetuneFine Tuning - Together AI Docshttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Fine Tuning - Together AI Docshttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/reference/cli/getting-startedGetting Started - Together AI DocsGet started with Together's Python CLI (together).https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Getting Started - Together AI DocsGet started with Together's Python CLI (together).https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/reference/cli/jig-redirect-stubContainers (Jig) - Together AI DocsCLI commands and configuration for Dedicated Containers.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Containers (Jig) - Together AI DocsCLI commands and configuration for Dedicated Containers.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/reference/cli/modelsModels - Together AI Docshttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Models - Together AI Docshttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/reference/clusters-createCreate a Cluster - Together AI DocsCreate an Instant Cluster on Together's high-performance GPU clusters. With features like on-demand scaling, long-lived resizable high-bandwidth shared DC-local storage, Kubernetes and Slurm cluster flavors, a REST API, and Terraform support, you can run workloads flexibly without complex infrastructure management.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Create a Cluster - Together AI DocsCreate an Instant Cluster on Together's high-performance GPU clusters. With features like on-demand scaling, long-lived resizable high-bandwidth shared DC-local storage, Kubernetes and Slurm cluster flavors, a REST API, and Terraform support, you can run workloads flexibly without complex infrastructure management.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/reference/clusters-deleteDelete a Cluster - Together AI DocsDelete a GPU cluster by cluster ID.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Delete a Cluster - Together AI DocsDelete a GPU cluster by cluster ID.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/reference/clusters-getRetrieve Cluster - Together AI DocsRetrieve information about a specific GPU cluster.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Retrieve Cluster - Together AI DocsRetrieve information about a specific GPU cluster.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/reference/clusters-listList all Clusters - Together AI DocsList all GPU clusters.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100List all Clusters - Together AI DocsList all GPU clusters.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/reference/clusters-list-regionsList compute region capabilities - Together AI Docshttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100List compute region capabilities - Together AI Docshttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/reference/clusters-updateUpdate or Scale GPU Cluster - Together AI DocsUpdate the configuration of an existing GPU cluster.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Update or Scale GPU Cluster - Together AI DocsUpdate the configuration of an existing GPU cluster.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/reference/clusters_storages-createCreate a shared volume - Together AI DocsInstant Clusters supports long-lived, resizable in-DC shared storage with user data persistence. You can dynamically create and attach volumes to your cluster at cluster creation time, and resize as your data grows. All shared storage is backed by multi-NIC bare metal paths, ensuring high-throughput and low-latency performance for shared storage.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Create a shared volume - Together AI DocsInstant Clusters supports long-lived, resizable in-DC shared storage with user data persistence. You can dynamically create and attach volumes to your cluster at cluster creation time, and resize as your data grows. All shared storage is backed by multi-NIC bare metal paths, ensuring high-throughput and low-latency performance for shared storage.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/reference/clusters_storages-deleteDelete a shared volume - Together AI DocsDelete a shared volume. Note that if this volume is attached to a cluster, deleting will fail.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Delete a shared volume - Together AI DocsDelete a shared volume. Note that if this volume is attached to a cluster, deleting will fail.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/reference/clusters_storages-getRetrieve a shared volumes - Together AI DocsRetrieve information about a specific shared volume.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Retrieve a shared volumes - Together AI DocsRetrieve information about a specific shared volume.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/reference/clusters_storages-listList shared volumes - Together AI DocsList all shared volumes.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100List shared volumes - Together AI DocsList all shared volumes.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/reference/clusters_storages-updateUpdate a shared volume - Together AI DocsUpdate the configuration of an existing shared volume.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Update a shared volume - Together AI DocsUpdate the configuration of an existing shared volume.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/reference/completionsCreate Completion - Together AI DocsGenerate text completions for a given prompt using a language, code, or image model.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Create Completion - Together AI DocsGenerate text completions for a given prompt using a language, code, or image model.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/reference/create-evaluationCreate Evaluation - Together AI Docshttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Create Evaluation - Together AI Docshttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/reference/create-videosCreate Video - Together AI DocsCreate a videohttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Create Video - Together AI DocsCreate a videohttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/reference/createendpointCreate A Dedicated Endpoint - Together AI DocsCreates a new dedicated endpoint for serving models. The endpoint will automatically start after creation. You can deploy any supported model on hardware configurations that meet the model's requirements.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Create A Dedicated Endpoint - Together AI DocsCreates a new dedicated endpoint for serving models. The endpoint will automatically start after creation. You can deploy any supported model on hardware configurations that meet the model's requirements.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/reference/dci-reference-jigJig CLI - Together AI DocsCLI commands, pyproject.toml configuration, environment variables, and Python SDK for Dedicated Containers.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Jig CLI - Together AI DocsCLI commands, pyproject.toml configuration, environment variables, and Python SDK for Dedicated Containers.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/reference/dci-reference-sprocketSprocket SDK - Together AI DocsAPI reference for Sprocket classes, functions, and configuration.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Sprocket SDK - Together AI DocsAPI reference for Sprocket classes, functions, and configuration.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/reference/delete-files-idDelete A File - Together AI DocsDelete a previously uploaded data file.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Delete A File - Together AI DocsDelete a previously uploaded data file.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/reference/delete-fine-tunes-idDelete A Fine-tuning Event - Together AI DocsDelete a fine-tuning job.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Delete A Fine-tuning Event - Together AI DocsDelete a fine-tuning job.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/reference/deleteendpointDelete Endpoint - Together AI DocsPermanently deletes an endpoint. This action cannot be undone.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Delete Endpoint - Together AI DocsPermanently deletes an endpoint. This action cannot be undone.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/reference/deployments-createCreate Deployment - Together AI DocsCreate a new deployment with specified configurationhttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Create Deployment - Together AI DocsCreate a new deployment with specified configurationhttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/reference/deployments-deleteDelete Deployment - Together AI DocsDelete an existing deploymenthttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Delete Deployment - Together AI DocsDelete an existing deploymenthttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/reference/deployments-getGet Deployment - Together AI DocsRetrieve details of a specific deployment by its ID or namehttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Get Deployment - Together AI DocsRetrieve details of a specific deployment by its ID or namehttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/reference/deployments-listList Deployments - Together AI DocsGet a list of all deployments in your projecthttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100List Deployments - Together AI DocsGet a list of all deployments in your projecthttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/reference/deployments-logsGet Deployment Logs - Together AI DocsRetrieve logs from a deployment, optionally filtered by replica ID.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Get Deployment Logs - Together AI DocsRetrieve logs from a deployment, optionally filtered by replica ID.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/reference/deployments-secrets-createCreate Secret - Together AI DocsCreate a new secret to store sensitive configuration valueshttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Create Secret - Together AI DocsCreate a new secret to store sensitive configuration valueshttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/reference/deployments-secrets-deleteDelete Secret - Together AI DocsDelete an existing secrethttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Delete Secret - Together AI DocsDelete an existing secrethttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/reference/deployments-secrets-getGet Secret - Together AI DocsRetrieve details of a specific secret by its ID or namehttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Get Secret - Together AI DocsRetrieve details of a specific secret by its ID or namehttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/reference/deployments-secrets-listList Secrets - Together AI DocsRetrieve all secrets in your projecthttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100List Secrets - Together AI DocsRetrieve all secrets in your projecthttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/reference/deployments-secrets-updateUpdate Secret - Together AI DocsUpdate an existing secret's value or metadatahttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Update Secret - Together AI DocsUpdate an existing secret's value or metadatahttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/reference/deployments-storage-getGet Storage File - Together AI DocsDownload a file by redirecting to a signed URLhttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Get Storage File - Together AI DocsDownload a file by redirecting to a signed URLhttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/reference/deployments-storage-volumes-createCreate Storage Volume - Together AI DocsCreate a new volume to preload files in deploymentshttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Create Storage Volume - Together AI DocsCreate a new volume to preload files in deploymentshttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/reference/deployments-storage-volumes-deleteDelete Storage Volume - Together AI DocsDelete an existing volumehttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Delete Storage Volume - Together AI DocsDelete an existing volumehttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/reference/deployments-storage-volumes-getGet Storage Volume - Together AI DocsRetrieve details of a specific volume by its ID or namehttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Get Storage Volume - Together AI DocsRetrieve details of a specific volume by its ID or namehttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/reference/deployments-storage-volumes-listList Storage Volumes - Together AI DocsRetrieve all volumes in your projecthttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100List Storage Volumes - Together AI DocsRetrieve all volumes in your projecthttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/reference/deployments-storage-volumes-updateUpdate Storage Volume - Together AI DocsUpdate an existing volume's configuration or contentshttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Update Storage Volume - Together AI DocsUpdate an existing volume's configuration or contentshttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/reference/deployments-updateUpdate Deployment - Together AI DocsUpdate an existing deployment configurationhttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Update Deployment - Together AI DocsUpdate an existing deployment configurationhttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/reference/embeddingsCreate Embedding - Together AI DocsGenerate vector embeddings for one or more text inputs. Returns numerical arrays representing semantic meaning, useful for search, classification, and retrieval.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Create Embedding - Together AI DocsGenerate vector embeddings for one or more text inputs. Returns numerical arrays representing semantic meaning, useful for search, classification, and retrieval.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/reference/get-evaluationGet Evaluation - Together AI Docshttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Get Evaluation - Together AI Docshttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/reference/get-evaluation-statusGet Evaluation Status - Together AI Docshttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Get Evaluation Status - Together AI Docshttps://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/reference/get-filesList All Files - Together AI DocsList the metadata for all uploaded data files.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100List All Files - Together AI DocsList the metadata for all uploaded data files.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/reference/get-files-idList File - Together AI DocsRetrieve the metadata for a single uploaded data file.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100List File - Together AI DocsRetrieve the metadata for a single uploaded data file.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/reference/get-files-id-contentGet File Contents - Together AI DocsGet the contents of a single uploaded data file.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100Get File Contents - Together AI DocsGet the contents of a single uploaded data file.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/reference/get-fine-tunesList All Jobs - Together AI DocsList the metadata for all fine-tuning jobs. Returns a list of FinetuneResponseTruncated objects.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100List All Jobs - Together AI DocsList the metadata for all fine-tuning jobs. Returns a list of FinetuneResponseTruncated objects.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/reference/get-fine-tunes-idList Job - Together AI DocsList the metadata for a single fine-tuning job.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100List Job - Together AI DocsList the metadata for a single fine-tuning job.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
/reference/get-fine-tunes-id-checkpointList checkpoints - Together AI DocsList the checkpoints for a single fine-tuning job.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100List checkpoints - Together AI DocsList the checkpoints for a single fine-tuning job.https://togetherai-52386018.mintlify.app/mintlify-assets/_next/imag…dDark%3D%2523050608&w=1200&q=100
You have reached the hard limit of 200 rows as a protection against very large output or exhausted memory. You can change this with --rows-limit.
No rows found, please edit your search term.

Heading structure

Found 200 row(s).
Heading structureCountErrors 🔽URL
  • <h1> Platform Overview [#page-title]
    • <h2> ​Platform Components [#platform-components]
      • <h3> ​Jig – Deployment CLI [#jig-–-deployment-cli]
      • <h3> ​Sprocket – Worker SDK [#sprocket-–-worker-sdk]
      • <h3> ​Container Registry [#container-registry]
    • <h2> ​Available Hardware [#available-hardware]
    • <h2> ​When to Use Dedicated Containers [#when-to-use-dedicated-containers]
    • <h2> ​How It Works [#how-it-works]
  • <h1> ​Monitoring and Observability [#monitoring-and-observability]
    • <h3> ​Metrics [#metrics]
    • <h3> ​Logging [#logging]
    • <h3> ​Health Checks [#health-checks]
  • <h1> ​Autoscaling [#autoscaling]
    • <h3> ​Configuration [#configuration]
    • <h3> ​Profiles [#profiles]
    • <h3> ​Scaling Behavior [#scaling-behavior]
  • <h1> ​Troubleshooting [#troubleshooting]
    • <h3> ​Common Issues [#common-issues]
    • <h3> ​Debug Mode [#debug-mode]
    • <h3> ​Getting Help [#getting-help]
  • <h1> ​FAQs [#faqs]
2114/docs/together-deployments
  • <h1> Together AI MCP Server [#page-title]
  • <h1> ​One-Click Installs [#one-click-installs]
    • <h3> ​Quick Start (Universal) [#quick-start-universal]
    • <h3> ​Claude Code [#claude-code]
    • <h3> ​Cursor [#cursor]
    • <h3> ​VS Code [#vs-code]
    • <h3> ​OpenAI Codex [#openai-codex]
    • <h3> ​Opencode [#opencode]
    • <h2> ​What you can do [#what-you-can-do]
98/docs/mcp
  • <h1> DeepSeek FAQs [#page-title]
    • <h3> ​How can I access DeepSeek R1 and V3? [#how-can-i-access-deepseek-r1-and-v3]
    • <h3> ​Why is R1 more expensive than V3 if they share the same architecture and are the same size? [#why-is-r1-more-expensive-than-v3-if-they-share-the-same-architecture-and-are-the-same-size]
    • <h3> ​Have you changed the DeepSeek model in any way? Is it quantized, distilled or modified? [#have-you-changed-the-deepseek-model-in-any-way-is-it-quantized-distilled-or-modified]
    • <h3> ​Do you send data to China or DeepSeek? [#do-you-send-data-to-china-or-deepseek]
    • <h3> ​Can I deploy DeepSeek in Dedicated Endpoints? What speed and costs can I expect? [#can-i-deploy-deepseek-in-dedicated-endpoints-what-speed-and-costs-can-i-expect]
    • <h3> ​What are the rate limits for DeepSeek R1? [#what-are-the-rate-limits-for-deepseek-r1]
    • <h3> ​How do I enable thinking mode for DeepSeek V3.1? [#how-do-i-enable-thinking-mode-for-deepseek-v3-1]
87/docs/deepseek-faqs
  • <h1> How to use Cline with DeepSeek V3 to build faster [#page-title]
    • <h3> ​1. Install Cline [#1-install-cline]
    • <h3> ​2. Select Cline [#2-select-cline]
    • <h3> ​3. Configure Together AI & DeepSeek V3 [#3-configure-together-ai-&-deepseek-v3]
43/docs/how-to-use-cline
  • <h1> How to run nanochat on Instant Clusters⚡️ [#page-title]
    • <h2> ​Overview [#overview]
    • <h2> ​Prerequisites [#prerequisites]
  • <h1> ​Training nanochat [#training-nanochat]
    • <h2> ​Step 1: Create an Instant Cluster [#step-1-create-an-instant-cluster]
    • <h2> ​Step 2: SSH into Your Cluster [#step-2-ssh-into-your-cluster]
    • <h2> ​Step 3: Clone nanochat and Set Up Environment [#step-3-clone-nanochat-and-set-up-environment]
    • <h2> ​Step 4: Access GPU Resources [#step-4-access-gpu-resources]
    • <h2> ​Step 5: Configure Cache Directory [#step-5-configure-cache-directory]
    • <h2> ​Step 6: Run the Training Pipeline [#step-6-run-the-training-pipeline]
  • <h1> ​nanochat Inference [#nanochat-inference]
    • <h2> ​Step 1: Download Your Cluster’s Kubeconfig [#step-1-download-your-cluster’s-kubeconfig]
    • <h2> ​Step 2: Access the Compute Pod via kubectl [#step-2-access-the-compute-pod-via-kubectl]
    • <h2> ​Step 3: Launch the nanochat Web Server [#step-3-launch-the-nanochat-web-server]
    • <h2> ​Step 4: Port Forward to Access the UI [#step-4-port-forward-to-access-the-ui]
    • <h2> ​Step 5: Chat with nanochat! [#step-5-chat-with-nanochat]
    • <h2> ​Understanding Training Costs and Performance [#understanding-training-costs-and-performance]
    • <h2> ​Troubleshooting [#troubleshooting]
    • <h2> ​Next Steps [#next-steps]
    • <h2> ​Additional Resources [#additional-resources]
203/docs/nanochat-on-instant-clusters
  • <h1> Inference Rate Limits [#page-title]
    • <h3> ​How We Measure Rate limits [#how-we-measure-rate-limits]
    • <h3> ​Fetching Latest Serverless Rate Limits [#fetching-latest-serverless-rate-limits]
    • <h2> ​Alternatives for High Volume or Bursty Workloads [#alternatives-for-high-volume-or-bursty-workloads]
    • <h2> ​Best Practice [#best-practice]
    • <h2> ​Dynamic Rate Limits [#dynamic-rate-limits]
      • <h3> ​Dynamic Rate [#dynamic-rate]
      • <h3> ​Behavior during burst failures [#behavior-during-burst-failures]
      • <h3> ​Recommendation [#recommendation]
92/docs/rate-limits
  • <h1> How to use OpenCode with Together AI to build faster [#page-title]
  • <h1> ​How to use OpenCode with Together AI to build faster [#how-to-use-opencode-with-together-ai-to-build-faster]
    • <h2> ​1. Install OpenCode [#1-install-opencode]
    • <h2> ​2. Launch OpenCode [#2-launch-opencode]
    • <h2> ​3. Configure Together AI [#3-configure-together-ai]
    • <h2> ​4. Bonus: install the opencode vs-code extension [#4-bonus-install-the-opencode-vs-code-extension]
    • <h2> ​Key Features & Usage [#key-features-&-usage]
      • <h3> ​Native Terminal Experience [#native-terminal-experience]
      • <h3> ​Plan Mode vs Build Mode [#plan-mode-vs-build-mode]
      • <h3> ​File References with Fuzzy Search [#file-references-with-fuzzy-search]
    • <h2> ​Best Practices [#best-practices]
      • <h3> ​Give Detailed Context [#give-detailed-context]
      • <h3> ​Use Examples and References [#use-examples-and-references]
      • <h3> ​Iterate on Plans [#iterate-on-plans]
    • <h2> ​Model Recommendations [#model-recommendations]
    • <h2> ​Getting Started [#getting-started]
162/docs/how-to-use-opencode
  • <h1> How to use Qwen Code with Together AI for enhanced development workflow [#page-title]
  • <h1> ​How to use Qwen Code with Together AI for enhanced development workflow [#how-to-use-qwen-code-with-together-ai-for-enhanced-development-workflow]
    • <h2> ​Why Use Qwen Code with Together AI? [#why-use-qwen-code-with-together-ai]
    • <h2> ​1. Install Qwen Code [#1-install-qwen-code]
    • <h2> ​2. Configure Together AI [#2-configure-together-ai]
      • <h3> ​Method 1: Environment Variables (Recommended) [#method-1-environment-variables-recommended]
      • <h3> ​Method 2: Project .env File [#method-2-project-env-file]
      • <h3> ​Get Your Together AI Credentials [#get-your-together-ai-credentials]
    • <h2> ​3. Choose Your Model [#3-choose-your-model]
      • <h3> ​Recommended Models for Coding [#recommended-models-for-coding]
      • <h3> ​Example Configuration [#example-configuration]
    • <h2> ​4. Launch and Use Qwen Code [#4-launch-and-use-qwen-code]
    • <h2> ​Advanced Tips [#advanced-tips]
      • <h3> ​Token Optimization [#token-optimization]
      • <h3> ​Model Selection Strategy [#model-selection-strategy]
      • <h3> ​Context Window Management [#context-window-management]
    • <h2> ​Troubleshooting [#troubleshooting]
      • <h3> ​Common Issues [#common-issues]
    • <h2> ​Getting Started Checklist [#getting-started-checklist]
192/docs/how-to-use-qwen-code
  • <h1> Data Preparation [#page-title]
    • <h3> ​Which file format should I use for data? [#which-file-format-should-i-use-for-data]
    • <h2> ​Text Data [#text-data]
    • <h2> ​Data formats [#data-formats]
      • <h3> ​Conversational Data [#conversational-data]
      • <h3> ​Instruction Data [#instruction-data]
      • <h3> ​Generic Text Data [#generic-text-data]
      • <h3> ​Preference Data [#preference-data]
      • <h3> ​Tool Calling Data [#tool-calling-data]
      • <h3> ​Reasoning Data [#reasoning-data]
    • <h2> ​Tokenized Data [#tokenized-data]
    • <h2> ​Example [#example]
    • <h2> ​File Check [#file-check]
131/docs/fine-tuning-data-preparation
  • <h1> Overview [#page-title]
    • <h2> New: Dedicated Container Inference
20/intro
  • <h1> Function Calling [#page-title]
    • <h2> ​Introduction [#introduction]
    • <h2> ​Basic Function Calling [#basic-function-calling]
      • <h3> ​Streaming [#streaming]
    • <h2> ​Supported models [#supported-models]
    • <h2> ​Vision language function calling [#vision-language-function-calling]
    • <h2> ​Types of Function Calling [#types-of-function-calling]
      • <h3> ​1. Simple Function Calling [#1-simple-function-calling]
      • <h3> ​2. Multiple Function Calling [#2-multiple-function-calling]
      • <h3> ​3. Parallel Function Calling [#3-parallel-function-calling]
      • <h3> ​4. Parallel Multiple Function Calling [#4-parallel-multiple-function-calling]
      • <h3> ​5. Multi-Step Function Calling [#5-multi-step-function-calling]
      • <h3> ​6. Multi-Turn Function Calling [#6-multi-turn-function-calling]
130/docs/function-calling
  • <h1> Quickstart [#page-title]
    • <h2> ​1. Register for an account [#1-register-for-an-account]
    • <h2> ​2. Install your preferred library [#2-install-your-preferred-library]
    • <h2> ​3. Run your first query against a model [#3-run-your-first-query-against-a-model]
    • <h2> ​Next steps [#next-steps]
    • <h2> ​Resources [#resources]
60/docs/quickstart
  • <h1> Video Generation [#page-title]
    • <h2> ​Generating a video [#generating-a-video]
    • <h2> ​Parameters [#parameters]
    • <h2> ​Reference Images [#reference-images]
    • <h2> ​Keyframe Control [#keyframe-control]
    • <h2> ​Guidance Scale [#guidance-scale]
    • <h2> ​Quality Control with Steps [#quality-control-with-steps]
    • <h2> ​Supported Model Details [#supported-model-details]
    • <h2> ​Troubleshooting [#troubleshooting]
90/docs/videos-overview
  • <h1> Create Chat Completion [#page-title]
10/reference/chat-completions
  • <h1> Batch [#page-title]
    • <h2> ​Overview [#overview]
    • <h2> ​Getting started [#getting-started]
      • <h3> ​1. Prepare your batch file [#1-prepare-your-batch-file]
      • <h3> ​2. Upload your batch input file [#2-upload-your-batch-input-file]
      • <h3> ​3. Create the batch [#3-create-the-batch]
      • <h3> ​4. Check the status of a batch [#4-check-the-status-of-a-batch]
      • <h3> ​5. Retrieve the results [#5-retrieve-the-results]
      • <h3> ​6. Cancel a batch [#6-cancel-a-batch]
      • <h3> ​7. Get a list of all batches [#7-get-a-list-of-all-batches]
    • <h2> ​Model availability & Pricing [#model-availability-&-pricing]
    • <h2> ​Rate limits [#rate-limits]
    • <h2> ​Error handling [#error-handling]
    • <h2> ​Best practices [#best-practices]
      • <h3> ​Optimal Batch Size [#optimal-batch-size]
      • <h3> ​Error Handling [#error-handling-2]
      • <h3> ​Model Selection [#model-selection]
      • <h3> ​Request Formatting [#request-formatting]
      • <h3> ​Monitoring [#monitoring]
    • <h2> ​FAQ [#faq]
200/docs/batch-inference
  • <h1> Guides Homepage [#page-title]
10/docs/guides
  • <h1> Vision LLMs [#page-title]
    • <h2> ​Quickstart [#quickstart]
      • <h3> ​1. Register for an account [#1-register-for-an-account]
      • <h3> ​2. Install your preferred library [#2-install-your-preferred-library]
      • <h3> ​3. Query the models via our API [#3-query-the-models-via-our-api]
      • <h3> ​Query models with a local image [#query-models-with-a-local-image]
      • <h3> ​Query models with video input [#query-models-with-video-input]
      • <h3> ​Query models with multiple images [#query-models-with-multiple-images]
      • <h3> ​Pricing [#pricing]
90/docs/vision-overview
  • <h1> Integrations [#page-title]
    • <h2> ​HuggingFace [#huggingface]
    • <h2> ​Vercel AI SDK [#vercel-ai-sdk]
    • <h2> ​Langchain [#langchain]
    • <h2> ​LlamaIndex [#llamaindex]
    • <h2> ​CrewAI [#crewai]
    • <h2> ​LangGraph [#langgraph]
    • <h2> ​PydanticAI [#pydanticai]
    • <h2> ​Arcade.dev [#arcade-dev]
    • <h2> ​DSPy [#dspy]
    • <h2> ​AutoGen(AG2) [#autogen-ag2]
    • <h2> ​Agno [#agno]
    • <h2> ​MongoDB [#mongodb]
    • <h2> ​Pinecone [#pinecone]
    • <h2> ​Helicone [#helicone]
    • <h2> ​Composio [#composio]
    • <h2> ​Pixeltable [#pixeltable]
170/docs/integrations
  • <h1> Together cookbooks & example apps
    • <h2> Featured cookbooks
      • <h3> Open Data Science Agent
      • <h3> Finetuning Cookbook
      • <h3> Evaluating LLMs on SimpleQA
    • <h2> Featured example app
      • <h3> LlamaCoder
    • <h2> Example apps
      • <h3> EasyEdit
      • <h3> Self.so
      • <h3> BlinkShot
      • <h3> Llama-OCR
      • <h3> Open Deep Research
      • <h3> BillSplit
      • <h3> Smart PDF
    • <h2> Cookbooks
      • <h3> Serial Chain Agent
      • <h3> Conditional Router Agent Workflow
      • <h3> Parallel Agent Workflow
      • <h3> Conversation Finetuning
      • <h3> LoRA Inference and Fine-tuning
      • <h3> Summarization Long Context Finetuning
      • <h3> Open Contextual RAG
      • <h3> Text RAG
      • <h3> Multimodal Search and Conditional Image Generation
      • <h3> Search with Reranking
      • <h3> Semantic Search
270/examples
  • <h1> Chat [#page-title]
    • <h2> ​Playground [#playground]
    • <h2> ​API Usage [#api-usage]
    • <h2> ​Running a single query [#running-a-single-query]
    • <h2> ​Having a long-running conversation [#having-a-long-running-conversation]
    • <h2> ​Customizing how the model responds [#customizing-how-the-model-responds]
    • <h2> ​Streaming responses [#streaming-responses]
    • <h2> ​A note on async support in Python [#a-note-on-async-support-in-python]
80/docs/chat-overview
  • <h1> OpenAI Compatibility [#page-title]
    • <h2> ​Configuring OpenAI to use Together’s API [#configuring-openai-to-use-together’s-api]
    • <h2> ​Querying a chat model [#querying-a-chat-model]
    • <h2> ​Streaming a response [#streaming-a-response]
    • <h2> ​Using Vision Models [#using-vision-models]
    • <h2> ​Image Generation [#image-generation]
    • <h2> ​Text-to-Speech [#text-to-speech]
    • <h2> ​Generating vector embeddings [#generating-vector-embeddings]
    • <h2> ​Structured Outputs [#structured-outputs]
    • <h2> ​Function Calling [#function-calling]
    • <h2> ​Community libraries [#community-libraries]
110/docs/openai-api-compatibility
  • <h1> Serverless Models [#page-title]
    • <h2> Chat
    • <h2> Image
    • <h2> Vision
    • <h2> Video
    • <h2> Audio
    • <h2> Embedding
    • <h2> Rerank
    • <h2> Moderation
    • <h2> ​Chat models [#chat-models]
    • <h2> ​Image models [#image-models]
    • <h2> ​Vision models [#vision-models]
    • <h2> ​Video models [#video-models]
    • <h2> ​Audio models [#audio-models]
    • <h2> ​Embedding models [#embedding-models]
    • <h2> ​Rerank models [#rerank-models]
    • <h2> ​Moderation models [#moderation-models]
170/docs/serverless-models
  • <h1> Structured Outputs [#page-title]
    • <h2> ​Introduction [#introduction]
    • <h2> ​Supported models [#supported-models]
    • <h2> ​Basic example [#basic-example]
      • <h3> ​Prompting the model [#prompting-the-model]
    • <h2> ​Regex example [#regex-example]
    • <h2> ​Reasoning model example [#reasoning-model-example]
    • <h2> ​Vision model example [#vision-model-example]
    • <h2> ​Try out your code in the Together Playground [#try-out-your-code-in-the-together-playground]
90/docs/json-mode
  • <h1> Reasoning [#page-title]
    • <h2> ​Supported models [#supported-models]
    • <h2> ​Quickstart [#quickstart]
    • <h2> ​Enabling and disabling reasoning [#enabling-and-disabling-reasoning]
    • <h2> ​Reasoning effort [#reasoning-effort]
      • <h3> ​Controlling reasoning depth via prompting [#controlling-reasoning-depth-via-prompting]
    • <h2> ​Thinking modes [#thinking-modes]
      • <h3> ​Interleaved thinking [#interleaved-thinking]
      • <h3> ​Preserved thinking [#preserved-thinking]
      • <h3> ​Turn-level thinking [#turn-level-thinking]
    • <h2> ​Handling reasoning tokens [#handling-reasoning-tokens]
      • <h3> ​Separate reasoning field [#separate-reasoning-field]
      • <h3> ​<think> tags in content [#<think>-tags-in-content]
    • <h2> ​Prompting best practices [#prompting-best-practices]
    • <h2> ​When not to use reasoning [#when-not-to-use-reasoning]
    • <h2> ​Managing costs and latency [#managing-costs-and-latency]
160/docs/reasoning-overview
  • <h1> Changelog [#page-title]
    • <h2> ​March, 2026 [#march-2026]
    • <h2> ​February, 2026 [#february-2026]
    • <h2> ​January, 2026 [#january-2026]
    • <h2> ​December, 2025 [#december-2025]
    • <h2> ​November, 2025 [#november-2025]
    • <h2> ​October, 2025 [#october-2025]
    • <h2> ​September, 2025 [#september-2025]
    • <h2> ​August, 2025 [#august-2025]
    • <h2> ​July, 2025 [#july-2025]
100/docs/changelog
  • <h1> Recommended Models [#page-title]
    • <h2> ​Recommended Models by Use Case [#recommended-models-by-use-case]
20/docs/recommended-models
  • <h1> Quickstart: Flux LoRA Inference [#page-title]
    • <h2> ​Generating an image using Flux LoRAs [#generating-an-image-using-flux-loras]
    • <h2> ​Acceptable LoRA URL formats [#acceptable-lora-url-formats]
    • <h2> ​Examples [#examples]
    • <h2> ​Pricing [#pricing]
50/docs/quickstart-flux-lora
  • <h1> Getting Started [#page-title]
    • <h2> ​Prerequisites [#prerequisites]
    • <h2> ​Install the library [#install-the-library]
    • <h2> ​Authenticate your shell [#authenticate-your-shell]
    • <h2> ​Usage [#usage]
      • <h3> ​Options [#options]
60/reference/cli/getting-started
  • <h1> Fine Tuning [#page-title]
    • <h2> ​Setup [#setup]
    • <h2> ​Create [#create]
    • <h2> ​List [#list]
    • <h2> ​Retrieve [#retrieve]
    • <h2> ​Monitor Events [#monitor-events]
    • <h2> ​Cancel [#cancel]
    • <h2> ​Status [#status]
    • <h2> ​Checkpoints [#checkpoints]
    • <h2> ​Download Model and Checkpoint Weights [#download-model-and-checkpoint-weights]
    • <h2> ​Delete [#delete]
110/reference/cli/finetune
  • <h1> Endpoints [#page-title]
    • <h2> ​Setup [#setup]
    • <h2> ​Endpoint ID [#endpoint-id]
      • <h3> ​How to find your endpoint ID [#how-to-find-your-endpoint-id]
    • <h2> ​Create [#create]
      • <h3> ​Usage [#usage]
      • <h3> ​Options [#options]
    • <h2> ​Hardware [#hardware]
      • <h3> ​Usage [#usage-2]
      • <h3> ​Options [#options-2]
    • <h2> ​Retrieve [#retrieve]
      • <h3> ​Usage [#usage-3]
      • <h3> ​Options [#options-3]
    • <h2> ​Update [#update]
      • <h3> ​Usage [#usage-4]
      • <h3> ​Options [#options-4]
    • <h2> ​Start [#start]
      • <h3> ​Usage [#usage-5]
      • <h3> ​Options [#options-5]
    • <h2> ​Stop [#stop]
      • <h3> ​Usage [#usage-6]
      • <h3> ​Options [#options-6]
    • <h2> ​Delete [#delete]
      • <h3> ​Usage [#usage-7]
    • <h2> ​List [#list]
      • <h3> ​Usage [#usage-8]
      • <h3> ​Options [#options-7]
270/reference/cli/endpoints
  • <h1> Authentication [#page-title]
    • <h2> ​Creating an Account [#creating-an-account]
    • <h2> ​Getting Your API Key [#getting-your-api-key]
    • <h2> ​API Key Security [#api-key-security]
      • <h3> ​Regenerating Your API Key [#regenerating-your-api-key]
    • <h2> ​Inviting Others to Use Your Account [#inviting-others-to-use-your-account]
    • <h2> ​Changing Your Email Address [#changing-your-email-address]
    • <h2> ​Deleting Your Account [#deleting-your-account]
      • <h3> ​Steps to Delete Your Account [#steps-to-delete-your-account]
90/reference/authentication
  • <h1> Create Image [#page-title]
10/reference/post-images-generations
  • <h1> Models [#page-title]
    • <h2> ​Setup [#setup]
    • <h2> ​Upload [#upload]
      • <h3> ​Options [#options]
    • <h2> ​List all models [#list-all-models]
      • <h3> ​Options [#options-2]
60/reference/cli/models
  • <h1> Evals [#page-title]
    • <h2> ​Setup [#setup]
    • <h2> ​Create [#create]
      • <h3> ​Options [#options]
    • <h2> ​List [#list]
      • <h3> ​Options [#options-2]
    • <h2> ​Retrieve [#retrieve]
    • <h2> ​Status [#status]
80/reference/cli/evals
  • <h1> Files [#page-title]
    • <h2> ​Setup [#setup]
    • <h2> ​Upload [#upload]
    • <h2> ​List [#list]
    • <h2> ​Retrieve [#retrieve]
    • <h2> ​Retrieve content [#retrieve-content]
    • <h2> ​Delete [#delete]
    • <h2> ​Check [#check]
80/reference/cli/files
  • <h1> LLM Evaluations [#page-title]
    • <h2> ​Overview [#overview]
    • <h2> ​Quickstart [#quickstart]
      • <h3> ​1. Prepare Your Dataset [#1-prepare-your-dataset]
      • <h3> ​2. Upload Your Dataset [#2-upload-your-dataset]
      • <h3> ​3. Run the Evaluation [#3-run-the-evaluation]
      • <h3> ​4. View Results [#4-view-results]
    • <h2> ​Understanding Templates [#understanding-templates]
      • <h3> ​Examples [#examples]
      • <h3> ​Basic Example [#basic-example]
      • <h3> ​Nested Data Example [#nested-data-example]
    • <h2> ​Best Practices [#best-practices]
    • <h2> ​Example: Classification System Prompt [#example-classification-system-prompt]
    • <h2> ​Models and endpoints [#models-and-endpoints]
    • <h2> ​Pricing [#pricing]
    • <h2> ​Waiting times [#waiting-times]
160/docs/ai-evaluations
  • <h1> How To Build An Interactive AI Tutor With Llama 3.1 [#page-title]
    • <h2> ​Building the input prompt and education dropdown [#building-the-input-prompt-and-education-dropdown]
    • <h2> ​Getting web sources with Exa [#getting-web-sources-with-exa]
    • <h2> ​Fetching the content from each source [#fetching-the-content-from-each-source]
    • <h2> ​Using the sources for the chatbot’s initial messages [#using-the-sources-for-the-chatbot’s-initial-messages]
    • <h2> ​Implementing the chatbot endpoint with Together AI’s SDK [#implementing-the-chatbot-endpoint-with-together-ai’s-sdk]
    • <h2> ​Displaying the chatbot’s response in the UI [#displaying-the-chatbot’s-response-in-the-ui]
    • <h2> ​Letting the user ask follow-up questions [#letting-the-user-ask-follow-up-questions]
    • <h2> ​Digging deeper [#digging-deeper]
90/docs/ai-tutor
  • <h1> Parallel Workflow [#page-title]
    • <h2> ​Parallel Architecture [#parallel-architecture]
      • <h3> ​Parallel Workflow Cookbook [#parallel-workflow-cookbook]
    • <h2> ​Setup Client & Helper Functions [#setup-client-&-helper-functions]
    • <h2> ​Implement Workflow [#implement-workflow]
    • <h2> ​Example Usage [#example-usage]
    • <h2> ​Use cases [#use-cases]
    • <h2> ​Subtask Agent Workflow [#subtask-agent-workflow]
      • <h3> ​Subtask Workflow Cookbook [#subtask-workflow-cookbook]
    • <h2> ​Setup Client & Helper Functions [#setup-client-&-helper-functions-2]
    • <h2> ​Implement Workflow [#implement-workflow-2]
    • <h2> ​Example Usage [#example-usage-2]
    • <h2> ​Use cases [#use-cases-2]
130/docs/parallel-workflows
  • <h1> Quickstart: Using Mastra with Together AI [#page-title]
    • <h2> ​Getting started [#getting-started]
      • <h3> ​Create a new Mastra project [#create-a-new-mastra-project]
      • <h3> ​Install dependencies [#install-dependencies]
      • <h3> ​Configure environment variables [#configure-environment-variables]
      • <h3> ​Configure your agent to use Together AI [#configure-your-agent-to-use-together-ai]
      • <h3> ​Running the application [#running-the-application]
    • <h2> ​Next Steps [#next-steps]
80/docs/using-together-with-mastra
  • <h1> Quickstart: Next.Js [#page-title]
    • <h2> ​Installation [#installation]
    • <h2> ​Ask a single question [#ask-a-single-question]
    • <h2> ​Have a long-running chat [#have-a-long-running-chat]
    • <h2> ​Using Vercel AI SDK [#using-vercel-ai-sdk]
    • <h2> ​Using Mastra [#using-mastra]
60/docs/nextjs-chat-quickstart
  • <h1> Quickstart: How to Use OpenClaw with Together AI [#page-title]
    • <h2> ​What is OpenClaw? [#what-is-openclaw]
    • <h2> ​Get started in 2 minutes [#get-started-in-2-minutes]
      • <h3> ​Prerequisites [#prerequisites]
      • <h3> ​Step 1: Onboard with Together AI [#step-1-onboard-with-together-ai]
      • <h3> ​Step 2: Set your default model [#step-2-set-your-default-model]
      • <h3> ​Step 3: Launch and chat [#step-3-launch-and-chat]
    • <h2> ​Environment note [#environment-note]
    • <h2> ​Why Together AI + OpenClaw? [#why-together-ai-+-openclaw]
    • <h2> ​Use cases [#use-cases]
    • <h2> ​The bottom line [#the-bottom-line]
110/docs/how-to-use-openclaw
  • <h1> How to build an AI audio transcription app with Whisper [#page-title]
    • <h2> ​Building the audio recording interface [#building-the-audio-recording-interface]
    • <h2> ​Recording audio in the browser [#recording-audio-in-the-browser]
    • <h2> ​Uploading and transcribing audio [#uploading-and-transcribing-audio]
    • <h2> ​Creating the transcription API with tRPC [#creating-the-transcription-api-with-trpc]
    • <h2> ​Supporting file uploads [#supporting-file-uploads]
    • <h2> ​Adding audio transformations [#adding-audio-transformations]
    • <h2> ​Type safety with tRPC [#type-safety-with-trpc]
    • <h2> ​Going beyond basic transcription [#going-beyond-basic-transcription]
90/docs/how-to-build-real-time-audio-transcription-app
  • <h1> Quickstart: Retrieval Augmented Generation (RAG) [#page-title]
    • <h2> ​1. Register for an account [#1-register-for-an-account]
    • <h2> ​2. Install your preferred library [#2-install-your-preferred-library]
    • <h2> ​3. Data Processing and Chunking [#3-data-processing-and-chunking]
    • <h2> ​4. Generate Vector Index and Perform Retrieval [#4-generate-vector-index-and-perform-retrieval]
    • <h2> ​5. Rerank To Improve Quality [#5-rerank-to-improve-quality]
    • <h2> ​6. Call Generative Model [#6-call-generative-model]
70/docs/quickstart-retrieval-augmented-generation-rag
  • <h1> Video Generation with Wan 2.1 [#page-title]
    • <h2> ​What You’ll Learn [#what-you’ll-learn]
    • <h2> ​Prerequisites [#prerequisites]
    • <h2> ​Overview [#overview]
    • <h2> ​How It Works [#how-it-works]
    • <h2> ​Project Structure [#project-structure]
    • <h2> ​Implementation [#implementation]
      • <h3> ​Sprocket Worker Code [#sprocket-worker-code]
      • <h3> ​Configuration [#configuration]
    • <h2> ​Key Concepts [#key-concepts]
      • <h3> ​How use_torchrun=True Works [#how-use_torchrun=true-works]
      • <h3> ​Distributed Process Initialization [#distributed-process-initialization]
      • <h3> ​Rank 0 Output Pattern [#rank-0-output-pattern]
      • <h3> ​Automatic File Upload with FileOutput [#automatic-file-upload-with-fileoutput]
      • <h3> ​Multi-GPU Configuration [#multi-gpu-configuration]
    • <h2> ​Deployment [#deployment]
      • <h3> ​Deploy [#deploy]
      • <h3> ​Check Deployment Status [#check-deployment-status]
      • <h3> ​Submit Jobs [#submit-jobs]
    • <h2> ​Input Parameters [#input-parameters]
    • <h2> ​Output [#output]
      • <h3> ​Scaling to More GPUs [#scaling-to-more-gpus]
    • <h2> ​Cleanup [#cleanup]
    • <h2> ​Next Steps [#next-steps]
240/docs/dedicated_containers_video
  • <h1> Building a RAG Workflow [#page-title]
    • <h2> ​Introduction [#introduction]
    • <h2> ​RAG Explanation [#rag-explanation]
    • <h2> ​Download and View the Dataset [#download-and-view-the-dataset]
    • <h2> ​Implement Retrieval Pipeline - “R” part of RAG [#implement-retrieval-pipeline-“r”-part-of-rag]
    • <h2> ​We can encapsulate the above in a function [#we-can-encapsulate-the-above-in-a-function]
    • <h2> ​Generation Step - “G” part of RAG [#generation-step-“g”-part-of-rag]
70/docs/building-a-rag-workflow
  • <h1> How To Implement Contextual RAG From Anthropic [#page-title]
    • <h2> ​Contextual RAG: [#contextual-rag]
    • <h2> ​Install Libraries [#install-libraries]
    • <h2> ​Data Processing and Chunking [#data-processing-and-chunking]
    • <h2> ​Generating Contextual Chunks [#generating-contextual-chunks]
    • <h2> ​Vector Index [#vector-index]
    • <h2> ​BM25 Index [#bm25-index]
    • <h2> ​Everything below this point will happen at query time! [#everything-below-this-point-will-happen-at-query-time]
    • <h2> ​Reranker To improve Quality [#reranker-to-improve-quality]
    • <h2> ​Call Generative Model - Llama 3.1 405B [#call-generative-model-llama-3-1-405b]
100/docs/how-to-implement-contextual-rag-from-anthropic
  • <h1> Building An AI Data Analyst [#page-title]
    • <h2> ​1. Prerequisites [#1-prerequisites]
    • <h2> ​2. Install the SDKs [#2-install-the-sdks]
    • <h2> ​3. Define your model and system prompt [#3-define-your-model-and-system-prompt]
    • <h2> ​4. Add code interpreting capabilities and initialize the model [#4-add-code-interpreting-capabilities-and-initialize-the-model]
    • <h2> ​5. Upload the dataset [#5-upload-the-dataset]
    • <h2> ​6. Put everything together [#6-put-everything-together]
    • <h2> ​7. Run the program and see the results [#7-run-the-program-and-see-the-results]
    • <h2> ​Resources [#resources]
90/docs/data-analyst-agent
  • <h1> Sequential Workflow [#page-title]
    • <h2> ​Workflow Architecture [#workflow-architecture]
      • <h3> ​Sequential Workflow Cookbook [#sequential-workflow-cookbook]
    • <h2> ​Setup Client [#setup-client]
    • <h2> ​Implement Workflow [#implement-workflow]
    • <h2> ​Example Usage [#example-usage]
    • <h2> ​Use cases [#use-cases]
70/docs/sequential-agent-workflow
  • <h1> How to Build Coding Agents [#page-title]
    • <h2> ​Setup [#setup]
    • <h2> ​Basic Chat Interaction [#basic-chat-interaction]
    • <h2> ​Tool use by LLMs [#tool-use-by-llms]
    • <h2> ​Defining Tools for the Agent [#defining-tools-for-the-agent]
    • <h2> ​Calling Tools [#calling-tools]
    • <h2> ​More tools: list_files and edit_file [#more-tools-list_files-and-edit_file]
      • <h3> ​list_files Tool: Given a path to a repo, this tool lists the files in that repo. [#list_files-tool-given-a-path-to-a-repo-this-tool-lists-the-files-in-that-repo]
      • <h3> ​edit_file Tool: Edit files by adding new content or replacing old content [#edit_file-tool-edit-files-by-adding-new-content-or-replacing-old-content]
    • <h2> ​Incorporating Tools into the Coding Agent [#incorporating-tools-into-the-coding-agent]
100/docs/how-to-build-coding-agents
  • <h1> Build a Phone Voice Agent with Together AI [#page-title]
    • <h2> ​Architecture [#architecture]
    • <h2> ​Prerequisites [#prerequisites]
    • <h2> ​Step 1: Create the Project [#step-1-create-the-project]
    • <h2> ​Step 2: Add Environment Variables [#step-2-add-environment-variables]
    • <h2> ​Step 3: Add the Audio Conversion Layer [#step-3-add-the-audio-conversion-layer]
    • <h2> ​Step 4: Add Local Voice Activity Detection [#step-4-add-local-voice-activity-detection]
    • <h2> ​Step 5: Build the Realtime STT -> LLM -> TTS Pipeline [#step-5-build-the-realtime-stt->-llm->-tts-pipeline]
    • <h2> ​Step 6: Build the Twilio Media Stream Session [#step-6-build-the-twilio-media-stream-session]
    • <h2> ​Step 7: Add the HTTP Server and TwiML Endpoint [#step-7-add-the-http-server-and-twiml-endpoint]
    • <h2> ​Step 8: Check Your Project Layout [#step-8-check-your-project-layout]
    • <h2> ​Step 9: Start the Server [#step-9-start-the-server]
    • <h2> ​Step 10: Expose the App and Connect Twilio [#step-10-expose-the-app-and-connect-twilio]
    • <h2> ​Step 11: Call the Number [#step-11-call-the-number]
    • <h2> ​How the Low-Latency Path Works [#how-the-low-latency-path-works]
    • <h2> ​Tuning the Voice Experience [#tuning-the-voice-experience]
160/docs/how-to-build-phone-voice-agent
  • <h1> How To Build An AI Search Engine (OSS Perplexity Clone) [#page-title]
    • <h2> ​Building the input prompt [#building-the-input-prompt]
    • <h2> ​Getting web sources with Exa [#getting-web-sources-with-exa]
    • <h2> ​Fetching the content from each source [#fetching-the-content-from-each-source]
    • <h2> ​Summarizing the sources [#summarizing-the-sources]
    • <h2> ​Displaying the answer in the UI [#displaying-the-answer-in-the-ui]
    • <h2> ​Digging deeper [#digging-deeper]
70/docs/ai-search-engine
  • <h1> Agent Workflows [#page-title]
    • <h2> ​Sequential [#sequential]
    • <h2> ​Parallel [#parallel]
    • <h2> ​Conditional (If statement) [#conditional-if-statement]
    • <h2> ​Iterative (For loop) [#iterative-for-loop]
50/docs/workflows
  • <h1> Iterative Workflow [#page-title]
    • <h2> ​Workflow Architecture [#workflow-architecture]
    • <h2> ​Setup Client & Helper Functions [#setup-client-&-helper-functions]
    • <h2> ​Implement Workflow [#implement-workflow]
    • <h2> ​Example Usage [#example-usage]
    • <h2> ​Use cases [#use-cases]
      • <h3> ​Iterative Workflow Cookbook [#iterative-workflow-cookbook]
70/docs/iterative-workflow
  • <h1> How to build a Lovable clone with Kimi K2 [#page-title]
    • <h2> ​Scaffolding the initial UI [#scaffolding-the-initial-ui]
    • <h2> ​Generating code in an API route [#generating-code-in-an-api-route]
    • <h2> ​Engineering the system message to only return code [#engineering-the-system-message-to-only-return-code]
    • <h2> ​Running the generated code in the browser [#running-the-generated-code-in-the-browser]
    • <h2> ​Streaming the code for immediate UI feedback [#streaming-the-code-for-immediate-ui-feedback]
    • <h2> ​Digging deeper [#digging-deeper]
70/docs/how-to-build-a-lovable-clone-with-kimi-k2
  • <h1> Conditional Workflow [#page-title]
    • <h2> ​Workflow Architecture [#workflow-architecture]
    • <h2> ​Setup Client & Helper Functions [#setup-client-&-helper-functions]
    • <h2> ​Implement Workflow [#implement-workflow]
    • <h2> ​Example Usage [#example-usage]
    • <h2> ​Use cases [#use-cases]
      • <h3> ​Conditional Workflow Cookbook [#conditional-workflow-cookbook]
70/docs/conditional-workflows
  • <h1> Quickstart: Using Hugging Face Inference With Together [#page-title]
    • <h2> ​Authentication and Billing [#authentication-and-billing]
    • <h2> ​Usage Examples [#usage-examples]
    • <h2> ​1. Text Generation - LLMs [#1-text-generation-llms]
      • <h3> ​a. Chat Completion with Hugging Face Hub library [#a-chat-completion-with-hugging-face-hub-library]
      • <h3> ​b. OpenAI client library [#b-openai-client-library]
    • <h2> ​2. Text-to-Image Generation [#2-text-to-image-generation]
70/docs/quickstart-using-hugging-face-inference
  • <h1> Together Mixture Of Agents (MoA) [#page-title]
    • <h2> ​What is Together MoA? [#what-is-together-moa]
    • <h2> ​Together MoA in 50 lines of code [#together-moa-in-50-lines-of-code]
    • <h2> ​Advanced MoA example [#advanced-moa-example]
    • <h2> ​Resources [#resources]
50/docs/mixture-of-agents
  • <h1> Getting Started with Logprobs [#page-title]
    • <h2> ​Returning logprobs [#returning-logprobs]
      • <h3> ​Response of returning logprobs [#response-of-returning-logprobs]
    • <h2> ​Converting logprobs to probabilities [#converting-logprobs-to-probabilities]
    • <h2> ​A practical example for logprobs: Classification [#a-practical-example-for-logprobs-classification]
    • <h2> ​Conclusion [#conclusion]
60/docs/logprobs
  • <h1> Image Generation with Flux2 [#page-title]
    • <h2> ​What You’ll Learn [#what-you’ll-learn]
    • <h2> ​Prerequisites [#prerequisites]
    • <h2> ​Overview [#overview]
    • <h2> ​How It Works [#how-it-works]
    • <h2> ​Project Structure [#project-structure]
    • <h2> ​Implementation [#implementation]
      • <h3> ​Sprocket Worker Code [#sprocket-worker-code]
      • <h3> ​Configuration [#configuration]
    • <h2> ​Key Concepts [#key-concepts]
      • <h3> ​Base64 Image Encoding [#base64-image-encoding]
      • <h3> ​Generation Parameters [#generation-parameters]
      • <h3> ​Using the Deployment Name from Environment [#using-the-deployment-name-from-environment]
    • <h2> ​Deployment [#deployment]
      • <h3> ​Deploy [#deploy]
      • <h3> ​Check Deployment Status [#check-deployment-status]
      • <h3> ​Submit Jobs [#submit-jobs]
    • <h2> ​Input Parameters [#input-parameters]
    • <h2> ​Output [#output]
      • <h3> ​Batch Processing and Autoscaling [#batch-processing-and-autoscaling]
    • <h2> ​Cleanup [#cleanup]
    • <h2> ​Next Steps [#next-steps]
220/docs/dedicated_containers_image
  • <h1> Python v2 SDK Migration Guide [#page-title]
    • <h2> ​Overview [#overview]
    • <h2> ​Feature Parity Matrix [#feature-parity-matrix]
    • <h2> ​Installation & Setup [#installation-&-setup]
    • <h2> ​Global Breaking Changes [#global-breaking-changes]
      • <h3> ​Constructor Parameters [#constructor-parameters]
      • <h3> ​Keyword-Only Arguments [#keyword-only-arguments]
      • <h3> ​Optional Parameters [#optional-parameters]
      • <h3> ​Extra Parameters [#extra-parameters]
      • <h3> ​Response Type Names [#response-type-names]
      • <h3> ​CLI Commands Removed [#cli-commands-removed]
    • <h2> ​APIs with No Changes Required [#apis-with-no-changes-required]
    • <h2> ​APIs with Changes Required [#apis-with-changes-required]
    • <h2> ​New SDK-Only Features [#new-sdk-only-features]
    • <h2> ​Error Handling Migration [#error-handling-migration]
    • <h2> ​Troubleshooting [#troubleshooting]
    • <h2> ​Best Practices [#best-practices]
    • <h2> ​Getting Help [#getting-help]
180/docs/pythonv2-migration-guide
  • <h1> How To Improve Search With Rerankers [#page-title]
    • <h2> ​Download and View the Dataset [#download-and-view-the-dataset]
    • <h2> ​Implement Semantic Search Pipeline [#implement-semantic-search-pipeline]
    • <h2> ​Use Llama Rank to Rerank Top 25 Movies [#use-llama-rank-to-rerank-top-25-movies]
40/docs/how-to-improve-search-with-rerankers
  • <h1> Quickstart: Using Vercel AI SDK With Together AI [#page-title]
    • <h2> ​QuickStart: 15 lines of code [#quickstart-15-lines-of-code]
      • <h3> ​Output [#output]
    • <h2> ​Streaming with the Vercel AI SDK [#streaming-with-the-vercel-ai-sdk]
      • <h3> ​Output [#output-2]
    • <h2> ​Image Generation [#image-generation]
    • <h2> ​Embedding Models [#embedding-models]
70/docs/using-together-with-vercels-ai-sdk
  • <h1> Quickstart: How to do OCR [#page-title]
    • <h2> ​Understanding OCR and Its Importance [#understanding-ocr-and-its-importance]
    • <h2> ​How to do standard OCR with Together SDK [#how-to-do-standard-ocr-with-together-sdk]
    • <h2> ​How to do structured OCR and extract JSON from images [#how-to-do-structured-ocr-and-extract-json-from-images]
    • <h2> ​Best Practices [#best-practices]
50/docs/quickstart-how-to-do-ocr
  • <h1> How To Build An Open Source NotebookLM: PDF To Podcast [#page-title]
    • <h2> ​Define Dialogue Schema with Pydantic [#define-dialogue-schema-with-pydantic]
    • <h2> ​System Prompt for Script Generation [#system-prompt-for-script-generation]
    • <h2> ​Download PDF and Extract Contents [#download-pdf-and-extract-contents]
    • <h2> ​Generate Podcast Script using JSON Mode [#generate-podcast-script-using-json-mode]
    • <h2> ​Generate Podcast Using TTS [#generate-podcast-using-tts]
60/docs/open-notebooklm-pdf-to-podcast
  • <h1> Speech-to-Text [#page-title]
    • <h2> ​Quick Start [#quick-start]
    • <h2> ​Available Models [#available-models]
    • <h2> ​Audio Transcription [#audio-transcription]
    • <h2> ​Real-time Streaming Transcription [#real-time-streaming-transcription]
    • <h2> ​Audio Translation [#audio-translation]
    • <h2> ​Speaker Diarization [#speaker-diarization]
    • <h2> ​Word-level Timestamps [#word-level-timestamps]
    • <h2> ​Response Formats [#response-formats]
    • <h2> ​Advanced Features [#advanced-features]
    • <h2> ​Async Support [#async-support]
    • <h2> ​Best Practices [#best-practices]
120/docs/speech-to-text
  • <h1> DSPy [#page-title]
    • <h2> ​Installing Libraries [#installing-libraries]
    • <h2> ​Example [#example]
    • <h2> ​Next Steps [#next-steps]
      • <h3> ​DSPy - Together AI Notebook [#dspy-together-ai-notebook]
50/docs/dspy
  • <h1> RAG Integrations [#page-title]
    • <h2> ​Using MongoDB [#using-mongodb]
    • <h2> ​Using LangChain [#using-langchain]
    • <h2> ​Using LlamaIndex [#using-llamaindex]
    • <h2> ​Using Pixeltable [#using-pixeltable]
50/docs/embeddings-rag
  • <h1> CrewAI [#page-title]
    • <h2> ​Installing Libraries [#installing-libraries]
    • <h2> ​Example [#example]
    • <h2> ​Example Output [#example-output]
40/docs/crewai
  • <h1> PydanticAI [#page-title]
    • <h2> ​Installing Libraries [#installing-libraries]
    • <h2> ​Example [#example]
      • <h3> ​Output [#output]
    • <h2> ​Next Steps [#next-steps]
      • <h3> ​PydanticAI - Together AI Notebook [#pydanticai-together-ai-notebook]
60/docs/pydanticai
  • <h1> Rerank [#page-title]
    • <h2> ​What is a reranker? [#what-is-a-reranker]
    • <h2> ​How does Together’s Rerank API work? [#how-does-together’s-rerank-api-work]
    • <h2> ​Get started [#get-started]
      • <h3> ​Example with text [#example-with-text]
      • <h3> ​Example with JSON data (dedicated endpoints only) [#example-with-json-data-dedicated-endpoints-only]
60/docs/rerank-overview
  • <h1> AutoGen(AG2) [#page-title]
    • <h2> ​Installing Libraries [#installing-libraries]
    • <h2> ​Example [#example]
    • <h2> ​Output [#output]
40/docs/autogen
  • <h1> LangGraph [#page-title]
    • <h2> ​Installing Libraries [#installing-libraries]
    • <h2> ​Example [#example]
    • <h2> ​Next Steps [#next-steps]
      • <h3> ​LangGraph - Together AI Notebook [#langgraph-together-ai-notebook]
50/docs/langgraph
  • <h1> Composio [#page-title]
    • <h2> ​Install Libraries [#install-libraries]
    • <h2> ​Example [#example]
      • <h3> ​Connect Your GitHub Account [#connect-your-github-account]
      • <h3> ​Get All Github Tools [#get-all-github-tools]
      • <h3> ​Create a Chat Completion with Tools [#create-a-chat-completion-with-tools]
    • <h2> ​Next Steps [#next-steps]
      • <h3> ​Composio - Together AI Cookbook [#composio-together-ai-cookbook]
80/docs/composio
  • <h1> Agno [#page-title]
    • <h2> ​Install Libraries [#install-libraries]
    • <h2> ​Authentication [#authentication]
    • <h2> ​Example [#example]
    • <h2> ​Next Steps [#next-steps]
      • <h3> ​Agno - Together AI Cookbook [#agno-together-ai-cookbook]
60/docs/agno
  • <h1> API & Integrations [#page-title]
    • <h2> ​Overview [#overview]
    • <h2> ​tcloud CLI [#tcloud-cli]
      • <h3> ​Installation [#installation]
      • <h3> ​Authentication [#authentication]
      • <h3> ​Common Commands [#common-commands]
    • <h2> ​REST API [#rest-api]
      • <h3> ​API Reference [#api-reference]
      • <h3> ​Example: Create Cluster [#example-create-cluster]
      • <h3> ​Example: List Clusters [#example-list-clusters]
      • <h3> ​Example: Delete Cluster [#example-delete-cluster]
    • <h2> ​Terraform Provider [#terraform-provider]
      • <h3> ​Setup [#setup]
      • <h3> ​Example: Define a Cluster [#example-define-a-cluster]
      • <h3> ​Benefits [#benefits]
    • <h2> ​SkyPilot Integration [#skypilot-integration]
      • <h3> ​Installation [#installation-2]
      • <h3> ​Setup [#setup-2]
      • <h3> ​Example: Launch a Workload [#example-launch-a-workload]
      • <h3> ​Example: Fine-tune GPT OSS [#example-fine-tune-gpt-oss]
      • <h3> ​Benefits [#benefits-2]
    • <h2> ​Automation Patterns [#automation-patterns]
      • <h3> ​CI/CD Integration [#ci/cd-integration]
      • <h3> ​Scheduled Jobs [#scheduled-jobs]
      • <h3> ​Auto-scaling Scripts [#auto-scaling-scripts]
    • <h2> ​Best Practices [#best-practices]
      • <h3> ​API Usage [#api-usage]
      • <h3> ​CLI Usage [#cli-usage]
      • <h3> ​Terraform [#terraform]
    • <h2> ​Troubleshooting [#troubleshooting]
      • <h3> ​Authentication issues [#authentication-issues]
      • <h3> ​API rate limits [#api-rate-limits]
      • <h3> ​Terraform state conflicts [#terraform-state-conflicts]
    • <h2> ​What’s Next? [#what’s-next]
340/docs/gpu-clusters-api
  • <h1> Deprecations [#page-title]
    • <h2> ​Overview [#overview]
    • <h2> ​Model Lifecycle Policy [#model-lifecycle-policy]
      • <h3> ​Model Upgrades (Redirects) [#model-upgrades-redirects]
      • <h3> ​New Models (No Redirect) [#new-models-no-redirect]
    • <h2> ​Active Model Redirects [#active-model-redirects]
    • <h2> ​Deprecation Policy [#deprecation-policy]
    • <h2> ​Migration Options [#migration-options]
    • <h2> ​Migration Steps [#migration-steps]
    • <h2> ​Deprecation History [#deprecation-history]
    • <h2> ​Recommended Actions [#recommended-actions]
110/docs/deprecations
  • <h1> Create an Audio Translation [#page-title]
10/reference/audio-translations
  • <h1> Create Audio Generation Request [#page-title]
10/reference/audio-speech
  • <h1> Dedicated Inference [#page-title]
    • <h2> ​Getting Started [#getting-started]
      • <h3> ​1. Select a model [#1-select-a-model]
      • <h3> ​2. Create a dedicated endpoint [#2-create-a-dedicated-endpoint]
      • <h3> ​3. Get endpoint status [#3-get-endpoint-status]
      • <h3> ​4. Start, stop & delete endpoint [#4-start-stop-&-delete-endpoint]
      • <h3> ​5. List your endpoints [#5-list-your-endpoints]
      • <h3> ​6. Send traffic to your endpoint [#6-send-traffic-to-your-endpoint]
    • <h2> ​Endpoint options [#endpoint-options]
      • <h3> ​Replica count [#replica-count]
      • <h3> ​Auto-shutdown [#auto-shutdown]
      • <h3> ​Choosing hardware and GPU count [#choosing-hardware-and-gpu-count]
      • <h3> ​Speculative decoding [#speculative-decoding]
      • <h3> ​Prompt caching [#prompt-caching]
140/docs/dedicated-inference
  • <h1> Create an Audio Transcription [#page-title]
10/reference/audio-transcriptions
  • <h1> Image Generation [#page-title]
    • <h2> ​Generating an image [#generating-an-image]
    • <h2> ​Provide reference image [#provide-reference-image]
      • <h3> ​Using image_url (Kontext models) [#using-image_url-kontext-models]
      • <h3> ​Using reference_images (FLUX.2 & Google models) [#using-reference_images-flux-2-&-google-models]
    • <h2> ​Supported Models [#supported-models]
    • <h2> ​Parameters [#parameters]
    • <h2> ​Generating Multiple Variations [#generating-multiple-variations]
    • <h2> ​Custom Dimensions & Aspect Ratios [#custom-dimensions-&-aspect-ratios]
    • <h2> ​Quality Control with Steps [#quality-control-with-steps]
    • <h2> ​Base64 Images [#base64-images]
    • <h2> ​Safety Checker [#safety-checker]
    • <h2> ​Troubleshooting [#troubleshooting]
130/docs/images-overview
  • <h1> GLM-5 Quickstart [#page-title]
    • <h2> ​How to use GLM-5 [#how-to-use-glm-5]
    • <h2> ​Thinking Modes [#thinking-modes]
      • <h3> ​Recommended Thinking Mode by Use Case [#recommended-thinking-mode-by-use-case]
      • <h3> ​Disabling Thinking [#disabling-thinking]
    • <h2> ​Tool Calling with Interleaved and Preserved Thinking [#tool-calling-with-interleaved-and-preserved-thinking]
    • <h2> ​Use Cases [#use-cases]
    • <h2> ​Prompting Tips [#prompting-tips]
    • <h2> ​General Limitations [#general-limitations]
90/docs/glm-5-quickstart
  • <h1> Kimi K2 QuickStart [#page-title]
    • <h2> ​How to use Kimi K2 [#how-to-use-kimi-k2]
    • <h2> ​Use cases [#use-cases]
    • <h2> ​Prompting tips [#prompting-tips]
    • <h2> ​General Limitations of Kimi K2 [#general-limitations-of-kimi-k2]
50/docs/kimi-k2-quickstart
  • <h1> Llama 4 Quickstart [#page-title]
    • <h2> ​How to use Llama 4 Models [#how-to-use-llama-4-models]
      • <h3> ​Output [#output]
      • <h3> ​Llama4 Notebook [#llama4-notebook]
    • <h2> ​Llama 4 Model Details [#llama-4-model-details]
      • <h3> ​Llama 4 Maverick [#llama-4-maverick]
      • <h3> ​Llama 4 Scout (Deprecated) [#llama-4-scout-deprecated]
    • <h2> ​Function Calling [#function-calling]
      • <h3> ​Output [#output-2]
    • <h2> ​Query models with multiple images [#query-models-with-multiple-images]
      • <h3> ​Output [#output-3]
    • <h2> ​Llama 4 Use-cases [#llama-4-use-cases]
      • <h3> ​Llama 4 Maverick: [#llama-4-maverick]
      • <h3> ​Llama 4 Scout (Deprecated): [#llama-4-scout-deprecated-]
140/docs/llama4-quickstart
  • <h1> Deployment Options Overview [#page-title]
    • <h2> ​Deployment Options Overview [#deployment-options-overview]
    • <h2> ​Together AI Cloud [#together-ai-cloud]
      • <h3> ​Key Features [#key-features]
    • <h2> ​Together AI VPC Deployment [#together-ai-vpc-deployment]
      • <h3> ​Key Features [#key-features-2]
      • <h3> ​Example: VPC Deployment in AWS [#example-vpc-deployment-in-aws]
    • <h2> ​Comparison of Deployment Options [#comparison-of-deployment-options]
    • <h2> ​Next Steps [#next-steps]
90/docs/deployment-options
  • <h1> Single Sign-On (SSO) [#page-title]
    • <h2> ​Supported Providers [#supported-providers]
    • <h2> ​What SSO Enables [#what-sso-enables]
    • <h2> ​Setting Up SSO [#setting-up-sso]
    • <h2> ​Migrating from Legacy Enterprise Sign-On [#migrating-from-legacy-enterprise-sign-on]
    • <h2> ​Session Management [#session-management]
    • <h2> ​FAQs [#faqs]
    • <h2> ​What’s Coming [#what’s-coming]
    • <h2> ​Related [#related]
    • <h2> Together's IAM Model
    • <h2> Organizations
    • <h2> Roles & Permissions
120/docs/sso
  • <h1> Playground [#page-title]
    • <h2> ​Instructions [#instructions]
      • <h3> ​Modifications [#modifications]
      • <h3> ​Parameters [#parameters]
40/docs/inference-web-interface
  • <h1> Dedicated Endpoints FAQs [#page-title]
    • <h2> ​How does the system scale? [#how-does-the-system-scale]
    • <h2> ​How does auto-scaling affect my costs? [#how-does-auto-scaling-affect-my-costs]
    • <h2> ​Is my endpoint guaranteed to scale to the max replica set? [#is-my-endpoint-guaranteed-to-scale-to-the-max-replica-set]
    • <h2> ​When to use vertical vs horizontal scale? [#when-to-use-vertical-vs-horizontal-scale]
      • <h3> ​Vertical scaling [#vertical-scaling]
      • <h3> ​Horizontal scaling [#horizontal-scaling]
    • <h2> ​Troubleshooting dedicated endpoints configuration [#troubleshooting-dedicated-endpoints-configuration]
    • <h2> ​Stopping an Endpoint [#stopping-an-endpoint]
      • <h3> ​Auto-shutdown [#auto-shutdown]
      • <h3> ​Web Interface [#web-interface]
      • <h3> ​API [#api]
    • <h2> ​Will I be billed for the time spent spinning up the endpoint or looking for resources? [#will-i-be-billed-for-the-time-spent-spinning-up-the-endpoint-or-looking-for-resources]
    • <h2> ​How much will I be charged to deploy a model? [#how-much-will-i-be-charged-to-deploy-a-model]
140/docs/dedicated-endpoints
  • <h1> Create Tickets In Slack [#page-title]
    • <h2> ​Emoji Ticketing [#emoji-ticketing]
20/docs/create-tickets-in-slack
  • <h1> Payment Methods & Invoices [#page-title]
    • <h2> ​Supported Payment Methods [#supported-payment-methods]
    • <h2> ​Credit and Debit Cards [#credit-and-debit-cards]
      • <h3> ​Updating Your Payment Card [#updating-your-payment-card]
      • <h3> ​Removing Payment Cards [#removing-payment-cards]
    • <h2> ​ACH Bank Transfers (Early Access) [#ach-bank-transfers-early-access]
      • <h3> ​Adding a bank account [#adding-a-bank-account]
      • <h3> ​Purchasing credits [#purchasing-credits]
      • <h3> ​Things to know [#things-to-know]
      • <h3> ​Troubleshooting [#troubleshooting]
    • <h2> ​Viewing Previous Invoices [#viewing-previous-invoices]
    • <h2> ​Adding Business Details to Invoices [#adding-business-details-to-invoices]
120/docs/billing-payment-methods
  • <h1> Organizations [#page-title]
    • <h2> ​Organization Membership [#organization-membership]
      • <h3> ​Single Sign-On (SSO) [#single-sign-on-sso]
      • <h3> ​Invitation-Based [#invitation-based]
      • <h3> ​Removing Members [#removing-members]
    • <h2> ​Roles [#roles]
    • <h2> ​Projects [#projects]
    • <h2> ​Billing [#billing]
80/docs/organizations
  • <h1> Billing Troubleshooting [#page-title]
    • <h2> ​Troubleshooting Payment Declines [#troubleshooting-payment-declines]
    • <h2> ​Understanding Pending Payments [#understanding-pending-payments]
    • <h2> ​Understanding Unexpected Charges [#understanding-unexpected-charges]
      • <h3> ​Common Causes of Unexpected Charges [#common-causes-of-unexpected-charges]
      • <h3> ​Managing Your Deployments [#managing-your-deployments]
60/docs/billing-troubleshooting
  • <h1> Usage Limits & Analytics [#page-title]
    • <h2> ​Build Tiers and Rate Limits [#build-tiers-and-rate-limits]
      • <h3> ​Required Spend and Rate Limits [#required-spend-and-rate-limits]
      • <h3> ​Model Access by Build Tier [#model-access-by-build-tier]
      • <h3> ​Important Note About Build Tier Access Restrictions [#important-note-about-build-tier-access-restrictions]
      • <h3> ​Exceptions [#exceptions]
      • <h3> ​Understanding Credit Types and Account Tiers [#understanding-credit-types-and-account-tiers]
    • <h2> ​Build Tier Update Delay After Purchase [#build-tier-update-delay-after-purchase]
      • <h3> ​What you may notice while the update is in progress [#what-you-may-notice-while-the-update-is-in-progress]
      • <h3> ​What you should do [#what-you-should-do]
    • <h2> ​Cost Analytics [#cost-analytics]
      • <h3> ​Filtering and Grouping [#filtering-and-grouping]
120/docs/billing-usage-limits
  • <h1> Customer Ticket Portal [#page-title]
    • <h2> ​Accessing the portal [#accessing-the-portal]
    • <h2> ​FAQs [#faqs]
      • <h3> ​I can’t find the ticket portal in the help center, what should I do? [#i-can’t-find-the-ticket-portal-in-the-help-center-what-should-i-do]
      • <h3> ​The ticket I filed is not showing up in the portal, what should I do? [#the-ticket-i-filed-is-not-showing-up-in-the-portal-what-should-i-do]
50/docs/support-ticket-portal
  • <h1> Inference FAQs [#page-title]
    • <h2> ​Model Selection and Availability [#model-selection-and-availability]
      • <h3> ​What models are available for inference on Together? [#what-models-are-available-for-inference-on-together]
      • <h3> ​Which model should I use? [#which-model-should-i-use]
    • <h2> ​Model Parameters and Usage [#model-parameters-and-usage]
      • <h3> ​What is the maximum context window supported by Together models? [#what-is-the-maximum-context-window-supported-by-together-models]
      • <h3> ​Where can I find default parameter values for a model? [#where-can-i-find-default-parameter-values-for-a-model]
      • <h3> ​How do I send a request to an inference endpoint? [#how-do-i-send-a-request-to-an-inference-endpoint]
      • <h3> ​Do you support function calling or tool use? [#do-you-support-function-calling-or-tool-use]
      • <h3> ​Function Calls Not Returned in Response “message.content” [#function-calls-not-returned-in-response-“message-content”]
      • <h3> ​Do you support structured outputs or JSON mode? [#do-you-support-structured-outputs-or-json-mode]
    • <h2> ​Performance and Optimization [#performance-and-optimization]
      • <h3> ​What kind of latency can I expect for inference requests? [#what-kind-of-latency-can-i-expect-for-inference-requests]
      • <h3> ​Is Together suitable for high-throughput workloads? [#is-together-suitable-for-high-throughput-workloads]
      • <h3> ​Does Together support streaming responses? [#does-together-support-streaming-responses]
      • <h3> ​Can I use quantized models for faster inference? [#can-i-use-quantized-models-for-faster-inference]
      • <h3> ​Can I cache prompts or use speculative decoding? [#can-i-cache-prompts-or-use-speculative-decoding]
      • <h3> ​Can I run batched or parallel inference requests? [#can-i-run-batched-or-parallel-inference-requests]
    • <h2> ​Data Privacy and Security [#data-privacy-and-security]
      • <h3> ​Is my data stored or logged? [#is-my-data-stored-or-logged]
      • <h3> ​Will my data be used to train other models? [#will-my-data-be-used-to-train-other-models]
      • <h3> ​Can I run inference in my own VPC or on-premise? [#can-i-run-inference-in-my-own-vpc-or-on-premise]
    • <h2> ​Billing and Limits [#billing-and-limits]
      • <h3> ​How is inference usage billed? [#how-is-inference-usage-billed]
      • <h3> ​What happens if I exceed my rate limit or quota? [#what-happens-if-i-exceed-my-rate-limit-or-quota]
    • <h2> ​Integrations and Support [#integrations-and-support]
      • <h3> ​Can I use Together inference with LangChain or LlamaIndex? [#can-i-use-together-inference-with-langchain-or-llamaindex]
      • <h3> ​How does Together ensure the uptime and reliability of its inference endpoints? [#how-does-together-ensure-the-uptime-and-reliability-of-its-inference-endpoints]
280/docs/inference-faqs
  • <h1> Together's IAM Model [#page-title]
    • <h2> ​Core Concepts [#core-concepts]
    • <h2> ​How It All Fits Together [#how-it-all-fits-together]
    • <h2> ​Resources [#resources]
    • <h2> ​Organization Members and Project Collaborators [#organization-members-and-project-collaborators]
    • <h2> ​Product-Specific Access Guides [#product-specific-access-guides]
    • <h2> GPU Clusters
    • <h2> ​Next Steps [#next-steps]
    • <h2> Organizations
    • <h2> Projects
    • <h2> Roles & Permissions
    • <h2> API Keys
    • <h2> Single Sign-On
130/docs/identity-access-management
  • <h1> API Keys & Authentication [#page-title]
    • <h2> ​Authentication [#authentication]
    • <h2> ​Organization Default Key (Deprecated) [#organization-default-key-deprecated]
    • <h2> ​Creating Additional Project API Keys [#creating-additional-project-api-keys]
    • <h2> ​Project Key Scoping [#project-key-scoping]
    • <h2> ​Cost Analytics & Usage [#cost-analytics-&-usage]
    • <h2> ​Current Limitations [#current-limitations]
    • <h2> ​Playground [#playground]
    • <h2> ​Best Practices [#best-practices]
    • <h2> ​Related [#related]
    • <h2> Projects
    • <h2> Roles & Permissions
    • <h2> API Reference
130/docs/api-keys-authentication
  • <h1> Projects [#page-title]
    • <h2> ​How Projects Work [#how-projects-work]
    • <h2> ​Project Resources [#project-resources]
    • <h2> ​Default Project [#default-project]
    • <h2> ​Managing Project Collaborators [#managing-project-collaborators]
      • <h3> ​Adding Collaborators [#adding-collaborators]
      • <h3> ​Removing Collaborators [#removing-collaborators]
    • <h2> ​Project API Keys [#project-api-keys]
    • <h2> ​Common Project Structures [#common-project-structures]
    • <h2> ​Next Steps [#next-steps]
    • <h2> Roles & Permissions
    • <h2> API Keys
    • <h2> Cluster Access
130/docs/projects
  • <h1> Credits [#page-title]
    • <h2> ​What are Credits Used For? [#what-are-credits-used-for]
    • <h2> ​Free Trial and Access Requirements [#free-trial-and-access-requirements]
    • <h2> ​Auto-Recharge Credits [#auto-recharge-credits]
    • <h2> ​Credit Expiration [#credit-expiration]
50/docs/billing-credits
  • <h1> Fine Tuning FAQs [#page-title]
    • <h2> ​Job Timing [#job-timing]
      • <h3> ​How long will it take for my job to start? [#how-long-will-it-take-for-my-job-to-start]
      • <h3> ​How long will my job take to run? [#how-long-will-my-job-take-to-run]
    • <h2> ​Pricing and Billing [#pricing-and-billing]
      • <h3> ​How can I estimate my fine-tuning job cost? [#how-can-i-estimate-my-fine-tuning-job-cost]
      • <h3> ​Fine-Tuning Pricing [#fine-tuning-pricing]
      • <h3> ​Dedicated Endpoint Charges for Fine-Tuned Models [#dedicated-endpoint-charges-for-fine-tuned-models]
      • <h3> ​Understanding Refunds When Canceling Fine-Tuning Jobs [#understanding-refunds-when-canceling-fine-tuning-jobs]
    • <h2> ​Errors and Troubleshooting [#errors-and-troubleshooting]
      • <h3> ​Why am I getting an error when uploading a training file? [#why-am-i-getting-an-error-when-uploading-a-training-file]
      • <h3> ​Why was my job cancelled? [#why-was-my-job-cancelled]
      • <h3> ​What should I do if my job is cancelled due to billing limits? [#what-should-i-do-if-my-job-is-cancelled-due-to-billing-limits]
      • <h3> ​Why was there an error while running my job? [#why-was-there-an-error-while-running-my-job]
      • <h3> ​How do I know if my job was restarted? [#how-do-i-know-if-my-job-was-restarted]
    • <h2> ​Common Error Codes During Fine-Tuning [#common-error-codes-during-fine-tuning]
    • <h2> ​Model Management [#model-management]
      • <h3> ​Can I download the weights of my model? [#can-i-download-the-weights-of-my-model]
180/docs/fine-tuning-faqs
  • <h1> Deploying Dedicated Endpoints [#page-title]
    • <h2> ​Creating an on demand dedicated endpoint [#creating-an-on-demand-dedicated-endpoint]
20/docs/dedicated-endpoints-ui
  • <h1> Error Codes [#page-title]
10/docs/error-codes
  • <h1> Roles & Permissions (RBAC) [#page-title]
    • <h2> ​Organization Roles [#organization-roles]
      • <h3> ​Organization Permissions [#organization-permissions]
    • <h2> ​Project Roles [#project-roles]
      • <h3> ​Project Permissions [#project-permissions]
    • <h2> ​External Collaborators [#external-collaborators]
    • <h2> ​Product-Specific Permissions [#product-specific-permissions]
      • <h3> ​GPU Clusters (Control Plane) [#gpu-clusters-control-plane]
      • <h3> ​GPU Clusters (Data Plane) [#gpu-clusters-data-plane]
      • <h3> ​Fine-Tuning, Endpoints, Serverless Inference & Other Products [#fine-tuning-endpoints-serverless-inference-&-other-products]
    • <h2> ​What’s Coming [#what’s-coming]
    • <h2> ​Related [#related]
    • <h2> Projects
    • <h2> Together's IAM Model
140/docs/roles-permissions
  • <h1> Quickstart [#page-title]
    • <h2> ​Prerequisites [#prerequisites]
    • <h2> ​Step 1: Install the Together CLI [#step-1-install-the-together-cli]
    • <h2> ​Step 2: Clone the Sprocket Examples [#step-2-clone-the-sprocket-examples]
    • <h2> ​Step 3: Build and Deploy [#step-3-build-and-deploy]
    • <h2> ​Step 4: Watch Deployment Status [#step-4-watch-deployment-status]
    • <h2> ​Step 5: Test the Health Endpoint [#step-5-test-the-health-endpoint]
    • <h2> ​Step 6: Submit a Job [#step-6-submit-a-job]
    • <h2> ​Step 7: Get the Job Result [#step-7-get-the-job-result]
    • <h2> ​Step 8: View Logs [#step-8-view-logs]
    • <h2> ​Step 9: Clean Up [#step-9-clean-up]
    • <h2> ​Next Steps [#next-steps]
      • <h3> ​Example Guides [#example-guides]
130/docs/containers-quickstart
  • <h1> Text-to-Speech [#page-title]
    • <h2> ​Quick Start [#quick-start]
    • <h2> ​Available Models [#available-models]
    • <h2> ​Parameters [#parameters]
    • <h2> ​Streaming Audio [#streaming-audio]
    • <h2> ​WebSocket API [#websocket-api]
    • <h2> ​Output Raw Bytes [#output-raw-bytes]
    • <h2> ​Response Formats [#response-formats]
    • <h2> ​Best Practices [#best-practices]
    • <h2> ​Supported Voices [#supported-voices]
    • <h2> ​Pricing [#pricing]
110/docs/text-to-speech
  • <h1> Introduction [#page-title]
    • <h2> ​Quickstart [#quickstart]
    • <h2> Deploy Your First Container
    • <h2> ​Concepts [#concepts]
    • <h2> Platform Overview
    • <h2> Jig CLI
    • <h2> Sprocket SDK
    • <h2> Queue API
    • <h2> ​Guides [#guides]
    • <h2> Image Generation
    • <h2> Video Generation
    • <h2> ​Reference [#reference]
    • <h2> Jig CLI
    • <h2> Sprocket SDK
    • <h2> REST API
    • <h2> Get Access
160/docs/dedicated-container-inference
  • <h1> Quickstart: Flux Kontext [#page-title]
    • <h2> ​Flux Kontext [#flux-kontext]
    • <h2> ​Generating an image [#generating-an-image]
    • <h2> ​Available Models [#available-models]
    • <h2> ​Common Use Cases [#common-use-cases]
    • <h2> ​Key Parameters [#key-parameters]
60/docs/quickstart-flux-kontext
  • <h1> Dedicated Models [#page-title]
    • <h2> ​Chat models [#chat-models]
    • <h2> ​Rerank models [#rerank-models]
30/docs/dedicated-models
  • <h1> DeepSeek R1 Quickstart [#page-title]
    • <h2> ​How to use DeepSeek-R1 API [#how-to-use-deepseek-r1-api]
    • <h2> ​Working with DeepSeek-R1 [#working-with-deepseek-r1]
    • <h2> ​DeepSeek-R1 Use-cases [#deepseek-r1-use-cases]
    • <h2> ​Managing Context and Costs [#managing-context-and-costs]
    • <h2> ​General Limitations [#general-limitations]
60/docs/deepseek-r1
  • <h1> Reasoning Models Guide [#page-title]
    • <h2> ​Reasoning vs. Non-reasoning Models [#reasoning-vs-non-reasoning-models]
    • <h2> ​Reasoning models use-cases [#reasoning-models-use-cases]
    • <h2> ​Pros and Cons [#pros-and-cons]
40/docs/reasoning-models-guide
  • <h1> Quickstart: FLUX.2 [#page-title]
    • <h2> ​FLUX.2 [#flux-2]
    • <h2> ​Generating an image [#generating-an-image]
    • <h2> ​Parameters [#parameters]
    • <h2> ​Image-to-Image with Reference Images [#image-to-image-with-reference-images]
    • <h2> ​JSON Structured Prompts [#json-structured-prompts]
    • <h2> ​HEX Color Code Prompting [#hex-color-code-prompting]
    • <h2> ​Advanced Use Cases [#advanced-use-cases]
    • <h2> ​Photography Styles [#photography-styles]
    • <h2> ​Multi-Language Support [#multi-language-support]
    • <h2> ​Prompting Best Practices [#prompting-best-practices]
    • <h2> ​Troubleshooting [#troubleshooting]
120/docs/quickstart-flux
  • <h1> Get Queue Metrics [#page-title]
10/reference/queue-metrics
  • <h1> Supported Models [#page-title]
    • <h2> ​LoRA Fine-tuning [#lora-fine-tuning]
    • <h2> ​Full Fine-tuning [#full-fine-tuning]
30/docs/fine-tuning-models
  • <h1> LoRA Supported Modules [#page-title]
    • <h2> ​Text Models [#text-models]
    • <h2> ​Multimodal Models [#multimodal-models]
30/docs/fine-tuning-lora-supported-modules
  • <h1> Upload a Model [#page-title]
    • <h2> ​Getting Started [#getting-started]
      • <h3> ​Requirements [#requirements]
      • <h3> ​Model file structure [#model-file-structure]
      • <h3> ​Uploading from Hugging Face [#uploading-from-hugging-face]
      • <h3> ​Uploading from S3 [#uploading-from-s3]
      • <h3> ​Upload the model [#upload-the-model]
      • <h3> ​Checking the status of your upload [#checking-the-status-of-your-upload]
      • <h3> ​Deploy the model [#deploy-the-model]
90/docs/custom-models
  • <h1> Introduction [#page-title]
10/reference/cli/beta-intro
  • <h1> Upload a file [#page-title]
10/reference/upload-file
  • <h1> Create Evaluation [#page-title]
10/reference/create-evaluation
  • <h1> Supported Models [#page-title]
    • <h2> ​Serverless models [#serverless-models]
    • <h2> ​Dedicated models [#dedicated-models]
    • <h2> ​External models [#external-models]
      • <h3> ​Supported shortcuts [#supported-shortcuts]
      • <h3> ​Custom base URL [#custom-base-url]
60/docs/evaluations-supported-models
  • <h1> AI Evaluations UI [#page-title]
    • <h2> ​Introduction [#introduction]
    • <h2> ​Step 1: Upload Your Dataset [#step-1-upload-your-dataset]
    • <h2> ​Step 2: Customize Your Evaluation Job [#step-2-customize-your-evaluation-job]
      • <h3> ​Evaluation Types [#evaluation-types]
      • <h3> ​Judge Configuration [#judge-configuration]
      • <h3> ​Evaluation Type Parameters [#evaluation-type-parameters]
      • <h3> ​Model Evaluation Configuration [#model-evaluation-configuration]
      • <h3> ​Using External Models [#using-external-models]
    • <h2> ​Step 3: Monitor Job Progress [#step-3-monitor-job-progress]
    • <h2> ​Step 4: Review Results [#step-4-review-results]
110/docs/ai-evaluations-ui
  • <h1> List Deployments [#page-title]
10/reference/deployments-list
  • <h1> Sprocket SDK [#page-title]
    • <h2> ​sprocket.Sprocket [#sprocket-sprocket]
    • <h2> ​sprocket.run [#sprocket-run]
    • <h2> ​sprocket.FileOutput [#sprocket-fileoutput]
    • <h2> ​sprocket.emit_info [#sprocket-emit_info]
    • <h2> ​sprocket.InputOutputProcessor [#sprocket-inputoutputprocessor]
      • <h3> ​Custom I/O Processing [#custom-i/o-processing]
    • <h2> ​HTTP Endpoints [#http-endpoints]
    • <h2> ​CLI Arguments [#cli-arguments]
    • <h2> ​Environment Variables [#environment-variables]
    • <h2> ​Complete Examples [#complete-examples]
      • <h3> ​Image Classification [#image-classification]
      • <h3> ​Video Generation with File Output [#video-generation-with-file-output]
      • <h3> ​Multi-Model Pipeline [#multi-model-pipeline]
140/reference/dci-reference-sprocket
  • <h1> Jig CLI [#page-title]
    • <h2> ​Environment Variables [#environment-variables]
    • <h2> ​Build [#build]
      • <h3> ​jig init [#jig-init]
      • <h3> ​jig dockerfile [#jig-dockerfile]
      • <h3> ​jig build [#jig-build]
      • <h3> ​jig push [#jig-push]
    • <h2> ​Deployments [#deployments]
      • <h3> ​jig deploy [#jig-deploy]
      • <h3> ​jig status [#jig-status]
      • <h3> ​jig list [#jig-list]
      • <h3> ​jig logs [#jig-logs]
      • <h3> ​jig destroy [#jig-destroy]
      • <h3> ​jig endpoint [#jig-endpoint]
    • <h2> ​Queue [#queue]
      • <h3> ​jig submit [#jig-submit]
      • <h3> ​jig job-status [#jig-job-status]
      • <h3> ​jig queue-status [#jig-queue-status]
    • <h2> ​Secrets [#secrets]
      • <h3> ​jig secrets set [#jig-secrets-set]
      • <h3> ​jig secrets list [#jig-secrets-list]
      • <h3> ​jig secrets unset [#jig-secrets-unset]
    • <h2> ​Volumes [#volumes]
      • <h3> ​jig volumes create [#jig-volumes-create]
      • <h3> ​jig volumes update [#jig-volumes-update]
      • <h3> ​jig volumes describe [#jig-volumes-describe]
      • <h3> ​jig volumes list [#jig-volumes-list]
      • <h3> ​jig volumes delete [#jig-volumes-delete]
    • <h2> ​Configuration Reference [#configuration-reference]
      • <h3> ​The [tool.jig.image] section [#the-tool-jig-image-section]
      • <h3> ​The [tool.jig.deploy] section [#the-tool-jig-deploy-section]
      • <h3> ​The [tool.jig.autoscaling] section [#the-tool-jig-autoscaling-section]
      • <h3> ​Full Configuration Example [#full-configuration-example]
330/reference/dci-reference-jig
  • <h1> Agent Integrations [#page-title]
    • <h2> ​LangGraph [#langgraph]
    • <h2> ​CrewAI [#crewai]
    • <h2> ​PydanticAI [#pydanticai]
    • <h2> ​AutoGen(AG2) [#autogen-ag2]
    • <h2> ​DSPy [#dspy]
    • <h2> ​Composio [#composio]
70/docs/agent-integrations
  • <h1> Create a Cluster [#page-title]
10/reference/clusters-create
  • <h1> Embeddings [#page-title]
    • <h2> ​Generating a single embedding [#generating-a-single-embedding]
    • <h2> ​Generating multiple embeddings [#generating-multiple-embeddings]
30/docs/embeddings-overview
  • <h1> Billing & Pricing [#page-title]
    • <h2> ​Billing [#billing]
      • <h3> ​Compute Billing [#compute-billing]
      • <h3> ​Storage Billing [#storage-billing]
      • <h3> ​Viewing Usage and Invoices [#viewing-usage-and-invoices]
      • <h3> ​Cluster and Storage Lifecycles [#cluster-and-storage-lifecycles]
      • <h3> ​Running Out of Credits [#running-out-of-credits]
      • <h3> ​Access Billing Dashboard [#access-billing-dashboard]
      • <h3> ​Invoice Breakdown [#invoice-breakdown]
    • <h2> ​Lifecycle Policies [#lifecycle-policies]
      • <h3> ​Cluster Lifecycle [#cluster-lifecycle]
      • <h3> ​Storage Lifecycle [#storage-lifecycle]
    • <h2> ​Best Practices [#best-practices]
      • <h3> ​Cost Optimization [#cost-optimization]
      • <h3> ​Budget Planning [#budget-planning]
    • <h2> ​Common Questions [#common-questions]
      • <h3> ​Can I get a refund for unused reservation time? [#can-i-get-a-refund-for-unused-reservation-time]
      • <h3> ​What happens if I scale beyond my reservation? [#what-happens-if-i-scale-beyond-my-reservation]
      • <h3> ​How is storage billed if my cluster is terminated? [#how-is-storage-billed-if-my-cluster-is-terminated]
      • <h3> ​Can I pause a cluster to save costs? [#can-i-pause-a-cluster-to-save-costs]
      • <h3> ​When does my reservation start? [#when-does-my-reservation-start]
    • <h2> ​Support [#support]
    • <h2> ​What’s Next? [#what’s-next]
230/docs/gpu-clusters-billing
  • <h1> Cluster Management [#page-title]
    • <h2> ​On this page [#on-this-page]
    • <h2> ​Kubernetes Usage [#kubernetes-usage]
      • <h3> ​Deploy Pods with Storage [#deploy-pods-with-storage]
      • <h3> ​Kubernetes Dashboard [#kubernetes-dashboard]
    • <h2> ​Direct SSH Access [#direct-ssh-access]
      • <h3> ​Prerequisites [#prerequisites]
      • <h3> ​SSH to GPU Worker Nodes (in Kubernetes) and Slurm Compute Nodes (Slurm) [#ssh-to-gpu-worker-nodes-in-kubernetes-and-slurm-compute-nodes-slurm]
      • <h3> ​SSH to Slurm Login Nodes [#ssh-to-slurm-login-nodes]
    • <h2> ​Managing Cluster Access [#managing-cluster-access]
      • <h3> ​Adding Users to a Cluster Project [#adding-users-to-a-cluster-project]
      • <h3> ​Removing Users [#removing-users]
    • <h2> Projects
    • <h2> Roles & Permissions
    • <h2> ​Cluster Scaling [#cluster-scaling]
      • <h3> ​Cluster Autoscaling [#cluster-autoscaling]
      • <h3> ​Targeted Scale-down [#targeted-scale-down]
    • <h2> ​Storage Management [#storage-management]
      • <h3> ​Storage Tiers [#storage-tiers]
      • <h3> ​Upload Data [#upload-data]
      • <h3> ​Resize Storage [#resize-storage]
    • <h2> ​Monitoring and Status [#monitoring-and-status]
      • <h3> ​Check Cluster Health [#check-cluster-health]
    • <h2> ​Best Practices [#best-practices]
      • <h3> ​Resource Management [#resource-management]
      • <h3> ​Job Scheduling [#job-scheduling]
      • <h3> ​Data Management [#data-management]
      • <h3> ​Scaling Strategy [#scaling-strategy]
    • <h2> ​GPU capacity not available [#gpu-capacity-not-available]
    • <h2> ​Troubleshooting [#troubleshooting]
      • <h3> ​Pods not scheduling [#pods-not-scheduling]
      • <h3> ​Storage mount issues [#storage-mount-issues]
      • <h3> ​Slurm jobs not running [#slurm-jobs-not-running]
    • <h2> ​What’s Next? [#what’s-next]
340/docs/gpu-clusters-management
  • <h1> Cluster Storage [#page-title]
    • <h2> ​Upload Your Data [#upload-your-data]
    • <h2> ​Storage Types [#storage-types]
      • <h3> ​1. Local disks [#1-local-disks]
      • <h3> ​2. Shared /home folder for Slurm cluster [#2-shared-/home-folder-for-slurm-cluster]
      • <h3> ​3. Shared remote attached storage [#3-shared-remote-attached-storage]
60/docs/cluster-storage
  • <h1> Quickstart: Create Your First Cluster [#page-title]
    • <h2> ​Create a Cluster [#create-a-cluster]
      • <h3> ​1. Access the Cluster Console [#1-access-the-cluster-console]
      • <h3> ​2. Choose Capacity Type [#2-choose-capacity-type]
      • <h3> ​3. Configure Your Cluster [#3-configure-your-cluster]
      • <h3> ​4. Create and Verify [#4-create-and-verify]
    • <h2> ​Next Steps [#next-steps]
      • <h3> ​For Kubernetes Clusters [#for-kubernetes-clusters]
      • <h3> ​For Slurm Clusters [#for-slurm-clusters]
    • <h2> ​Common First Tasks [#common-first-tasks]
      • <h3> ​Upload Data [#upload-data]
      • <h3> ​Run a Test Job [#run-a-test-job]
    • <h2> ​Troubleshooting [#troubleshooting]
      • <h3> ​Can’t see my nodes [#can’t-see-my-nodes]
      • <h3> ​SSH connection refused [#ssh-connection-refused]
      • <h3> ​Capacity unavailable [#capacity-unavailable]
    • <h2> ​What’s Next? [#what’s-next]
170/docs/gpu-clusters-quickstart
  • <h1> GPU Clusters Overview [#page-title]
    • <h2> ​What are GPU Clusters? [#what-are-gpu-clusters]
    • <h2> ​Concepts [#concepts]
      • <h3> ​Kubernetes Cluster Architecture [#kubernetes-cluster-architecture]
      • <h3> ​Slurm on Kubernetes via Slinky [#slurm-on-kubernetes-via-slinky]
    • <h2> ​Key Features [#key-features]
    • <h2> ​Available Hardware [#available-hardware]
    • <h2> ​Capacity Options [#capacity-options]
      • <h3> ​Reserved Capacity [#reserved-capacity]
      • <h3> ​On-demand Capacity [#on-demand-capacity]
      • <h3> ​Mixing Capacity Types [#mixing-capacity-types]
      • <h3> ​Choosing the Right Type [#choosing-the-right-type]
    • <h2> ​Storage [#storage]
    • <h2> ​Workload Management [#workload-management]
      • <h3> ​Kubernetes [#kubernetes]
      • <h3> ​Slurm [#slurm]
    • <h2> ​Getting Started [#getting-started]
    • <h2> ​Support [#support]
180/docs/gpu-clusters-overview
  • <h1> Health Checks and Node Repair [#page-title]
    • <h2> ​Overview [#overview]
    • <h2> ​Health Checks [#health-checks]
    • <h2> ​How to Run Health Checks [#how-to-run-health-checks]
      • <h3> ​Quick Steps [#quick-steps]
    • <h2> ​Available Health Check Tests [#available-health-check-tests]
      • <h3> ​GPU Diagnostics [#gpu-diagnostics]
      • <h3> ​Network Performance [#network-performance]
      • <h3> ​PCIe Performance [#pcie-performance]
    • <h2> ​Understanding Test Results [#understanding-test-results]
    • <h2> ​Automatic Acceptance Testing [#automatic-acceptance-testing]
      • <h3> ​During Cluster Provisioning [#during-cluster-provisioning]
      • <h3> ​Viewing Acceptance Test Results [#viewing-acceptance-test-results]
      • <h3> ​Why Acceptance Testing Matters [#why-acceptance-testing-matters]
    • <h2> ​When to Run Health Checks [#when-to-run-health-checks]
    • <h2> ​Best Practices [#best-practices]
    • <h2> ​Node Repair [#node-repair]
      • <h3> ​How to Trigger Node Repair [#how-to-trigger-node-repair]
      • <h3> ​Node Repair Lifecycle [#node-repair-lifecycle]
      • <h3> ​Available Repair Actions [#available-repair-actions]
      • <h3> ​Decision Guide: Which Repair Action to Use [#decision-guide-which-repair-action-to-use]
      • <h3> ​Monitoring Repair Progress [#monitoring-repair-progress]
      • <h3> ​Best Practices for Node Repair [#best-practices-for-node-repair]
      • <h3> ​Common Diagnostic Commands [#common-diagnostic-commands]
      • <h3> ​When to Contact Support [#when-to-contact-support]
    • <h2> ​What’s Next? [#what’s-next]
260/docs/health-checks
  • <h1> Create realtime text-to-speech [#page-title]
10/reference/audio-speech-websocket
  • <h1> Create Completion [#page-title]
10/reference/completions
  • <h1> Create a realtime audio transcription [#page-title]
10/reference/audio-transcriptions-realtime
  • <h1> Upload a LoRA Adapter [#page-title]
    • <h2> ​Overview [#overview]
      • <h3> ​Key benefits [#key-benefits]
      • <h3> ​Supported base models [#supported-base-models]
    • <h2> ​Implemenation guide [#implemenation-guide]
      • <h3> ​Prerequisites [#prerequisites]
      • <h3> ​Upload from S3 [#upload-from-s3]
      • <h3> ​Upload from the Hugging Face Hub [#upload-from-the-hugging-face-hub]
      • <h3> ​Upload response [#upload-response]
      • <h3> ​Monitor upload progress [#monitor-upload-progress]
      • <h3> ​Run LoRA inference: [#run-lora-inference]
    • <h2> ​Troubleshooting [#troubleshooting]
      • <h3> ​FAQs [#faqs]
130/docs/adapter-upload
  • <h1> OpenAI GPT-OSS Quickstart [#page-title]
    • <h2> ​How to use GPT-OSS API [#how-to-use-gpt-oss-api]
    • <h2> ​Available Models [#available-models]
    • <h2> ​GPT-OSS Best Practices [#gpt-oss-best-practices]
    • <h2> ​GPT-OSS Use Cases [#gpt-oss-use-cases]
    • <h2> ​Managing Context and Costs [#managing-context-and-costs]
    • <h2> ​Technical Architecture [#technical-architecture]
70/docs/gpt-oss
  • <h1> List All Endpoints [#page-title]
10/reference/listendpoints
  • <h1> Kimi K2 Thinking QuickStart [#page-title]
    • <h2> ​How to use Kimi K2 Thinking [#how-to-use-kimi-k2-thinking]
    • <h2> ​Use cases [#use-cases]
    • <h2> ​Prompting tips [#prompting-tips]
    • <h2> ​General Limitations of Kimi K2 Thinking [#general-limitations-of-kimi-k2-thinking]
50/docs/kimi-k2-thinking-quickstart
  • <h1> DeepSeek V3.1 QuickStart [#page-title]
    • <h2> ​How to use DeepSeek V3.1 [#how-to-use-deepseek-v3-1]
    • <h2> ​Hybrid Thinking [#hybrid-thinking]
    • <h2> ​How is it different from DeepSeek V3? [#how-is-it-different-from-deepseek-v3]
40/docs/deepseek-3-1-quickstart
  • <h1> Fine-tuning Guide [#page-title]
    • <h2> ​Introduction [#introduction]
      • <h3> ​Fine-tuning Guide Notebook [#fine-tuning-guide-notebook]
    • <h2> ​Table of Contents [#table-of-contents]
    • <h2> ​What is Fine-tuning? [#what-is-fine-tuning]
    • <h2> ​Getting Started [#getting-started]
    • <h2> ​Dataset Preparation [#dataset-preparation]
    • <h2> ​Starting a Fine-tuning Job [#starting-a-fine-tuning-job]
    • <h2> ​Monitoring a Fine-tuning Job [#monitoring-a-fine-tuning-job]
    • <h2> ​Deleting a fine-tuning job [#deleting-a-fine-tuning-job]
    • <h2> ​Using a Fine-tuned Model [#using-a-fine-tuned-model]
    • <h2> ​Evaluating a Fine-tuned Model [#evaluating-a-fine-tuned-model]
    • <h2> ​Advanced Topics [#advanced-topics]
      • <h3> ​Continued Fine-tuning jobs and LoRA Serverless Inference [#continued-fine-tuning-jobs-and-lora-serverless-inference]
140/docs/fine-tuning-quickstart
  • <h1> Parameters [#page-title]
    • <h2> ​Max tokens [#max-tokens]
    • <h2> ​Stop words [#stop-words]
    • <h2> ​Temperature [#temperature]
    • <h2> ​Top_p [#top-p]
    • <h2> ​Top_k [#top-k]
    • <h2> ​Repetition penalty [#repetition-penalty]
    • <h2> ​Logprops (API only) [#logprops-api-only]
80/docs/inference-parameters
  • <h1> Inference [#page-title]
10/reference/inference
  • <h1> Jig CLI [#page-title]
    • <h2> ​The Deploy Workflow [#the-deploy-workflow]
    • <h2> ​Cache Warmup [#cache-warmup]
      • <h3> ​How It Works [#how-it-works]
      • <h3> ​Sprocket Integration [#sprocket-integration]
      • <h3> ​Requirements [#requirements]
    • <h2> ​Secrets [#secrets]
    • <h2> ​Volumes [#volumes]
80/docs/deployments-jig
  • <h1> Sprocket SDK [#page-title]
    • <h2> ​How Sprocket Works [#how-sprocket-works]
      • <h3> ​Architecture [#architecture]
    • <h2> ​File Handling [#file-handling]
    • <h2> ​Multi-GPU / Distributed Inference [#multi-gpu-/-distributed-inference]
    • <h2> ​Error Handling [#error-handling]
    • <h2> ​Graceful Shutdown [#graceful-shutdown]
    • <h2> ​Running Modes [#running-modes]
      • <h3> ​Queue Mode [#queue-mode]
      • <h3> ​HTTP Mode (Development/Testing) [#http-mode-development/testing]
    • <h2> ​Progress Reporting [#progress-reporting]
110/docs/deployments-sprocket
  • <h1> LoRA Fine-Tuning and Inference [#page-title]
    • <h2> ​Overview [#overview]
    • <h2> ​Quick start [#quick-start]
      • <h3> ​Prerequisites [#prerequisites]
      • <h3> ​Step 1: Upload Training Data [#step-1-upload-training-data]
      • <h3> ​Step 2: Create Fine-tuning Job [#step-2-create-fine-tuning-job]
      • <h3> ​Step 3: Getting the output model [#step-3-getting-the-output-model]
      • <h3> ​Step 4: Running LoRA inference [#step-4-running-lora-inference]
    • <h2> ​Performance Characteristics [#performance-characteristics]
      • <h3> ​Latency Expectations [#latency-expectations]
    • <h2> ​Best Practices [#best-practices]
    • <h2> ​Frequently Asked Questions [#frequently-asked-questions]
      • <h3> ​Which base models support LoRA fine-tuning? [#which-base-models-support-lora-fine-tuning]
      • <h3> ​What are typical inference latencies? [#what-are-typical-inference-latencies]
      • <h3> ​Can I use streaming responses? [#can-i-use-streaming-responses]
      • <h3> ​How do I migrate pre-December 2024 adapters? [#how-do-i-migrate-pre-december-2024-adapters]
      • <h3> ​What’s the difference between LoRA and full fine-tuning? [#what’s-the-difference-between-lora-and-full-fine-tuning]
    • <h2> ​Next Steps [#next-steps]
180/docs/lora-training-and-inference
  • <h1> Queue API [#page-title]
    • <h2> ​Core Concepts [#core-concepts]
      • <h3> ​Jobs [#jobs]
      • <h3> ​Job Lifecycle [#job-lifecycle]
      • <h3> ​Priority [#priority]
      • <h3> ​Job State with info [#job-state-with-info]
    • <h2> ​Polling for Job Completion [#polling-for-job-completion]
    • <h2> ​Best Practices [#best-practices]
      • <h3> ​Use Priority for Tiered Service [#use-priority-for-tiered-service]
      • <h3> ​Track Progress for Long-Running Jobs [#track-progress-for-long-running-jobs]
      • <h3> ​Handle All Terminal States [#handle-all-terminal-states]
      • <h3> ​Store Metadata in info [#store-metadata-in-info]
    • <h2> ​Error Codes [#error-codes]
    • <h2> ​Related Resources [#related-resources]
140/docs/deployments-queue
  • <h1> Prompting DeepSeek R1 [#page-title]
10/docs/prompting-deepseek-r1
  • <h1> Create Embedding [#page-title]
10/reference/embeddings
  • <h1> Cancel Queue Job [#page-title]
10/reference/queue-cancel
  • <h1> Submit Queue Job [#page-title]
10/reference/queue-submit
  • <h1> Get Queue Status [#page-title]
10/reference/queue-status
  • <h1> Preference Fine-Tuning [#page-title]
    • <h2> ​Data Preparation [#data-preparation]
    • <h2> ​Launching preference fine-tuning [#launching-preference-fine-tuning]
      • <h3> ​Hyperparameters [#hyperparameters]
    • <h2> ​Metrics [#metrics]
    • <h2> ​Combining methods: supervised fine-tuning & preference fine-tuning [#combining-methods-supervised-fine-tuning-&-preference-fine-tuning]
60/docs/preference-fine-tuning
  • <h1> Function Calling Fine-tuning [#page-title]
    • <h2> ​Introduction [#introduction]
    • <h2> ​Quick Links [#quick-links]
    • <h2> ​Function Calling Dataset [#function-calling-dataset]
      • <h3> ​Conversation Tool Calling Format [#conversation-tool-calling-format]
      • <h3> ​Preference Tool Calling Format [#preference-tool-calling-format]
    • <h2> ​Supported Models [#supported-models]
    • <h2> ​Check and Upload Dataset [#check-and-upload-dataset]
    • <h2> ​Starting a Fine-tuning Job [#starting-a-fine-tuning-job]
      • <h3> ​LoRA Fine-tuning (Recommended) [#lora-fine-tuning-recommended]
      • <h3> ​Full Fine-tuning [#full-fine-tuning]
    • <h2> ​Monitoring Your Fine-tuning Job [#monitoring-your-fine-tuning-job]
    • <h2> ​Using Your Fine-tuned Model [#using-your-fine-tuned-model]
      • <h3> ​Dedicated Endpoint Deployment [#dedicated-endpoint-deployment]
140/docs/fine-tuning-function-calling
  • <h1> Deploying a Fine-tuned Model [#page-title]
    • <h2> ​Hosting your model on Together AI [#hosting-your-model-on-together-ai]
    • <h2> ​Serverless LoRA Inference [#serverless-lora-inference]
    • <h2> ​Running Your Model Locally [#running-your-model-locally]
40/docs/deploying-a-fine-tuned-model
  • <h1> Reasoning Fine-tuning [#page-title]
    • <h2> ​Introduction [#introduction]
    • <h2> ​Quick Links [#quick-links]
    • <h2> ​Reasoning Dataset [#reasoning-dataset]
      • <h3> ​Conversation Reasoning Format [#conversation-reasoning-format]
      • <h3> ​Preference Reasoning Format [#preference-reasoning-format]
    • <h2> ​Supported Models [#supported-models]
    • <h2> ​Check and Upload Dataset [#check-and-upload-dataset]
    • <h2> ​Starting a Fine-tuning Job [#starting-a-fine-tuning-job]
      • <h3> ​LoRA Fine-tuning (Recommended) [#lora-fine-tuning-recommended]
      • <h3> ​Full Fine-tuning [#full-fine-tuning]
    • <h2> ​Monitoring Your Fine-tuning Job [#monitoring-your-fine-tuning-job]
    • <h2> ​Using Your Fine-tuned Model [#using-your-fine-tuned-model]
      • <h3> ​Dedicated Endpoint Deployment [#dedicated-endpoint-deployment]
140/docs/fine-tuning-reasoning
  • <h1> Fine-tuning BYOM [#page-title]
    • <h2> ​Overview [#overview]
      • <h3> ​Prerequisites [#prerequisites]
      • <h3> ​Compatibility Check [#compatibility-check]
    • <h2> ​Quick Start [#quick-start]
      • <h3> ​Parameter Explanation [#parameter-explanation]
    • <h2> ​Detailed Implementation Guide [#detailed-implementation-guide]
    • <h2> ​Common Use Cases & Examples [#common-use-cases-&-examples]
      • <h3> ​Architecture-Specific Examples [#architecture-specific-examples]
      • <h3> ​End-to-End Workflow Examples [#end-to-end-workflow-examples]
      • <h3> ​Continuing Training from a Previous Fine-tune [#continuing-training-from-a-previous-fine-tune]
      • <h3> ​Fine-tuning a Community Specialist Model [#fine-tuning-a-community-specialist-model]
    • <h2> ​Troubleshooting [#troubleshooting]
    • <h2> ​Frequently Asked Questions [#frequently-asked-questions]
    • <h2> ​Support [#support]
150/docs/fine-tuning-byom
  • <h1> Pricing [#page-title]
    • <h2> ​Overview [#overview]
    • <h2> ​How Pricing Works [#how-pricing-works]
    • <h2> ​Token Calculation [#token-calculation]
    • <h2> ​Frequently Asked Questions [#frequently-asked-questions]
      • <h3> ​Is there a minimum price for fine-tuning? [#is-there-a-minimum-price-for-fine-tuning]
      • <h3> ​What happens if I cancel my job? [#what-happens-if-i-cancel-my-job]
      • <h3> ​How can I estimate my fine-tuning job cost? [#how-can-i-estimate-my-fine-tuning-job-cost]
80/docs/fine-tuning-pricing
  • <h1> Vision-Language Fine-tuning [#page-title]
    • <h2> ​Introduction [#introduction]
    • <h2> ​Quick Links [#quick-links]
    • <h2> ​VLM Fine-tuning Dataset [#vlm-fine-tuning-dataset]
      • <h3> ​Converting Image URLs to Base64 [#converting-image-urls-to-base64]
      • <h3> ​Conversational Format [#conversational-format]
      • <h3> ​Instruction Format [#instruction-format]
      • <h3> ​Preferential Format [#preferential-format]
    • <h2> ​Supported Models [#supported-models]
    • <h2> ​Check and Upload Dataset [#check-and-upload-dataset]
    • <h2> ​Starting a Fine-tuning Job [#starting-a-fine-tuning-job]
      • <h3> ​VLM-Specific Parameters [#vlm-specific-parameters]
      • <h3> ​LoRA Fine-tuning (Recommended) [#lora-fine-tuning-recommended]
      • <h3> ​Full Fine-tuning [#full-fine-tuning]
    • <h2> ​Monitoring Your Fine-tuning Job [#monitoring-your-fine-tuning-job]
    • <h2> ​Using Your Fine-tuned Model [#using-your-fine-tuned-model]
      • <h3> ​Option 1: Serverless LoRA Inference [#option-1-serverless-lora-inference]
      • <h3> ​Option 2: Dedicated Endpoint Deployment [#option-2-dedicated-endpoint-deployment]
180/docs/fine-tuning-vlm
  • <h1> Clusters [#page-title]
    • <h2> ​Setup [#setup]
    • <h2> ​clusters create [#clusters-create]
    • <h2> ​clusters update [#clusters-update]
    • <h2> ​clusters retrieve [#clusters-retrieve]
    • <h2> ​clusters delete [#clusters-delete]
    • <h2> ​clusters list [#clusters-list]
    • <h2> ​clusters list-regions [#clusters-list-regions]
    • <h2> ​clusters get-credentials [#clusters-get-credentials]
    • <h2> ​clusters storage create [#clusters-storage-create]
    • <h2> ​clusters storage retrieve [#clusters-storage-retrieve]
    • <h2> ​clusters storage list [#clusters-storage-list]
    • <h2> ​clusters storage delete [#clusters-storage-delete]
130/reference/cli/clusters
  • <h1> Containers (Jig) [#page-title]
10/reference/cli/jig-redirect-stub
  • <h1> List All Files [#page-title]
10/reference/get-files
  • <h1> Get File Contents [#page-title]
10/reference/get-files-id-content
  • <h1> List All Evaluations [#page-title]
10/reference/list-evaluations
  • <h1> List File [#page-title]
10/reference/get-files-id
  • <h1> Delete A File [#page-title]
10/reference/delete-files-id
  • <h1> Get Evaluation [#page-title]
10/reference/get-evaluation
  • <h1> Delete A Fine-tuning Event [#page-title]
10/reference/delete-fine-tunes-id
  • <h1> List Evaluation Models [#page-title]
10/reference/list-evaluation-models
  • <h1> Get Evaluation Status [#page-title]
10/reference/get-evaluation-status
  • <h1> Together Code Interpreter [#page-title]
    • <h2> ​Run your first query using the TCI [#run-your-first-query-using-the-tci]
    • <h2> ​Example Use Cases [#example-use-cases]
    • <h2> ​Response Format [#response-format]
    • <h2> ​Usage overview [#usage-overview]
    • <h2> ​Reusing sessions and maintaining state between runs [#reusing-sessions-and-maintaining-state-between-runs]
    • <h2> ​Using the TCI for Data analysis [#using-the-tci-for-data-analysis]
    • <h2> ​Uploading and using files with TCI [#uploading-and-using-files-with-tci]
    • <h2> ​Pre-installed dependencies [#pre-installed-dependencies]
    • <h2> ​List Active Sessions [#list-active-sessions]
    • <h2> ​Further reading [#further-reading]
    • <h2> ​Troubleshooting & questions [#troubleshooting-&-questions]
120/docs/together-code-interpreter
  • <h1> Create Deployment [#page-title]
10/reference/deployments-create
  • <h1> Get Deployment [#page-title]
10/reference/deployments-get
  • <h1> Delete Deployment [#page-title]
10/reference/deployments-delete
  • <h1> Get Deployment Logs [#page-title]
10/reference/deployments-logs
  • <h1> List compute region capabilities [#page-title]
10/reference/clusters-list-regions
  • <h1> Update Deployment [#page-title]
10/reference/deployments-update
  • <h1> List all Clusters [#page-title]
10/reference/clusters-list
  • <h1> Delete a Cluster [#page-title]
10/reference/clusters-delete
  • <h1> Update or Scale GPU Cluster [#page-title]
10/reference/clusters-update
  • <h1> Retrieve Cluster [#page-title]
10/reference/clusters-get
  • <h1> Slurm Management System [#page-title]
    • <h2> ​Overview [#overview]
      • <h3> ​Slurm Basic Concepts [#slurm-basic-concepts]
      • <h3> ​Using Slurm [#using-slurm]
      • <h3> ​Slurm Job Arrays [#slurm-job-arrays]
      • <h3> ​Troubleshooting Slurm [#troubleshooting-slurm]
60/docs/slurm
  • <h1> Slurm Configuration [#page-title]
    • <h2> ​Prerequisites [#prerequisites]
    • <h2> ​Configuration Files [#configuration-files]
    • <h2> ​Edit Configuration [#edit-configuration]
      • <h3> ​Update ConfigMap [#update-configmap]
      • <h3> ​Restart Components [#restart-components]
      • <h3> ​Verify Changes [#verify-changes]
    • <h2> ​Configuration Examples [#configuration-examples]
      • <h3> ​Configure GPU Resources [#configure-gpu-resources]
      • <h3> ​Modify Partitions [#modify-partitions]
      • <h3> ​Tune Scheduler [#tune-scheduler]
      • <h3> ​Update Resource Allocation [#update-resource-allocation]
      • <h3> ​Enable Cgroup Limits [#enable-cgroup-limits]
    • <h2> ​Troubleshooting [#troubleshooting]
      • <h3> ​Configuration Not Applied [#configuration-not-applied]
      • <h3> ​Syntax Errors [#syntax-errors]
      • <h3> ​Pods Not Restarting [#pods-not-restarting]
      • <h3> ​Jobs Failing After Changes [#jobs-failing-after-changes]
    • <h2> ​Quick Reference [#quick-reference]
      • <h3> ​View Configurations [#view-configurations]
      • <h3> ​Restart Components [#restart-components-2]
      • <h3> ​Monitor Cluster [#monitor-cluster]
    • <h2> ​Best Practices [#best-practices]
    • <h2> ​Additional Resources [#additional-resources]
240/docs/slurm-configuration
  • <h1> Create A Rerank Request [#page-title]
10/reference/rerank
  • <h1> List All Models [#page-title]
10/reference/models
  • <h1> Create Video [#page-title]
10/reference/create-videos
  • <h1> Upload a custom model or adapter [#page-title]
10/reference/upload-model
  • <h1> List Available Hardware Configurations [#page-title]
10/reference/listhardware
  • <h1> Delete Endpoint [#page-title]
10/reference/deleteendpoint
  • <h1> Update, Start or Stop Endpoint [#page-title]
10/reference/updateendpoint
  • <h1> Get Endpoint By ID [#page-title]
10/reference/getendpoint
  • <h1> Delete Storage Volume [#page-title]
10/reference/deployments-storage-volumes-delete
  • <h1> Create A Dedicated Endpoint [#page-title]
10/reference/createendpoint
  • <h1> List Job Events [#page-title]
10/reference/get-fine-tunes-id-events
  • <h1> Download Model [#page-title]
10/reference/get-finetune-download
  • <h1> Create Job [#page-title]
10/reference/post-fine-tunes
  • <h1> List Job [#page-title]
10/reference/get-fine-tunes-id
  • <h1> List checkpoints [#page-title]
10/reference/get-fine-tunes-id-checkpoint
  • <h1> Cancel Job [#page-title]
10/reference/post-fine-tunes-id-cancel
  • <h1> Together Code Sandbox [#page-title]
    • <h2> ​Accessing Together Code Sandbox [#accessing-together-code-sandbox]
    • <h2> ​Getting Started [#getting-started]
    • <h2> ​Sandbox life-cycle [#sandbox-life-cycle]
    • <h2> ​Managing CLEAN bootups [#managing-clean-bootups]
    • <h2> ​Using templates [#using-templates]
    • <h2> ​Creating the template [#creating-the-template]
      • <h3> ​Note [#note]
    • <h2> ​Connecting Sandboxes in the browser [#connecting-sandboxes-in-the-browser]
    • <h2> ​Disconnecting the Sandbox [#disconnecting-the-sandbox]
    • <h2> ​Pricing [#pricing]
      • <h3> ​Note [#note-2]
    • <h2> ​VM credit prices by VM size [#vm-credit-prices-by-vm-size]
      • <h3> ​Concurrent VMs [#concurrent-vms]
      • <h3> ​For enterprise [#for-enterprise]
      • <h3> ​Estimating your bill [#estimating-your-bill]
    • <h2> ​Further reading [#further-reading]
170/docs/together-code-sandbox
You have reached the hard limit of 200 rows as a protection against very large output or exhausted memory. You can change this with --rows-limit.
No rows found, please edit your search term.

404 URLs

No 404 URLs found.

Redirected URLs

Found 15 row(s).
StatusRedirected URL 🔼Target URLFound at URL
308 //intro
308 /docs/intro/docs/quickstart-retrieval-augmented-generation-rag
308 /docs/finetuning/docs/fine-tuning-quickstart/docs/preference-fine-tuning
308 /docs/gpu-clusters-capacity-types/docs/gpu-clusters-overview/docs/gpu-clusters-billing
308 /docs/inference-models/docs/serverless-models/reference/chat-completions
308 /docs/inference-rest/intro/docs/error-codes
308 /docs/instant-clusters/docs/gpu-clusters-overview/docs/nanochat-on-instant-clusters
308 /docs/integrations-2/docs/agent-integrations/docs/guides
308 /docs/lora-inference/docs/lora-training-and-inference/docs/changelog
307 /external-link-02https://www.together.ai/blog/how-to-build-a-real-time-image-generat…_au*MTgxMTcxNDI4OS4xNzQyOTc3MTMx/docs/data-analyst-agent
308 /reference/chat-completions-1/reference/chat-completions/docs/changelog
308 /reference/completions-1/reference/completions/docs/serverless-models
308 /reference/embeddings-2/reference/embeddings/docs/recommended-models
308 /reference/rerank-1/reference/rerank/docs/rerank-overview
307 /typescript-libraryhttps://github.com/togethercomputer/together-typescript/reference/authentication
No rows found, please edit your search term.

Skipped URLs Summary

Found 73 row(s).
ReasonDomainUnique URLs 🔽
Not allowed hostapi.together.xyz52
Not allowed hostwww.together.ai41
Not allowed hostgithub.com30
Not allowed hosthuggingface.co20
Not allowed hostapi.together.ai19
Not allowed hostslurm.schedmd.com5
Not allowed hoste2b.dev4
Not allowed hostcodesandbox.io4
Not allowed hostkubernetes.io4
Not allowed hosttogether.ai4
Not allowed hosttogetherai.link4
Not allowed hostreplicate.com2
Not allowed hostai-sdk.dev2
Not allowed hostdocs.llamaindex.ai2
Not allowed hostdocs.nvidia.com2
Not allowed hostdiscord.com2
Not allowed hostwww.turboseek.io1
Not allowed hostwww.npmjs.com1
Not allowed hostcline.bot1
Not allowed hostplatform.openai.com1
Not allowed hostwww.youtube.com1
Not allowed hostnextjs.org1
Not allowed hostwww.logo-creator.io1
Not allowed hostmastra.ai1
Not allowed hostdeveloper.mozilla.org1
Not allowed hostjinja.palletsprojects.com1
Not allowed hostpaulgraham.com1
Not allowed hostwww.usebillsplit.com1
Not allowed hostwww.pdftochat.com1
Not allowed hostmodelcontextprotocol.io1
Not allowed hostampcode.com1
Not allowed hostsandpack.codesandbox.io1
Not allowed hosttogether-nextjs-chat.vercel.app1
Not allowed hostmybucket.s3.amazonaws.com1
Not allowed hostnext-s3-upload.codingvalue.com1
Not allowed hostwww.opendeepresearch.dev1
Not allowed hostnotebooklm.google1
Not allowed hostllamacoder.together.ai1
Not allowed hostsupport.together.ai1
Not allowed hostwww.picmenu.co1
Robots.txtdocs.together.ai1
Not allowed hostcursor.com1
Not allowed hostopenclaw.ai1
Not allowed hostdashboard.exa.ai1
Not allowed hostpython.langchain.com1
Not allowed hostdocs.openclaw.ai1
Not allowed hostwww.anthropic.com1
Not allowed hostpypi.org1
Not allowed hostwww.smartpdfs.ai1
Not allowed hostwww.easyedit.io1
Not allowed hostdocs.astral.sh1
Not allowed hostjson-schema.org1
Not allowed hostwww.kaggle.com1
Not allowed hostportal.usepylon.com1
Not allowed hoststytch.com1
Not allowed hostdiscord.gg1
Not allowed hostllamaocr.com1
Not allowed hostdocs.pixeltable.com1
Not allowed hostdatascience.fm1
Not allowed hostsmithery.ai1
Not allowed hostvscode.dev1
Not allowed hostwww.blinkshot.io1
Not allowed hostwww.napkins.dev1
Not allowed hostwhichllm.together.ai1
Not allowed hostdocs.docker.com1
Not allowed hostwww.self.so1
Not allowed hostopen-vsx.org1
Not allowed hostllamatutor.together.ai1
Not allowed hostwww.python.org1
Not allowed hostarcade.dev1
Not allowed hostcivitai.com1
Not allowed hostexa.ai1
Not allowed hostplatform.composio.dev1
No rows found, please edit your search term.

Skipped URLs

Found 200 row(s).
ReasonSkipped URL 🔼SourceFound at URL
Robots.txt/cdn-cgi/l/email-protection<a href>/docs/integrations
Not allowed hosthttp://together.ai/<a href>/reference/authentication
Not allowed hosthttps://ai-sdk.dev/docs/reference/ai-sdk-core/embed<a href>/docs/using-together-with-vercels-ai-sdk
Not allowed hosthttps://ai-sdk.dev/docs/reference/ai-sdk-core/generate-image<a href>/docs/using-together-with-vercels-ai-sdk
Not allowed hosthttps://ampcode.com/how-to-build-an-agent<a href>/docs/how-to-build-coding-agents
Not allowed hosthttps://api.together.ai/<a href>/docs/integrations
Not allowed hosthttps://api.together.ai/clusters<a href>/docs/nanochat-on-instant-clusters
Not allowed hosthttps://api.together.ai/containers<a href>/docs/containers-quickstart
Not allowed hosthttps://api.together.ai/endpoints<a href>/reference/cli/endpoints
Not allowed hosthttps://api.together.ai/endpoints/configure<a href>/docs/serverless-models
Not allowed hosthttps://api.together.ai/evaluations<a href>/docs/ai-evaluations
Not allowed hosthttps://api.together.ai/jobs<a href>/docs/fine-tuning-faqs
Not allowed hosthttps://api.together.ai/models<a href>/docs/custom-models
Not allowed hosthttps://api.together.ai/models?filter=dedicated<a href>/docs/dedicated-inference
Not allowed hosthttps://api.together.ai/playground/Qwen/Qwen3-VL-8B-Instruct<a href>/docs/vision-overview
Not allowed hosthttps://api.together.ai/playground/Qwen/Qwen3.5-397B-A17B<a href>/docs/vision-overview
Not allowed hosthttps://api.together.ai/playground/chat/Qwen/Qwen3-VL-8B-Instruct<a href>/docs/json-mode
Not allowed hosthttps://api.together.ai/playground/google/gemma-3n-E4B-it<a href>/docs/vision-overview
Not allowed hosthttps://api.together.ai/playground/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8<a href>/docs/vision-overview
Not allowed hosthttps://api.together.ai/settings/api-keys<a href>/reference/authentication
Not allowed hosthttps://api.together.ai/settings/billing<a href>/docs/billing-payment-methods
Not allowed hosthttps://api.together.ai/settings/profile<a href>/docs/inference-faqs
Not allowed hosthttps://api.together.ai/settings/ssh-key<a href>/docs/gpu-clusters-management
Not allowed hosthttps://api.together.ai/signin<a href>/docs/deployment-options
Not allowed hosthttps://api.together.xyz/<a href>/docs/llama4-quickstart
Not allowed hosthttps://api.together.xyz/models<a href>/docs/dedicated-endpoints
Not allowed hosthttps://api.together.xyz/models/Austism/chronos-hermes-13b<a href>/docs/deprecations
Not allowed hosthttps://api.together.xyz/models/Nexusflow/NexusRaven-V2-13B<a href>/docs/deprecations
Not allowed hosthttps://api.together.xyz/models/NousResearch/Nous-Capybara-7B-V1p9<a href>/docs/deprecations
Not allowed hosthttps://api.together.xyz/models/NousResearch/Nous-Hermes-2-Mistral-7B-DPO<a href>/docs/deprecations
Not allowed hosthttps://api.together.xyz/models/NousResearch/Nous-Hermes-2-Mixtral-8x7B-SFT<a href>/docs/deprecations
Not allowed hosthttps://api.together.xyz/models/NousResearch/Nous-Hermes-Llama2-13b<a href>/docs/deprecations
Not allowed hosthttps://api.together.xyz/models/NousResearch/Nous-Hermes-llama-2-7b<a href>/docs/deprecations
Not allowed hosthttps://api.together.xyz/models/Open-Orca/Mistral-7B-OpenOrca<a href>/docs/deprecations
Not allowed hosthttps://api.together.xyz/models/Qwen/Qwen1.5-0.5B<a href>/docs/deprecations
Not allowed hosthttps://api.together.xyz/models/Qwen/Qwen1.5-0.5B-Chat<a href>/docs/deprecations
Not allowed hosthttps://api.together.xyz/models/Qwen/Qwen1.5-1.8B<a href>/docs/deprecations
Not allowed hosthttps://api.together.xyz/models/Qwen/Qwen1.5-1.8B-Chat<a href>/docs/deprecations
Not allowed hosthttps://api.together.xyz/models/Qwen/Qwen1.5-14B<a href>/docs/deprecations
Not allowed hosthttps://api.together.xyz/models/Qwen/Qwen1.5-14B-Chat<a href>/docs/deprecations
Not allowed hosthttps://api.together.xyz/models/Qwen/Qwen1.5-4B<a href>/docs/deprecations
Not allowed hosthttps://api.together.xyz/models/Qwen/Qwen1.5-4B-Chat<a href>/docs/deprecations
Not allowed hosthttps://api.together.xyz/models/Qwen/Qwen1.5-7B<a href>/docs/deprecations
Not allowed hosthttps://api.together.xyz/models/Qwen/Qwen1.5-7B-Chat<a href>/docs/deprecations
Not allowed hosthttps://api.together.xyz/models/Undi95/ReMM-SLERP-L2-13B<a href>/docs/deprecations
Not allowed hosthttps://api.together.xyz/models/Undi95/Toppy-M-7B<a href>/docs/deprecations
Not allowed hosthttps://api.together.xyz/models/WizardLM/WizardLM-13B-V1.2<a href>/docs/deprecations
Not allowed hosthttps://api.together.xyz/models/codellama/CodeLlama-13b-Instruct-hf<a href>/docs/deprecations
Not allowed hosthttps://api.together.xyz/models/codellama/CodeLlama-13b-Python-hf<a href>/docs/deprecations
Not allowed hosthttps://api.together.xyz/models/codellama/CodeLlama-7b-Instruct-hf<a href>/docs/deprecations
Not allowed hosthttps://api.together.xyz/models/codellama/CodeLlama-7b-Python-hf<a href>/docs/deprecations
Not allowed hosthttps://api.together.xyz/models/deepseek-ai/DeepSeek-R1<a href>/docs/deepseek-faqs
Not allowed hosthttps://api.together.xyz/models/deepseek-ai/DeepSeek-V3<a href>/docs/deepseek-faqs
Not allowed hosthttps://api.together.xyz/models/google/gemma-2b<a href>/docs/deprecations
Not allowed hosthttps://api.together.xyz/models/google/gemma-7b<a href>/docs/deprecations
Not allowed hosthttps://api.together.xyz/models/google/gemma-7b-it<a href>/docs/deprecations
Not allowed hosthttps://api.together.xyz/models/lmsys/vicuna-13b-v1.5<a href>/docs/deprecations
Not allowed hosthttps://api.together.xyz/models/lmsys/vicuna-7b-v1.5<a href>/docs/deprecations
Not allowed hosthttps://api.together.xyz/models/meta-llama/Llama-2-7b-chat-hf<a href>/docs/deprecations
Not allowed hosthttps://api.together.xyz/models/meta-llama/Llama-3-8b-hf<a href>/docs/deprecations
Not allowed hosthttps://api.together.xyz/models/meta-llama/Meta-Llama-3-70B<a href>/docs/deprecations
Not allowed hosthttps://api.together.xyz/models/microsoft/phi-2<a href>/docs/deprecations
Not allowed hosthttps://api.together.xyz/models/openchat/openchat-3.5-1210<a href>/docs/deprecations
Not allowed hosthttps://api.together.xyz/models/snorkelai/Snorkel-Mistral-PairRM-DPO<a href>/docs/deprecations
Not allowed hosthttps://api.together.xyz/models/teknium/OpenHermes-2-Mistral-7B<a href>/docs/deprecations
Not allowed hosthttps://api.together.xyz/models/teknium/OpenHermes-2p5-Mistral-7B<a href>/docs/deprecations
Not allowed hosthttps://api.together.xyz/models/togethercomputer/LLaMA-2-7B-32K<a href>/docs/deprecations
Not allowed hosthttps://api.together.xyz/models/togethercomputer/Llama-2-7B-32K-Instruct<a href>/docs/deprecations
Not allowed hosthttps://api.together.xyz/models/togethercomputer/alpaca-7b<a href>/docs/deprecations
Not allowed hosthttps://api.together.xyz/models/upload<a href>/docs/custom-models
Not allowed hosthttps://api.together.xyz/models/zero-one-ai/Yi-6B<a href>/docs/deprecations
Not allowed hosthttps://api.together.xyz/models?filter=dedicated<a href>/docs/dedicated-endpoints
Not allowed hosthttps://api.together.xyz/playground<a href>/docs/quickstart
Not allowed hosthttps://api.together.xyz/settings/api-keys<a href>/docs/quickstart
Not allowed hosthttps://api.together.xyz/settings/billing<a href>/docs/error-codes
Not allowed hosthttps://api.together.xyz/settings/profile<a href>/reference/authentication
Not allowed hosthttps://arcade.dev/<a href>/docs/integrations
Not allowed hosthttps://civitai.com/api/download/models/913438?type=Model&format=SafeTensor<a href>/docs/quickstart-flux-lora
Not allowed hosthttps://cline.bot/<a href>/docs/how-to-use-cline
Not allowed hosthttps://codesandbox.io/blog/joining-together-ai-introducing-codesandbox-sdk<a href>/docs/together-code-sandbox
Not allowed hosthttps://codesandbox.io/docs/sdk/manage-sandboxes<a href>/docs/together-code-sandbox
Not allowed hosthttps://codesandbox.io/pricing<a href>/docs/together-code-sandbox
Not allowed hosthttps://codesandbox.io/t/api<a href>/docs/together-code-sandbox
Not allowed hosthttps://cursor.com/en/install-mcp?name=together-docs&config=eyJ1cmw…RvY3MudG9nZXRoZXIuYWkvbWNwIn0%3D<a href>/docs/mcp
Not allowed hosthttps://dashboard.exa.ai/api-keys<a href>/docs/ai-tutor
Not allowed hosthttps://datascience.fm/creating-dynamic-prompts-with-jinja2-for-llm-queries/<a href>/docs/ai-evaluations
Not allowed hosthttps://developer.mozilla.org/en-US/docs/Web/JavaScript/Reference/Global_Objects/AsyncGenerator<a href>/docs/how-to-build-a-lovable-clone-with-kimi-k2
Not allowed hosthttps://discord.com/channels/1082503318624022589/1228037496257118242<a href>/docs/pythonv2-migration-guide
Not allowed hosthttps://discord.com/invite/9Rk6sSeWEG<a href>/docs/quickstart
Not allowed hosthttps://discord.gg/9Rk6sSeWEG<a href>/docs/fine-tuning-byom
Not allowed hosthttps://docs.astral.sh/uv/<a href>/docs/pythonv2-migration-guide
Not allowed hosthttps://docs.docker.com/engine/install<a href>/docs/dedicated_containers_video
Not allowed hosthttps://docs.llamaindex.ai/en/stable/api_reference/embeddings/together/<a href>/docs/integrations
Not allowed hosthttps://docs.llamaindex.ai/en/stable/examples/llm/together/<a href>/docs/integrations
Not allowed hosthttps://docs.nvidia.com/datacenter/dcgm/latest/user-guide/dcgm-diagnostics.html<a href>/docs/health-checks
Not allowed hosthttps://docs.nvidia.com/deeplearning/nccl/user-guide/docs/index.html<a href>/docs/health-checks
Not allowed hosthttps://docs.openclaw.ai/install<a href>/docs/how-to-use-openclaw
Not allowed hosthttps://docs.pixeltable.com/sdk/latest/together<a href>/docs/embeddings-rag
Not allowed hosthttps://e2b.dev/docs<a href>/docs/data-analyst-agent
Not allowed hosthttps://e2b.dev/docs/api-key<a href>/docs/data-analyst-agent
Not allowed hosthttps://e2b.dev/docs/filesystem/upload<a href>/docs/data-analyst-agent
Not allowed hosthttps://e2b.dev/docs/legacy/code-interpreter/installation<a href>/docs/data-analyst-agent
Not allowed hosthttps://exa.ai/<a href>/docs/ai-tutor
Not allowed hosthttps://github.com/MoonshotAI/Kimi-K2<a href>/docs/kimi-k2-quickstart
Not allowed hosthttps://github.com/NVIDIA/nvbandwidth<a href>/docs/health-checks
Not allowed hosthttps://github.com/Nutlope/blinkshot<a href>/examples
Not allowed hosthttps://github.com/Nutlope/easyedit<a href>/examples
Not allowed hosthttps://github.com/Nutlope/llama-ocr<a href>/examples
Not allowed hosthttps://github.com/Nutlope/llamacoder<a href>/docs/how-to-build-a-lovable-clone-with-kimi-k2
Not allowed hosthttps://github.com/Nutlope/llamatutor<a href>/docs/ai-tutor
Not allowed hosthttps://github.com/Nutlope/open-deep-research<a href>/examples
Not allowed hosthttps://github.com/Nutlope/smartpdfs<a href>/examples
Not allowed hosthttps://github.com/Nutlope/turboseek/<a href>/docs/ai-search-engine
Not allowed hosthttps://github.com/astral-sh/uv<a href>/docs/containers-quickstart
Not allowed hosthttps://github.com/e2b-dev/e2b-cookbook/tree/main<a href>/docs/data-analyst-agent
Not allowed hosthttps://github.com/facebook/zstd<a href>/docs/deploying-a-fine-tuned-model
Not allowed hosthttps://github.com/gabrielchua/open-notebooklm<a href>/docs/open-notebooklm-pdf-to-podcast
Not allowed hosthttps://github.com/karpathy/nanochat<a href>/docs/nanochat-on-instant-clusters
Not allowed hosthttps://github.com/nutlope/billsplit<a href>/examples
Not allowed hosthttps://github.com/nutlope/whisper<a href>/docs/how-to-build-real-time-audio-transcription-app
Not allowed hosthttps://github.com/openai/codex<a href>/docs/mcp
Not allowed hosthttps://github.com/openai/openai-python<a href>/docs/quickstart-using-hugging-face-inference
Not allowed hosthttps://github.com/samselikoff/together-nextjs-chat<a href>/docs/nextjs-chat-quickstart
Not allowed hosthttps://github.com/skypilot-org/skypilot/tree/master/llm/gpt-oss-finetuning<a href>/docs/gpu-clusters-api
Not allowed hosthttps://github.com/snakers4/silero-vad<a href>/docs/how-to-build-phone-voice-agent
Not allowed hosthttps://github.com/togethercomputer/MoA<a href>/docs/mixture-of-agents
Not allowed hosthttps://github.com/togethercomputer/together-cookbook<a href>/docs/quickstart
Not allowed hosthttps://github.com/togethercomputer/together-cookbook/tree/main/Agents<a href>/docs/serverless-models
Not allowed hosthttps://github.com/togethercomputer/together-py<a href>/reference/chat-completions
Not allowed hosthttps://github.com/togethercomputer/together-py/blob/main/examples/tokenize_data.py<a href>/docs/fine-tuning-data-preparation
Not allowed hosthttps://github.com/togethercomputer/together-python<a href>/reference/dci-reference-jig
Not allowed hosthttps://github.com/togethercomputer/together-typescript<a href>/reference/chat-completions
Not allowed hosthttps://github.com/wilicc/gpu-burn<a href>/docs/health-checks
Not allowed hosthttps://huggingface.co/XLabs-AI/flux-lora-collection/blob/main/anime_lora.safetensors<a href>/docs/quickstart-flux-lora
Not allowed hosthttps://huggingface.co/XLabs-AI/flux-lora-collection/resolve/main/anime_lora.safetensors<a href>/docs/quickstart-flux-lora
Not allowed hosthttps://huggingface.co/blog/chat-templates<a href>/docs/ai-evaluations
Not allowed hosthttps://huggingface.co/datasets/HuggingFaceFW/fineweb-edu<a href>/docs/nanochat-on-instant-clusters
Not allowed hosthttps://huggingface.co/datasets/allenai/WildChat<a href>/docs/fine-tuning-data-preparation
Not allowed hosthttps://huggingface.co/datasets/clam004/antihallucination_dataset<a href>/docs/fine-tuning-data-preparation
Not allowed hosthttps://huggingface.co/datasets/davanstrien/cosmochat<a href>/docs/fine-tuning-data-preparation
Not allowed hosthttps://huggingface.co/datasets/glaiveai/glaive-code-assistant<a href>/docs/fine-tuning-data-preparation
Not allowed hosthttps://huggingface.co/datasets/meta-math/MetaMathQA<a href>/docs/fine-tuning-data-preparation
Not allowed hosthttps://huggingface.co/datasets/togethercomputer/RedPajama-Data-1T-Sample<a href>/docs/fine-tuning-data-preparation
Not allowed hosthttps://huggingface.co/deepseek-ai/DeepSeek-R1?inference_api=true&i…rovider=together&language=python<a href>/docs/quickstart-using-hugging-face-inference
Not allowed hosthttps://huggingface.co/docs/transformers/main/en/chat_templating<a href>/docs/fine-tuning-data-preparation
Not allowed hosthttps://huggingface.co/docs/trl/main/en/reducing_memory_usage<a href>/docs/fine-tuning-data-preparation
Not allowed hosthttps://huggingface.co/models?inference_provider=together&other=tex…neration-inference&sort=trending<a href>/docs/quickstart-using-hugging-face-inference
Not allowed hosthttps://huggingface.co/models?inference_provider=together&pipeline_tag=text-to-image&sort=trending<a href>/docs/quickstart-using-hugging-face-inference
Not allowed hosthttps://huggingface.co/models?inference_provider=together&sort=trending<a href>/docs/quickstart-using-hugging-face-inference
Not allowed hosthttps://huggingface.co/moonshotai/Kimi-K2-Thinking<a href>/docs/kimi-k2-thinking-quickstart
Not allowed hosthttps://huggingface.co/multimodalart/flux-tarot-v1<a href>/docs/quickstart-flux-lora
Not allowed hosthttps://huggingface.co/settings/inference-providers<a href>/docs/quickstart-using-hugging-face-inference
Not allowed hosthttps://huggingface.co/spaces/huggingfacejs/chat-template-playground<a href>/docs/ai-evaluations
Not allowed hosthttps://jinja.palletsprojects.com/en/stable/<a href>/docs/ai-evaluations
Not allowed hosthttps://json-schema.org/<a href>/docs/json-mode
Not allowed hosthttps://kubernetes.io/docs/concepts/storage/persistent-volumes/<a href>/docs/gpu-clusters-management
Not allowed hosthttps://kubernetes.io/docs/concepts/storage/volumes/<a href>/docs/gpu-clusters-management
Not allowed hosthttps://kubernetes.io/docs/tasks/tools/<a href>/docs/nanochat-on-instant-clusters
Not allowed hosthttps://kubernetes.io/docs/tasks/tools/install-kubectl-macos/<a href>/docs/gpu-clusters-quickstart
Not allowed hosthttps://llamacoder.together.ai/<a href>/examples
Not allowed hosthttps://llamaocr.com/<a href>/examples
Not allowed hosthttps://llamatutor.together.ai/<a href>/docs/ai-tutor
Not allowed hosthttps://mastra.ai/docs<a href>/docs/using-together-with-mastra
Not allowed hosthttps://modelcontextprotocol.io/<a href>/docs/mcp
Not allowed hosthttps://mybucket.s3.amazonaws.com/my_special_lora.safetensors<a href>/docs/quickstart-flux-lora
Not allowed hosthttps://next-s3-upload.codingvalue.com/<a href>/docs/how-to-build-real-time-audio-transcription-app
Not allowed hosthttps://nextjs.org/docs/app/getting-started/installation<a href>/docs/nextjs-chat-quickstart
Not allowed hosthttps://notebooklm.google/<a href>/docs/open-notebooklm-pdf-to-podcast
Not allowed hosthttps://open-vsx.org/extension/sst-dev/opencode<a href>/docs/how-to-use-opencode
Not allowed hosthttps://openclaw.ai/showcase<a href>/docs/how-to-use-openclaw
Not allowed hosthttps://paulgraham.com/foundermode.html<a href>/docs/quickstart-retrieval-augmented-generation-rag
Not allowed hosthttps://platform.composio.dev/<a href>/docs/composio
Not allowed hosthttps://platform.openai.com/docs/libraries<a href>/docs/openai-api-compatibility
Not allowed hosthttps://portal.usepylon.com/together-ai/forms/support-request<a href>/docs/sso
Not allowed hosthttps://pypi.org/project/transformers/<a href>/docs/deploying-a-fine-tuned-model
Not allowed hosthttps://python.langchain.com/docs/integrations/providers/together/<a href>/docs/integrations
Not allowed hosthttps://replicate.com/fofr/flux-black-light<a href>/docs/quickstart-flux-lora
Not allowed hosthttps://replicate.com/fofr/flux-black-light/versions/d0d48e298dcb51…a063936637a33ac52a8ffd6a94859af7<a href>/docs/quickstart-flux-lora
Not allowed hosthttps://sandpack.codesandbox.io/<a href>/docs/how-to-build-a-lovable-clone-with-kimi-k2
Not allowed hosthttps://slurm.schedmd.com/configurator.html<a href>/docs/slurm-configuration
Not allowed hosthttps://slurm.schedmd.com/gres.html<a href>/docs/slurm-configuration
Not allowed hosthttps://slurm.schedmd.com/quickstart.html<a href>/docs/slurm
Not allowed hosthttps://slurm.schedmd.com/sched_config.html<a href>/docs/slurm-configuration
Not allowed hosthttps://slurm.schedmd.com/slurm.conf.html<a href>/docs/slurm-configuration
Not allowed hosthttps://smithery.ai/server/@togethercomputer/mcp-server-tci<a href>/docs/together-code-interpreter
Not allowed hosthttps://stytch.com/docs/b2b/guides/sso/provider-setup<a href>/docs/sso
Not allowed hosthttps://support.together.ai/<a href>/docs/fine-tuning-byom
Not allowed hosthttps://together-nextjs-chat.vercel.app/<a href>/docs/nextjs-chat-quickstart
Not allowed hosthttps://together.ai/demos<a href>/docs/quickstart
Not allowed hosthttps://together.ai/monthly-reserved<a href>/docs/deprecations
Not allowed hosthttps://together.ai/pricing<a href>/docs/recommended-models
Not allowed hosthttps://togetherai.link/agent-recipes-deep-dive-evaluator<a href>/docs/iterative-workflow
Not allowed hosthttps://togetherai.link/agent-recipes-deep-dive-orchestrator<a href>/docs/parallel-workflows
Not allowed hosthttps://togetherai.link/agent-recipes-deep-dive-parallelization<a href>/docs/parallel-workflows
Not allowed hosthttps://togetherai.link/agent-recipes-deep-dive-routing<a href>/docs/conditional-workflows
Not allowed hosthttps://vscode.dev/redirect/mcp/install?name=Together%20AI%20Docs&c…F%2Fdocs.together.ai%2Fmcp%22%7D<a href>/docs/mcp
Not allowed hosthttps://whichllm.together.ai/<a href>/docs/recommended-models
Not allowed hosthttps://www.anthropic.com/news/contextual-retrieval<a href>/docs/how-to-implement-contextual-rag-from-anthropic
Not allowed hosthttps://www.blinkshot.io/<a href>/examples
Not allowed hosthttps://www.easyedit.io/<a href>/examples
You have reached the hard limit of 200 rows as a protection against very large output or exhausted memory. You can change this with --rows-limit.
No rows found, please edit your search term.

External URLs

253 external URL(s)
Found 200 row(s).
External URLPages 🔽Found on URL (max 5)
http://together.ai/1/reference/authentication
https://ai-sdk.dev/docs/reference/ai-sdk-core/embed1/docs/using-together-with-vercels-ai-sdk
https://ai-sdk.dev/docs/reference/ai-sdk-core/generate-image1/docs/using-together-with-vercels-ai-sdk
https://ampcode.com/how-to-build-an-agent1/docs/how-to-build-coding-agents
https://api.together.ai/1/docs/integrations
https://api.together.ai/clusters1/docs/nanochat-on-instant-clusters
https://api.together.ai/containers1/docs/containers-quickstart
https://api.together.ai/endpoints1/reference/cli/endpoints
https://api.together.ai/endpoints/configure1/docs/serverless-models
https://api.together.ai/evaluations1/docs/ai-evaluations
https://api.together.ai/jobs1/docs/fine-tuning-faqs
https://api.together.ai/models1/docs/custom-models
https://api.together.ai/models?filter=dedicated1/docs/dedicated-inference
https://api.together.ai/playground/Qwen/Qwen3-VL-8B-Instruct1/docs/vision-overview
https://api.together.ai/playground/Qwen/Qwen3.5-397B-A17B1/docs/vision-overview
https://api.together.ai/playground/chat/Qwen/Qwen3-VL-8B-Instruct1/docs/json-mode
https://api.together.ai/playground/google/gemma-3n-E4B-it1/docs/vision-overview
https://api.together.ai/playground/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP81/docs/vision-overview
https://api.together.ai/settings/api-keys1/reference/authentication
https://api.together.ai/settings/billing1/docs/billing-payment-methods
https://api.together.ai/settings/profile1/docs/inference-faqs
https://api.together.ai/settings/ssh-key1/docs/gpu-clusters-management
https://api.together.ai/signin1/docs/deployment-options
https://api.together.xyz/1/docs/llama4-quickstart
https://api.together.xyz/models1/docs/dedicated-endpoints
https://api.together.xyz/models/Austism/chronos-hermes-13b1/docs/deprecations
https://api.together.xyz/models/Nexusflow/NexusRaven-V2-13B1/docs/deprecations
https://api.together.xyz/models/NousResearch/Nous-Capybara-7B-V1p91/docs/deprecations
https://api.together.xyz/models/NousResearch/Nous-Hermes-2-Mistral-7B-DPO1/docs/deprecations
https://api.together.xyz/models/NousResearch/Nous-Hermes-2-Mixtral-8x7B-SFT1/docs/deprecations
https://api.together.xyz/models/NousResearch/Nous-Hermes-Llama2-13b1/docs/deprecations
https://api.together.xyz/models/NousResearch/Nous-Hermes-llama-2-7b1/docs/deprecations
https://api.together.xyz/models/Open-Orca/Mistral-7B-OpenOrca1/docs/deprecations
https://api.together.xyz/models/Qwen/Qwen1.5-0.5B1/docs/deprecations
https://api.together.xyz/models/Qwen/Qwen1.5-0.5B-Chat1/docs/deprecations
https://api.together.xyz/models/Qwen/Qwen1.5-1.8B1/docs/deprecations
https://api.together.xyz/models/Qwen/Qwen1.5-1.8B-Chat1/docs/deprecations
https://api.together.xyz/models/Qwen/Qwen1.5-14B1/docs/deprecations
https://api.together.xyz/models/Qwen/Qwen1.5-14B-Chat1/docs/deprecations
https://api.together.xyz/models/Qwen/Qwen1.5-4B1/docs/deprecations
https://api.together.xyz/models/Qwen/Qwen1.5-4B-Chat1/docs/deprecations
https://api.together.xyz/models/Qwen/Qwen1.5-7B1/docs/deprecations
https://api.together.xyz/models/Qwen/Qwen1.5-7B-Chat1/docs/deprecations
https://api.together.xyz/models/Undi95/ReMM-SLERP-L2-13B1/docs/deprecations
https://api.together.xyz/models/Undi95/Toppy-M-7B1/docs/deprecations
https://api.together.xyz/models/WizardLM/WizardLM-13B-V1.21/docs/deprecations
https://api.together.xyz/models/codellama/CodeLlama-13b-Instruct-hf1/docs/deprecations
https://api.together.xyz/models/codellama/CodeLlama-13b-Python-hf1/docs/deprecations
https://api.together.xyz/models/codellama/CodeLlama-7b-Instruct-hf1/docs/deprecations
https://api.together.xyz/models/codellama/CodeLlama-7b-Python-hf1/docs/deprecations
https://api.together.xyz/models/deepseek-ai/DeepSeek-R11/docs/deepseek-faqs
https://api.together.xyz/models/deepseek-ai/DeepSeek-V31/docs/deepseek-faqs
https://api.together.xyz/models/google/gemma-2b1/docs/deprecations
https://api.together.xyz/models/google/gemma-7b1/docs/deprecations
https://api.together.xyz/models/google/gemma-7b-it1/docs/deprecations
https://api.together.xyz/models/lmsys/vicuna-13b-v1.51/docs/deprecations
https://api.together.xyz/models/lmsys/vicuna-7b-v1.51/docs/deprecations
https://api.together.xyz/models/meta-llama/Llama-2-7b-chat-hf1/docs/deprecations
https://api.together.xyz/models/meta-llama/Llama-3-8b-hf1/docs/deprecations
https://api.together.xyz/models/meta-llama/Meta-Llama-3-70B1/docs/deprecations
https://api.together.xyz/models/microsoft/phi-21/docs/deprecations
https://api.together.xyz/models/openchat/openchat-3.5-12101/docs/deprecations
https://api.together.xyz/models/snorkelai/Snorkel-Mistral-PairRM-DPO1/docs/deprecations
https://api.together.xyz/models/teknium/OpenHermes-2-Mistral-7B1/docs/deprecations
https://api.together.xyz/models/teknium/OpenHermes-2p5-Mistral-7B1/docs/deprecations
https://api.together.xyz/models/togethercomputer/LLaMA-2-7B-32K1/docs/deprecations
https://api.together.xyz/models/togethercomputer/Llama-2-7B-32K-Instruct1/docs/deprecations
https://api.together.xyz/models/togethercomputer/alpaca-7b1/docs/deprecations
https://api.together.xyz/models/upload1/docs/custom-models
https://api.together.xyz/models/zero-one-ai/Yi-6B1/docs/deprecations
https://api.together.xyz/models?filter=dedicated1/docs/dedicated-endpoints
https://api.together.xyz/playground1/docs/quickstart
https://api.together.xyz/settings/api-keys1/docs/quickstart
https://api.together.xyz/settings/billing1/docs/error-codes
https://api.together.xyz/settings/profile1/reference/authentication
https://arcade.dev/1/docs/integrations
https://civitai.com/api/download/models/913438?type=Model&format=SafeTensor1/docs/quickstart-flux-lora
https://cline.bot/1/docs/how-to-use-cline
https://codesandbox.io/blog/joining-together-ai-introducing-codesandbox-sdk1/docs/together-code-sandbox
https://codesandbox.io/docs/sdk/manage-sandboxes1/docs/together-code-sandbox
https://codesandbox.io/pricing1/docs/together-code-sandbox
https://codesandbox.io/t/api1/docs/together-code-sandbox
https://cursor.com/en/install-mcp?name=together-docs&config=eyJ1cmw…RvY3MudG9nZXRoZXIuYWkvbWNwIn0%3D1/docs/mcp
https://dashboard.exa.ai/api-keys1/docs/ai-tutor
https://datascience.fm/creating-dynamic-prompts-with-jinja2-for-llm-queries/1/docs/ai-evaluations
https://developer.mozilla.org/en-US/docs/Web/JavaScript/Reference/Global_Objects/AsyncGenerator1/docs/how-to-build-a-lovable-clone-with-kimi-k2
https://discord.com/channels/1082503318624022589/12280374962571182421/docs/pythonv2-migration-guide
https://discord.com/invite/9Rk6sSeWEG1/docs/quickstart
https://discord.gg/9Rk6sSeWEG1/docs/fine-tuning-byom
https://docs.astral.sh/uv/1/docs/pythonv2-migration-guide
https://docs.docker.com/engine/install1/docs/dedicated_containers_video
https://docs.llamaindex.ai/en/stable/api_reference/embeddings/together/1/docs/integrations
https://docs.llamaindex.ai/en/stable/examples/llm/together/1/docs/integrations
https://docs.nvidia.com/datacenter/dcgm/latest/user-guide/dcgm-diagnostics.html1/docs/health-checks
https://docs.nvidia.com/deeplearning/nccl/user-guide/docs/index.html1/docs/health-checks
https://docs.openclaw.ai/install1/docs/how-to-use-openclaw
https://docs.pixeltable.com/sdk/latest/together1/docs/embeddings-rag
https://e2b.dev/docs1/docs/data-analyst-agent
https://e2b.dev/docs/api-key1/docs/data-analyst-agent
https://e2b.dev/docs/filesystem/upload1/docs/data-analyst-agent
https://e2b.dev/docs/legacy/code-interpreter/installation1/docs/data-analyst-agent
https://exa.ai/1/docs/ai-tutor
https://github.com/MoonshotAI/Kimi-K21/docs/kimi-k2-quickstart
https://github.com/NVIDIA/nvbandwidth1/docs/health-checks
https://github.com/Nutlope/blinkshot1/examples
https://github.com/Nutlope/easyedit1/examples
https://github.com/Nutlope/llama-ocr1/examples
https://github.com/Nutlope/llamacoder1/docs/how-to-build-a-lovable-clone-with-kimi-k2
https://github.com/Nutlope/llamatutor1/docs/ai-tutor
https://github.com/Nutlope/open-deep-research1/examples
https://github.com/Nutlope/smartpdfs1/examples
https://github.com/Nutlope/turboseek/1/docs/ai-search-engine
https://github.com/astral-sh/uv1/docs/containers-quickstart
https://github.com/e2b-dev/e2b-cookbook/tree/main1/docs/data-analyst-agent
https://github.com/facebook/zstd1/docs/deploying-a-fine-tuned-model
https://github.com/gabrielchua/open-notebooklm1/docs/open-notebooklm-pdf-to-podcast
https://github.com/karpathy/nanochat1/docs/nanochat-on-instant-clusters
https://github.com/nutlope/billsplit1/examples
https://github.com/nutlope/whisper1/docs/how-to-build-real-time-audio-transcription-app
https://github.com/openai/codex1/docs/mcp
https://github.com/openai/openai-python1/docs/quickstart-using-hugging-face-inference
https://github.com/samselikoff/together-nextjs-chat1/docs/nextjs-chat-quickstart
https://github.com/skypilot-org/skypilot/tree/master/llm/gpt-oss-finetuning1/docs/gpu-clusters-api
https://github.com/snakers4/silero-vad1/docs/how-to-build-phone-voice-agent
https://github.com/togethercomputer/MoA1/docs/mixture-of-agents
https://github.com/togethercomputer/together-cookbook1/docs/quickstart
https://github.com/togethercomputer/together-cookbook/tree/main/Agents1/docs/serverless-models
https://github.com/togethercomputer/together-py1/reference/chat-completions
https://github.com/togethercomputer/together-py/blob/main/examples/tokenize_data.py1/docs/fine-tuning-data-preparation
https://github.com/togethercomputer/together-python1/reference/dci-reference-jig
https://github.com/togethercomputer/together-typescript1/reference/chat-completions
https://github.com/wilicc/gpu-burn1/docs/health-checks
https://huggingface.co/XLabs-AI/flux-lora-collection/blob/main/anime_lora.safetensors1/docs/quickstart-flux-lora
https://huggingface.co/XLabs-AI/flux-lora-collection/resolve/main/anime_lora.safetensors1/docs/quickstart-flux-lora
https://huggingface.co/blog/chat-templates1/docs/ai-evaluations
https://huggingface.co/datasets/HuggingFaceFW/fineweb-edu1/docs/nanochat-on-instant-clusters
https://huggingface.co/datasets/allenai/WildChat1/docs/fine-tuning-data-preparation
https://huggingface.co/datasets/clam004/antihallucination_dataset1/docs/fine-tuning-data-preparation
https://huggingface.co/datasets/davanstrien/cosmochat1/docs/fine-tuning-data-preparation
https://huggingface.co/datasets/glaiveai/glaive-code-assistant1/docs/fine-tuning-data-preparation
https://huggingface.co/datasets/meta-math/MetaMathQA1/docs/fine-tuning-data-preparation
https://huggingface.co/datasets/togethercomputer/RedPajama-Data-1T-Sample1/docs/fine-tuning-data-preparation
https://huggingface.co/deepseek-ai/DeepSeek-R1?inference_api=true&i…rovider=together&language=python1/docs/quickstart-using-hugging-face-inference
https://huggingface.co/docs/transformers/main/en/chat_templating1/docs/fine-tuning-data-preparation
https://huggingface.co/docs/trl/main/en/reducing_memory_usage1/docs/fine-tuning-data-preparation
https://huggingface.co/models?inference_provider=together&other=tex…neration-inference&sort=trending1/docs/quickstart-using-hugging-face-inference
https://huggingface.co/models?inference_provider=together&pipeline_tag=text-to-image&sort=trending1/docs/quickstart-using-hugging-face-inference
https://huggingface.co/models?inference_provider=together&sort=trending1/docs/quickstart-using-hugging-face-inference
https://huggingface.co/moonshotai/Kimi-K2-Thinking1/docs/kimi-k2-thinking-quickstart
https://huggingface.co/multimodalart/flux-tarot-v11/docs/quickstart-flux-lora
https://huggingface.co/settings/inference-providers1/docs/quickstart-using-hugging-face-inference
https://huggingface.co/spaces/huggingfacejs/chat-template-playground1/docs/ai-evaluations
https://jinja.palletsprojects.com/en/stable/1/docs/ai-evaluations
https://json-schema.org/1/docs/json-mode
https://kubernetes.io/docs/concepts/storage/persistent-volumes/1/docs/gpu-clusters-management
https://kubernetes.io/docs/concepts/storage/volumes/1/docs/gpu-clusters-management
https://kubernetes.io/docs/tasks/tools/1/docs/nanochat-on-instant-clusters
https://kubernetes.io/docs/tasks/tools/install-kubectl-macos/1/docs/gpu-clusters-quickstart
https://llamacoder.together.ai/1/examples
https://llamaocr.com/1/examples
https://llamatutor.together.ai/1/docs/ai-tutor
https://mastra.ai/docs1/docs/using-together-with-mastra
https://modelcontextprotocol.io/1/docs/mcp
https://mybucket.s3.amazonaws.com/my_special_lora.safetensors1/docs/quickstart-flux-lora
https://next-s3-upload.codingvalue.com/1/docs/how-to-build-real-time-audio-transcription-app
https://nextjs.org/docs/app/getting-started/installation1/docs/nextjs-chat-quickstart
https://notebooklm.google/1/docs/open-notebooklm-pdf-to-podcast
https://open-vsx.org/extension/sst-dev/opencode1/docs/how-to-use-opencode
https://openclaw.ai/showcase1/docs/how-to-use-openclaw
https://paulgraham.com/foundermode.html1/docs/quickstart-retrieval-augmented-generation-rag
https://platform.composio.dev/1/docs/composio
https://platform.openai.com/docs/libraries1/docs/openai-api-compatibility
https://portal.usepylon.com/together-ai/forms/support-request1/docs/sso
https://pypi.org/project/transformers/1/docs/deploying-a-fine-tuned-model
https://python.langchain.com/docs/integrations/providers/together/1/docs/integrations
https://replicate.com/fofr/flux-black-light1/docs/quickstart-flux-lora
https://replicate.com/fofr/flux-black-light/versions/d0d48e298dcb51…a063936637a33ac52a8ffd6a94859af71/docs/quickstart-flux-lora
https://sandpack.codesandbox.io/1/docs/how-to-build-a-lovable-clone-with-kimi-k2
https://slurm.schedmd.com/configurator.html1/docs/slurm-configuration
https://slurm.schedmd.com/gres.html1/docs/slurm-configuration
https://slurm.schedmd.com/quickstart.html1/docs/slurm
https://slurm.schedmd.com/sched_config.html1/docs/slurm-configuration
https://slurm.schedmd.com/slurm.conf.html1/docs/slurm-configuration
https://smithery.ai/server/@togethercomputer/mcp-server-tci1/docs/together-code-interpreter
https://stytch.com/docs/b2b/guides/sso/provider-setup1/docs/sso
https://support.together.ai/1/docs/fine-tuning-byom
https://together-nextjs-chat.vercel.app/1/docs/nextjs-chat-quickstart
https://together.ai/demos1/docs/quickstart
https://together.ai/monthly-reserved1/docs/deprecations
https://together.ai/pricing1/docs/recommended-models
https://togetherai.link/agent-recipes-deep-dive-evaluator1/docs/iterative-workflow
https://togetherai.link/agent-recipes-deep-dive-orchestrator1/docs/parallel-workflows
https://togetherai.link/agent-recipes-deep-dive-parallelization1/docs/parallel-workflows
https://togetherai.link/agent-recipes-deep-dive-routing1/docs/conditional-workflows
https://vscode.dev/redirect/mcp/install?name=Together%20AI%20Docs&c…F%2Fdocs.together.ai%2Fmcp%22%7D1/docs/mcp
https://whichllm.together.ai/1/docs/recommended-models
https://www.anthropic.com/news/contextual-retrieval1/docs/how-to-implement-contextual-rag-from-anthropic
https://www.blinkshot.io/1/examples
https://www.easyedit.io/1/examples
https://www.kaggle.com/datasets/nishanthsalian/socioeconomic-country-profiles1/docs/data-analyst-agent
You have reached the hard limit of 200 rows as a protection against very large output or exhausted memory. You can change this with --rows-limit.
No rows found, please edit your search term.

TOP fastest URLs

Found 20 row(s).
Time 🔼StatusFast URL
94 ms 200 /docs/dedicated-models
97 ms 200 /docs/reasoning-models-guide
97 ms 200 /docs/slurm
97 ms 200 /docs/organizations
100 ms200 /reference/list-evaluations
100 ms200 /docs/create-tickets-in-slack
100 ms200 /docs/embeddings-rag
101 ms200 /docs/autogen
102 ms200 /docs/pydanticai
103 ms200 /docs/deployment-options
104 ms200 /docs/billing-payment-methods
104 ms200 /docs/using-together-with-vercels-ai-sdk
104 ms200 /reference/clusters-list
104 ms200 /reference/clusters-update
105 ms200 /docs/projects
105 ms200 /reference/get-evaluation-status
105 ms200 /docs/gpu-clusters-billing
106 ms200 /reference/clusters-list-regions
107 ms200 /docs/embeddings-overview
108 ms200 /docs/billing-credits
No rows found, please edit your search term.

TOP slowest URLs

Found 20 row(s).
Time 🔽StatusSlow URL
498 ms200 /reference/post-fine-tunes
460 ms200 /reference/cli/endpoints
424 ms200 /reference/deployments-storage-volumes-update
411 ms200 /reference/deployments-storage-get
402 ms200 /reference/deployments-secrets-get
374 ms200 /reference/createendpoint
374 ms200 /reference/get-fine-tunes
372 ms200 /reference/delete-files-id
358 ms200 /reference/cli/finetune
350 ms200 /reference/get-finetune-download
350 ms200 /examples
341 ms200 /docs/how-to-build-phone-voice-agent
333 ms200 /reference/deployments-storage-volumes-list
313 ms200 /reference/deployments-storage-volumes-create
309 ms200 /reference/tci-execute
307 ms200 /docs/fine-tuning-lora-supported-modules
299 ms200 /reference/dci-reference-jig
297 ms200 /reference/listendpoints
294 ms200 /reference/clusters_storages-update
288 ms200 /reference/get-fine-tunes-id-checkpoint
No rows found, please edit your search term.

Content types

Content typeURLs 🔽Total sizeTotal timeAvg timeStatus 20xStatus 30x
HTML225126 MB46 s206 ms 225 0
Redirect152 kB5.1 s340 ms 015

Content types (MIME types)

Content typeURLs 🔽Total sizeTotal timeAvg timeStatus 20xStatus 30x
text/html; charset=utf-8225126 MB46 s206 ms 225 0
text / html152 kB5.1 s340 ms 015

Source domains

DomainTotalsHTMLRedirect
docs.together.ai238 / 126MB / 46s223 / 126MB / 41s15 / 2kB / 5.1s
github.com1 / 468kB / 759ms1 / 468kB / 759ms
www.together.ai1 / 369kB / 4.5s1 / 369kB / 4.5s

HTTP headers

Found 29 row(s).
Header 🔼OccursUniqueValues previewMin valueMax value
Age145-[ignored generic values]9.3 hour(s)10.6 hour(s)
Alt-Svc2381h3=":443"; ma=86400
Cache-Control2381no-store, no-cache, must-revalidate, proxy-revalidate, max-age=0
Cf-Cache-Status2381DYNAMIC
Cf-Ray238-[ignored generic values]
Content-Security-Policy2381worker-src * blob: data: 'unsafe-eval' 'unsafe-inline'; object-src data: ; base-…m-action 'self' https://codesandbox.io;
Content-Type2382text/html; charset=utf-8 (223) / text/html (15)
Date238-[ignored generic values]2026-03-242026-03-24
Expires238-[ignored generic values]
Link2381; rel="llms-txt", ; rel="llms-full-txt"
Location1512[see values below]
Pragma2381no-cache
Server2381cloudflare
Strict-Transport-Security2381max-age=2592000; includeSubDomains
Vary2381rsc, next-router-state-tree, next-router-prefetch, next-router-segment-prefetch, Accept-Encoding
X-Cache-Key23820+[see values below]
X-Content-Type-Options2381nosniff
X-Frame-Options2381DENY
X-Llms-Txt2381/llms.txt
X-Matched-Path2381/_sites/[subdomain]/[[...slug]]
X-Mint-Proxy-Version23811.0.0-prod
X-Mintlify-Client-Version23810.0.2698
X-Nextjs-Prerender23811
X-Nextjs-Stale-Time238160
X-Served-Version2381dpl_Cy2pZ1YHL7un8yN36DStGn7XHFL2
X-Vercel-Cache2382MISS (226) / HIT (12)
X-Vercel-Id23820+[see values below]
X-Vercel-Project-Id2381prj_3kakCEKDVpOxnQIJmKyTWs83RXEa
X-Version2381dpl_Cy2pZ1YHL7un8yN36DStGn7XHFL2
No rows found, please edit your search term.

HTTP header values

Found 76 row(s).
HeaderOccursValue
Alt-Svc238h3=":443"; ma=86400
Cache-Control238no-store, no-cache, must-revalidate, proxy-revalidate, max-age=0
Cf-Cache-Status238DYNAMIC
Content-Security-Policy238worker-src * blob: data: 'unsafe-eval' 'unsafe-inline'; object-src data: ; base-uri 'self'; upgrade-insecure-requests; frame-ancestors 'self' https://dashboard.mintlify.com; form-action 'self' https://codesandbox.io;
Content-Type223text/html; charset=utf-8
Content-Type15text / html
Link238</llms.txt>; rel="llms-txt", </llms-full.txt>; rel="llms-full-txt"
Location3/intro
Location2/docs/gpu-clusters-overview
Location1/reference/rerank
Location1/docs/serverless-models
Location1/reference/embeddings
Location1/docs/fine-tuning-quickstart
Location1/reference/completions
Location1/reference/chat-completions
Location1/docs/agent-integrations
Location1https://www.together.ai/blog/how-to-build-a-real-time-image-generat…_au*MTgxMTcxNDI4OS4xNzQyOTc3MTMx
Location1/docs/lora-training-and-inference
Location1https://github.com/togethercomputer/together-typescript
Pragma238no-cache
Server238cloudflare
Strict-Transport-Security238max-age=2592000; includeSubDomains
Vary238rsc, next-router-state-tree, next-router-prefetch, next-router-segment-prefetch, Accept-Encoding
X-Cache-Key1togetherai-52386018/229/dpl_Cy2pZ1YHL7un8yN36DStGn7XHFL2/intro#html=html
X-Cache-Key1togetherai-52386018/229/dpl_Cy2pZ1YHL7un8yN36DStGn7XHFL2/docs/json-mode#html=html
X-Cache-Key1togetherai-52386018/229/dpl_Cy2pZ1YHL7un8yN36DStGn7XHFL2/docs/function-calling#html=html
X-Cache-Key1togetherai-52386018/229/dpl_Cy2pZ1YHL7un8yN36DStGn7XHFL2/docs/vision-overview#html=html
X-Cache-Key1togetherai-52386018/229/dpl_Cy2pZ1YHL7un8yN36DStGn7XHFL2/docs/videos-overview#html=html
X-Cache-Key1togetherai-52386018/229/dpl_Cy2pZ1YHL7un8yN36DStGn7XHFL2/reference/chat-completions#html=html
X-Cache-Key1togetherai-52386018/229/dpl_Cy2pZ1YHL7un8yN36DStGn7XHFL2/docs/serverless-models#html=html
X-Cache-Key1togetherai-52386018/229/dpl_Cy2pZ1YHL7un8yN36DStGn7XHFL2/docs/reasoning-overview#html=html
X-Cache-Key1togetherai-52386018/229/dpl_Cy2pZ1YHL7un8yN36DStGn7XHFL2/docs/chat-overview#html=html
X-Cache-Key1togetherai-52386018/229/dpl_Cy2pZ1YHL7un8yN36DStGn7XHFL2/docs/quickstart#html=html
X-Cache-Key1togetherai-52386018/229/dpl_Cy2pZ1YHL7un8yN36DStGn7XHFL2/docs/batch-inference#html=html
X-Cache-Key1togetherai-52386018/229/dpl_Cy2pZ1YHL7un8yN36DStGn7XHFL2/docs/recommended-models#html=html
X-Cache-Key1togetherai-52386018/229/dpl_Cy2pZ1YHL7un8yN36DStGn7XHFL2/examples#html=html
X-Cache-Key1togetherai-52386018/229/dpl_Cy2pZ1YHL7un8yN36DStGn7XHFL2/docs/openai-api-compatibility#html=html
X-Cache-Key1togetherai-52386018/229/dpl_Cy2pZ1YHL7un8yN36DStGn7XHFL2/docs/guides#html=html
X-Cache-Key1togetherai-52386018/229/dpl_Cy2pZ1YHL7un8yN36DStGn7XHFL2/docs/mcp#html=html
X-Cache-Key1togetherai-52386018/229/dpl_Cy2pZ1YHL7un8yN36DStGn7XHFL2/docs/integrations#html=html
X-Cache-Key1togetherai-52386018/229/dpl_Cy2pZ1YHL7un8yN36DStGn7XHFL2/docs/rate-limits#html=html
X-Cache-Key1togetherai-52386018/229/dpl_Cy2pZ1YHL7un8yN36DStGn7XHFL2/#html=html
X-Cache-Key1togetherai-52386018/229/dpl_Cy2pZ1YHL7un8yN36DStGn7XHFL2/docs/changelog#html=html
X-Content-Type-Options238nosniff
X-Frame-Options238DENY
X-Llms-Txt238/llms.txt
X-Matched-Path238/_sites/[subdomain]/[[...slug]]
X-Mint-Proxy-Version2381.0.0-prod
X-Mintlify-Client-Version2380.0.2698
X-Nextjs-Prerender2381
X-Nextjs-Stale-Time23860
X-Served-Version238dpl_Cy2pZ1YHL7un8yN36DStGn7XHFL2
X-Vercel-Cache226MISS
X-Vercel-Cache12HIT
X-Vercel-Id1fra1:iad1::iad1::nctv8-1774360781219-407014f04dae
X-Vercel-Id1fra1:iad1::iad1::284l4-1774360780016-d0873a6962fc
X-Vercel-Id1fra1:iad1::iad1::mhj4h-1774360779848-556421759da0
X-Vercel-Id1fra1:iad1::iad1::qmhz8-1774360780513-c4965c5372d9
X-Vercel-Id1fra1:iad1::iad1::nctv8-1774360780944-061bf01ae39b
X-Vercel-Id1fra1:iad1::iad1::fm5lh-1774360780712-0b5149dec54f
X-Vercel-Id1fra1:iad1::iad1::b5z6r-1774360780674-386146074567
X-Vercel-Id1fra1:iad1::iad1::qmhz8-1774360781164-9f75c164bda9
X-Vercel-Id1fra1:iad1::iad1::q8fbs-1774360780225-f86acd22a0fc
X-Vercel-Id1fra1:iad1::iad1::f42x7-1774360780323-30ccff976b55
X-Vercel-Id1fra1:iad1::iad1::qpjgg-1774360780414-c1b07758ccf5
X-Vercel-Id1fra1:sin1:iad1::iad1::mf7m6-1774360779052-5ccc59b1dfd4
X-Vercel-Id1fra1:iad1::iad1::6g7zm-1774360779507-eb03ef3dc5bf
X-Vercel-Id1fra1:iad1::iad1::284l4-1774360779619-d58edcd742da
X-Vercel-Id1fra1:iad1::iad1::7wzt4-1774360780129-3c79f458afe5
X-Vercel-Id1fra1:iad1::iad1::f42x7-1774360781009-46dd1c852143
X-Vercel-Id1fra1:iad1::iad1::f42x7-1774360779864-a2e9790f18ae
X-Vercel-Id1fra1:iad1::iad1::rs4qd-1774360779918-d916e8bad9f6
X-Vercel-Id1fra1:iad1::iad1::d85th-1774360780812-fd865f82c0f2
X-Vercel-Id1fra1:iad1::iad1::9m6qc-1774360779367-c9e60eec00f8
X-Vercel-Project-Id238prj_3kakCEKDVpOxnQIJmKyTWs83RXEa
X-Version238dpl_Cy2pZ1YHL7un8yN36DStGn7XHFL2
No rows found, please edit your search term.

HTTP Caching by content type (only from crawlable domains)

Content typeCache typeURLs 🔽AVG lifetimeMIN lifetimeMAX lifetime
HTMLCache-Control2230 s 0 s 0 s
RedirectCache-Control150 s 0 s 0 s

HTTP Caching by domain

DomainCache typeURLs 🔽AVG lifetimeMIN lifetimeMAX lifetime
docs.together.aiCache-Control2380 s 0 s 0 s
www.together.aiLast-Modified1---
github.comCache-Control + ETag10 s 0 s 0 s

HTTP Caching by domain and content type

DomainContent typeCache typeURLs 🔽AVG lifetimeMIN lifetimeMAX lifetime
docs.together.aiHTMLCache-Control2230 s 0 s 0 s
docs.together.aiRedirectCache-Control150 s 0 s 0 s
github.comHTMLCache-Control + ETag10 s 0 s 0 s
www.together.aiHTMLLast-Modified1---

DNS info

DNS resolving tree
docs.together.ai
  IPv4: 172.64.150.175
  IPv4: 104.18.37.81
  IPv6: 2a06:98c1:3105::ac40:96af
  IPv6: 2606:4700:4401::6812:2551
DNS server: 127.0.0.53

SSL/TLS info

InfoText
IssuerC = US, O = Google Trust Services, CN = WE1
SubjectCN = together.ai
Valid fromMar  1 23:06:50 2026 GMT (VALID already 22.6 day(s))
Valid toMay 31 00:06:38 2026 GMT (VALID still for 67.4 day(s))
Supported protocolsTLSv1.2, TLSv1.3
RAW certificate outputCertificate:
    Data:
        Version: 3 (0x2)
        Serial Number:
            75:a0:b9:df:43:71:0a:18:0e:a6:b9:86:eb:21:61:43
        Signature Algorithm: ecdsa-with-SHA256
        Issuer: C = US, O = Google Trust Services, CN = WE1
        Validity
            Not Before: Mar  1 23:06:50 2026 GMT
            Not After : May 31 00:06:38 2026 GMT
        Subject: CN = together.ai
        Subject Public Key Info:
            Public Key Algorithm: id-ecPublicKey
                Public-Key: (256 bit)
                pub:
                    04:5c:f5:82:22:e2:37:09:64:2d:89:1e:86:6b:bc:
                    dc:8e:71:de:0a:27:81:4d:a9:4f:18:82:21:85:3d:
                    14:f1:b3:51:e2:e0:ef:65:36:15:fa:8e:eb:5f:86:
                    ae:a7:19:32:11:82:00:c4:5e:d9:84:e9:b1:45:3e:
                    5e:66:f3:13:c9
                ASN1 OID: prime256v1
                NIST CURVE: P-256
        X509v3 extensions:
            X509v3 Key Usage: critical
                Digital Signature
            X509v3 Extended Key Usage: 
                TLS Web Server Authentication
            X509v3 Basic Constraints: critical
                CA:FALSE
            X509v3 Subject Key Identifier: 
                FC:BA:7A:F1:C9:E4:4A:DF:1D:2B:E9:22:24:BA:CC:58:B2:E0:E8:90
            X509v3 Authority Key Identifier: 
                90:77:92:35:67:C4:FF:A8:CC:A9:E6:7B:D9:80:79:7B:CC:93:F9:38
            Authority Information Access: 
                OCSP - URI:http://o.pki.goog/s/we1/daA
                CA Issuers - URI:http://i.pki.goog/we1.crt
            X509v3 Subject Alternative Name: 
                DNS:together.ai, DNS:*.together.ai
            X509v3 Certificate Policies: 
                Policy: 2.23.140.1.2.1
            X509v3 CRL Distribution Points: 
                Full Name:
                  URI:http://c.pki.goog/we1/-A4QIxeBtHI.crl
            CT Precertificate SCTs: 
                Signed Certificate Timestamp:
                    Version   : v1 (0x0)
                    Log ID    : 64:11:C4:6C:A4:12:EC:A7:89:1C:A2:02:2E:00:BC:AB:
                                4F:28:07:D4:1E:35:27:AB:EA:FE:D5:03:C9:7D:CD:F0
                    Timestamp : Mar  2 00:06:51.459 2026 GMT
                    Extensions: none
                    Signature : ecdsa-with-SHA256
                                30:44:02:20:2D:CF:8A:88:17:78:9D:FF:05:52:56:88:
                                70:1F:79:FD:CE:19:DF:3E:28:D8:AE:F2:14:70:67:3C:
                                51:46:F4:89:02:20:16:81:E9:C2:B2:AC:0B:A6:A9:25:
                                86:AC:94:F6:E7:C1:2B:D8:19:E3:46:DE:52:4C:F0:FF:
                                49:14:79:52:1D:7A
                Signed Certificate Timestamp:
                    Version   : v1 (0x0)
                    Log ID    : 0E:57:94:BC:F3:AE:A9:3E:33:1B:2C:99:07:B3:F7:90:
                                DF:9B:C2:3D:71:32:25:DD:21:A9:25:AC:61:C5:4E:21
                    Timestamp : Mar  2 00:06:51.430 2026 GMT
                    Extensions: none
                    Signature : ecdsa-with-SHA256
                                30:45:02:20:2E:3E:EE:4F:38:F1:7F:60:73:E7:16:F5:
                                89:C1:88:F3:59:9D:12:A5:14:61:16:9E:BB:32:EB:77:
                                46:0F:0A:69:02:21:00:BB:1C:E5:D9:87:32:E6:48:CB:
                                C7:FB:80:71:88:21:A2:61:C9:43:9F:1C:D2:06:C7:F4:
                                00:85:E1:75:75:DA:80
    Signature Algorithm: ecdsa-with-SHA256
    Signature Value:
        30:45:02:20:78:c7:e3:9b:53:f6:95:ab:3e:56:8e:bf:2b:83:
        0f:3d:32:ba:ed:06:05:8a:3b:83:88:24:b1:06:9b:ca:aa:ae:
        02:21:00:8f:bf:5d:4d:ff:56:8b:0e:6d:1e:3f:5b:52:41:ae:
        47:87:72:43:83:01:58:40:fa:74:86:2c:ac:f0:1c:0b:fe
RAW protocols output
=== ssl2 ===
s_client: Unknown option: -ssl2
s_client: Use -help for summary.

=== ssl3 ===
s_client: Unknown option: -ssl3
s_client: Use -help for summary.

=== tls1 ===
40F7CB6D88720000:error:0A0000BF:SSL routines:tls_setup_handshake:no protocols available:../ssl/statem/statem_lib.c:104:
CONNECTED(00000003)
---
no peer certificate available
---
No client certificate CA names sent
---
SSL handshake has read 0 bytes and written 7 bytes
Verification: OK
---
New, (NONE), Cipher is (NONE)
Secure Renegotiation IS NOT supported
Compression: NONE
Expansion: NONE
No ALPN negotiated
Early data was not sent
Verify return code: 0 (ok)
---

=== tls1_1 ===
40E72E713A7A0000:error:0A0000BF:SSL routines:tls_setup_handshake:no protocols available:../ssl/statem/statem_lib.c:104:
CONNECTED(00000003)
---
no peer certificate available
---
No client certificate CA names sent
---
SSL handshake has read 0 bytes and written 7 bytes
Verification: OK
---
New, (NONE), Cipher is (NONE)
Secure Renegotiation IS NOT supported
Compression: NONE
Expansion: NONE
No ALPN negotiated
Early data was not sent
Verify return code: 0 (ok)
---

=== tls1_2 ===
depth=2 C = US, O = Google Trust Services LLC, CN = GTS Root R4
verify return:1
depth=1 C = US, O = Google Trust Services, CN = WE1
verify return:1
depth=0 CN = together.ai
verify return:1
CONNECTED(00000003)
---
Certificate chain
 0 s:CN = together.ai
   i:C = US, O = Google Trust Services, CN = WE1
   a:PKEY: id-ecPublicKey, 256 (bit); sigalg: ecdsa-with-SHA256
   v:NotBefore: Mar  1 23:06:50 2026 GMT; NotAfter: May 31 00:06:38 2026 GMT
 1 s:C = US, O = Google Trust Services, CN = WE1
   i:C = US, O = Google Trust Services LLC, CN = GTS Root R4
   a:PKEY: id-ecPublicKey, 256 (bit); sigalg: ecdsa-with-SHA384
   v:NotBefore: Dec 13 09:00:00 2023 GMT; NotAfter: Feb 20 14:00:00 2029 GMT
 2 s:C = US, O = Google Trust Services LLC, CN = GTS Root R4
   i:C = BE, O = GlobalSign nv-sa, OU = Root CA, CN = GlobalSign Root CA
   a:PKEY: id-ecPublicKey, 384 (bit); sigalg: RSA-SHA256
   v:NotBefore: Nov 15 03:43:21 2023 GMT; NotAfter: Jan 28 00:00:42 2028 GMT
---
Server certificate
-----BEGIN CERTIFICATE-----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-----END CERTIFICATE-----
subject=CN = together.ai
issuer=C = US, O = Google Trust Services, CN = WE1
---
No client certificate CA names sent
Peer signing digest: SHA256
Peer signature type: ECDSA
Server Temp Key: X25519, 253 bits
---
SSL handshake has read 2975 bytes and written 298 bytes
Verification: OK
---
New, TLSv1.2, Cipher is ECDHE-ECDSA-CHACHA20-POLY1305
Server public key is 256 bit
Secure Renegotiation IS supported
Compression: NONE
Expansion: NONE
No ALPN negotiated
SSL-Session:
    Protocol  : TLSv1.2
    Cipher    : ECDHE-ECDSA-CHACHA20-POLY1305
    Session-ID: B962F672FF6E8DFBF4ED9363A8F8097C61F2CA820C95C9C114C8B277E3648735
    Session-ID-ctx: 
    Master-Key: D0A8723F3D1C25F5F903A8471CF670344CCF5A0127CBE49B672C9438F667C55DAC9CE088BA7E4257E8E832185441A8C9
    PSK identity: None
    PSK identity hint: None
    SRP username: None
    TLS session ticket lifetime hint: 64799 (seconds)
    TLS session ticket:
    0000 - 58 ba fa fe 9f 59 67 54-85 a3 80 be 80 cd cb b7   X....YgT........
    0010 - 94 6c fb 98 75 e7 87 b9-44 b9 61 34 33 38 64 bb   .l..u...D.a438d.
    0020 - 3e 8d af 1f 89 39 8e 6b-7b 4b f6 7c 98 56 39 6f   >....9.k{K.|.V9o
    0030 - 70 42 e5 12 ae 3b ab bc-d2 b4 a0 97 d2 67 b8 13   pB...;.......g..
    0040 - 9a b5 bd 3d 77 51 3b 9f-27 ca d5 07 40 6d 6c 4c   ...=wQ;.'...@mlL
    0050 - 30 e0 82 39 d5 04 29 2f-67 ce a8 c0 bb 83 28 f3   0..9..)/g.....(.
    0060 - 34 00 5f d5 4b 3c d1 ca-87 d0 99 64 ca 35 68 a8   4._.K<.....d.5h.
    0070 - e0 7a 6a bf bb 27 77 78-df 8b e1 05 ef ef bc 3a   .zj..'wx.......:
    0080 - 15 f6 ee f6 4f 49 49 9a-aa 11 4e 97 9f 3e 07 67   ....OII...N..>.g
    0090 - 81 42 81 2a a6 31 0c 7e-e3 4b f0 2b e7 41 70 d0   .B.*.1.~.K.+.Ap.
    00a0 - 0e a4 64 f9 22 48 68 1f-db ab 39 7f 69 6c 2e c9   ..d."Hh...9.il..
    00b0 - 0e cd d8 68 9c 58 86 e9-0d a5 2f 39 59 e4 8e ea   ...h.X..../9Y...

    Start Time: 1774360804
    Timeout   : 7200 (sec)
    Verify return code: 0 (ok)
    Extended master secret: yes
---
DONE

=== tls1_3 ===
depth=2 C = US, O = Google Trust Services LLC, CN = GTS Root R4
verify return:1
depth=1 C = US, O = Google Trust Services, CN = WE1
verify return:1
depth=0 CN = together.ai
verify return:1
CONNECTED(00000003)
---
Certificate chain
 0 s:CN = together.ai
   i:C = US, O = Google Trust Services, CN = WE1
   a:PKEY: id-ecPublicKey, 256 (bit); sigalg: ecdsa-with-SHA256
   v:NotBefore: Mar  1 23:06:50 2026 GMT; NotAfter: May 31 00:06:38 2026 GMT
 1 s:C = US, O = Google Trust Services, CN = WE1
   i:C = US, O = Google Trust Services LLC, CN = GTS Root R4
   a:PKEY: id-ecPublicKey, 256 (bit); sigalg: ecdsa-with-SHA384
   v:NotBefore: Dec 13 09:00:00 2023 GMT; NotAfter: Feb 20 14:00:00 2029 GMT
 2 s:C = US, O = Google Trust Services LLC, CN = GTS Root R4
   i:C = BE, O = GlobalSign nv-sa, OU = Root CA, CN = GlobalSign Root CA
   a:PKEY: id-ecPublicKey, 384 (bit); sigalg: RSA-SHA256
   v:NotBefore: Nov 15 03:43:21 2023 GMT; NotAfter: Jan 28 00:00:42 2028 GMT
---
Server certificate
-----BEGIN CERTIFICATE-----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-----END CERTIFICATE-----
subject=CN = together.ai
issuer=C = US, O = Google Trust Services, CN = WE1
---
No client certificate CA names sent
Peer signing digest: SHA256
Peer signature type: ECDSA
Server Temp Key: X25519, 253 bits
---
SSL handshake has read 2824 bytes and written 330 bytes
Verification: OK
---
New, TLSv1.3, Cipher is TLS_AES_256_GCM_SHA384
Server public key is 256 bit
Secure Renegotiation IS NOT supported
Compression: NONE
Expansion: NONE
No ALPN negotiated
Early data was not sent
Verify return code: 0 (ok)
---
DONE

Crawler stats

Basic stats
Total execution time27 s
Total URLs240
Total size126 MB
Requests - total time51 s
Requests - avg time215 ms
Requests - min time94 ms
Requests - max time4.5 s
Requests by status200: 225
307: 2
308: 13

Analysis stats

Found 21 row(s).
Class::methodExec time 🔽Exec count
BestPracticeAnalyzer::checkHeadingStructure1.3 s 225
BestPracticeAnalyzer::checkNonClickablePhoneNumbers1.1 s 225
AccessibilityAnalyzer::checkMissingLabels1.1 s 223
AccessibilityAnalyzer::checkMissingAriaLabels1.1 s 223
AccessibilityAnalyzer::checkMissingRoles888 ms 223
AccessibilityAnalyzer::checkMissingLang743 ms 223
BestPracticeAnalyzer::checkMaxDOMDepth673 ms 225
SslTlsAnalyzer::getTLSandSSLCertificateInfo606 ms 1
BestPracticeAnalyzer::checkInlineSvg219 ms 225
BestPracticeAnalyzer::checkMissingQuotesOnAttributes87 ms 225
SeoAndOpenGraphAnalyzer::analyzeHeadings31 ms 1
AccessibilityAnalyzer::checkImageAltAttributes30 ms 223
SecurityAnalyzer::checkHtmlSecurity23 ms 223
SecurityAnalyzer::checkHeaders5 ms 223
SeoAndOpenGraphAnalyzer::analyzeOpenGraph0 ms 1
SeoAndOpenGraphAnalyzer::analyzeSeo0 ms 1
BestPracticeAnalyzer::checkTitleUniqueness0 ms 1
BestPracticeAnalyzer::checkMetaDescriptionUniqueness0 ms 1
BestPracticeAnalyzer::checkBrotliSupport0 ms 1
BestPracticeAnalyzer::checkWebpSupport0 ms 1
BestPracticeAnalyzer::checkAvifSupport0 ms 1
No rows found, please edit your search term.

Content processor stats

Found 12 row(s).
Class::methodExec time 🔽Exec count
NextJsProcessor::applyContentChangesBeforeUrlParsing1.3 s 225
HtmlProcessor::findUrls605 ms 238
JavaScriptProcessor::findUrls600 ms 223
CssProcessor::findUrls28 ms 223
AstroProcessor::findUrls14 ms 223
AstroProcessor::applyContentChangesBeforeUrlParsing0 ms 225
NextJsProcessor::findUrls0 ms 223
JavaScriptProcessor::applyContentChangesBeforeUrlParsing0 ms 225
SvelteProcessor::applyContentChangesBeforeUrlParsing0 ms 225
HtmlProcessor::applyContentChangesBeforeUrlParsing0 ms 240
SvelteProcessor::findUrls0 ms 223
CssProcessor::applyContentChangesBeforeUrlParsing0 ms 225
No rows found, please edit your search term.

Crawler info

Version 2.1.0.20260317
Executed At 2026-03-24 13:59:37
Command siteone-crawler --url=https://docs.together.ai --markdown-export-dir=/tmp/siteone-together_ai --markdown-exclude-selector=header,footer,nav,.sidebar,.menu,.breadcrumb,script,style --timeout=30 --workers=5 --disable-javascript --disable-styles --disable-fonts --disable-images --disable-files --no-color --hide-progress-bar --output=text
Hostname ubuntu-8gb-hel1-1
User-Agent Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/26.0.0.0 Safari/537.36 siteone-crawler/2.1.0.20260317