[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-together-ai-together-batch-inference":3,"mdc-mfl6m9-key":34,"related-org-together-ai-together-batch-inference":525,"related-repo-together-ai-together-batch-inference":699},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":12,"stars":23,"repoUrl":24,"updatedAt":25,"license":26,"forks":27,"topics":28,"repo":29,"sourceUrl":32,"mdContent":33},"together-batch-inference","run asynchronous batch inference jobs","High-volume, asynchronous offline inference at up to 50% lower cost via Together AI's Batch API. Prepare JSONL inputs, upload files, create jobs, poll status, and download outputs. Reach for it whenever the user needs non-interactive bulk inference rather than real-time chat or evaluation jobs.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},"together-ai","Together AI","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Ftogether-ai.jpg","togethercomputer",[13,17,20],{"name":14,"slug":15,"type":16},"Performance","performance","tag",{"name":18,"slug":19,"type":16},"LLM","llm",{"name":21,"slug":22,"type":16},"Automation","automation",31,"https:\u002F\u002Fgithub.com\u002Ftogethercomputer\u002Fskills","2026-07-17T06:08:23.919602",null,4,[],{"repoUrl":24,"stars":23,"forks":27,"topics":30,"description":31},[],"Skills to help your coding agents use Together AI products.","https:\u002F\u002Fgithub.com\u002Ftogethercomputer\u002Fskills\u002Ftree\u002FHEAD\u002Fskills\u002Ftogether-batch-inference","---\nname: together-batch-inference\ndescription: \"High-volume, asynchronous offline inference at up to 50% lower cost via Together AI's Batch API. Prepare JSONL inputs, upload files, create jobs, poll status, and download outputs. Reach for it whenever the user needs non-interactive bulk inference rather than real-time chat or evaluation jobs.\"\n---\n\n# Together Batch Inference\n\n## Overview\n\nUse Together AI's Batch API for large offline workloads where latency is not the primary concern.\n\nTypical fits:\n\n- bulk classification\n- synthetic data generation\n- dataset transformations\n- large summarization or enrichment jobs\n- low-cost asynchronous inference\n\n## When This Skill Wins\n\n- The user has many independent requests to run\n- A JSONL request file is acceptable\n- Turnaround time can be minutes or hours instead of seconds\n- Lower cost matters more than immediate interactivity\n\n## Hand Off To Another Skill\n\n- Use `together-chat-completions` for real-time requests or tool-calling apps\n- Use `together-evaluations` for managed LLM-as-a-judge workflows\n- Use `together-embeddings` for retrieval-specific vector generation\n\n## Quick Routing\n\n- **End-to-end batch workflow**\n  - Start with [scripts\u002Fbatch_workflow.py](scripts\u002Fbatch_workflow.py) or [scripts\u002Fbatch_workflow.ts](scripts\u002Fbatch_workflow.ts)\n- **Request format, status model, and result downloads**\n  - Read [references\u002Fapi-reference.md](references\u002Fapi-reference.md)\n- **Operational guidance and batch sizing**\n  - Read [references\u002Fapi-reference.md](references\u002Fapi-reference.md)\n\n## Workflow\n\n1. Build a JSONL file where each line contains `custom_id` and `body`.\n2. Upload the file with `purpose=\"batch-api\"`.\n3. Create the batch with `input_file_id=...` and the target endpoint.\n4. Poll until the job is terminal.\n5. Download output and error files, then reconcile by `custom_id`.\n\n## High-Signal Rules\n\n- Python scripts require the Together v2 SDK (`together>=2.0.0`). If the user is on an older version, they must upgrade first: `uv pip install --upgrade \"together>=2.0.0\"`.\n- Use `input_file_id`, not legacy file parameters.\n- Keep `custom_id` stable and meaningful so result reconciliation is easy.\n- Batch is for independent requests. If the workload depends on shared conversation state, it is probably the wrong tool.\n- Always inspect the error file in addition to the success output.\n- `client.batches.create()` returns a wrapper; access the batch object via `response.job` (e.g., `response.job.id`). `client.batches.retrieve()` returns the batch object directly.\n- For classification or labeling workloads, set `max_tokens` low (e.g., 4), use `temperature: 0`, and constrain the system prompt to return only the label. This minimizes output tokens and cost.\n- Small batches (under 1K requests) typically complete in minutes. The 24-hour completion window is a maximum, not typical.\n\n## Resource Map\n\n- **API reference and operational guidance**: [references\u002Fapi-reference.md](references\u002Fapi-reference.md)\n- **Python workflow**: [scripts\u002Fbatch_workflow.py](scripts\u002Fbatch_workflow.py)\n- **TypeScript workflow**: [scripts\u002Fbatch_workflow.ts](scripts\u002Fbatch_workflow.ts)\n\n## Official Docs\n\n- [Batch Inference](https:\u002F\u002Fdocs.together.ai\u002Fdocs\u002Fbatch-inference)\n- [Batch API](https:\u002F\u002Fdocs.together.ai\u002Freference\u002Fbatch-create)\n",{"data":35,"body":36},{"name":4,"description":6},{"type":37,"children":38},"root",[39,47,54,60,65,95,101,124,130,171,177,250,256,322,328,446,452,495,501],{"type":40,"tag":41,"props":42,"children":43},"element","h1",{"id":4},[44],{"type":45,"value":46},"text","Together Batch Inference",{"type":40,"tag":48,"props":49,"children":51},"h2",{"id":50},"overview",[52],{"type":45,"value":53},"Overview",{"type":40,"tag":55,"props":56,"children":57},"p",{},[58],{"type":45,"value":59},"Use Together AI's Batch API for large offline workloads where latency is not the primary concern.",{"type":40,"tag":55,"props":61,"children":62},{},[63],{"type":45,"value":64},"Typical fits:",{"type":40,"tag":66,"props":67,"children":68},"ul",{},[69,75,80,85,90],{"type":40,"tag":70,"props":71,"children":72},"li",{},[73],{"type":45,"value":74},"bulk classification",{"type":40,"tag":70,"props":76,"children":77},{},[78],{"type":45,"value":79},"synthetic data generation",{"type":40,"tag":70,"props":81,"children":82},{},[83],{"type":45,"value":84},"dataset transformations",{"type":40,"tag":70,"props":86,"children":87},{},[88],{"type":45,"value":89},"large summarization or enrichment jobs",{"type":40,"tag":70,"props":91,"children":92},{},[93],{"type":45,"value":94},"low-cost asynchronous inference",{"type":40,"tag":48,"props":96,"children":98},{"id":97},"when-this-skill-wins",[99],{"type":45,"value":100},"When This Skill Wins",{"type":40,"tag":66,"props":102,"children":103},{},[104,109,114,119],{"type":40,"tag":70,"props":105,"children":106},{},[107],{"type":45,"value":108},"The user has many independent requests to run",{"type":40,"tag":70,"props":110,"children":111},{},[112],{"type":45,"value":113},"A JSONL request file is acceptable",{"type":40,"tag":70,"props":115,"children":116},{},[117],{"type":45,"value":118},"Turnaround time can be minutes or hours instead of seconds",{"type":40,"tag":70,"props":120,"children":121},{},[122],{"type":45,"value":123},"Lower cost matters more than immediate interactivity",{"type":40,"tag":48,"props":125,"children":127},{"id":126},"hand-off-to-another-skill",[128],{"type":45,"value":129},"Hand Off To Another Skill",{"type":40,"tag":66,"props":131,"children":132},{},[133,147,159],{"type":40,"tag":70,"props":134,"children":135},{},[136,138,145],{"type":45,"value":137},"Use ",{"type":40,"tag":139,"props":140,"children":142},"code",{"className":141},[],[143],{"type":45,"value":144},"together-chat-completions",{"type":45,"value":146}," for real-time requests or tool-calling apps",{"type":40,"tag":70,"props":148,"children":149},{},[150,151,157],{"type":45,"value":137},{"type":40,"tag":139,"props":152,"children":154},{"className":153},[],[155],{"type":45,"value":156},"together-evaluations",{"type":45,"value":158}," for managed LLM-as-a-judge workflows",{"type":40,"tag":70,"props":160,"children":161},{},[162,163,169],{"type":45,"value":137},{"type":40,"tag":139,"props":164,"children":166},{"className":165},[],[167],{"type":45,"value":168},"together-embeddings",{"type":45,"value":170}," for retrieval-specific vector generation",{"type":40,"tag":48,"props":172,"children":174},{"id":173},"quick-routing",[175],{"type":45,"value":176},"Quick Routing",{"type":40,"tag":66,"props":178,"children":179},{},[180,210,231],{"type":40,"tag":70,"props":181,"children":182},{},[183,189],{"type":40,"tag":184,"props":185,"children":186},"strong",{},[187],{"type":45,"value":188},"End-to-end batch workflow",{"type":40,"tag":66,"props":190,"children":191},{},[192],{"type":40,"tag":70,"props":193,"children":194},{},[195,197,203,205],{"type":45,"value":196},"Start with ",{"type":40,"tag":198,"props":199,"children":201},"a",{"href":200},"scripts\u002Fbatch_workflow.py",[202],{"type":45,"value":200},{"type":45,"value":204}," or ",{"type":40,"tag":198,"props":206,"children":208},{"href":207},"scripts\u002Fbatch_workflow.ts",[209],{"type":45,"value":207},{"type":40,"tag":70,"props":211,"children":212},{},[213,218],{"type":40,"tag":184,"props":214,"children":215},{},[216],{"type":45,"value":217},"Request format, status model, and result downloads",{"type":40,"tag":66,"props":219,"children":220},{},[221],{"type":40,"tag":70,"props":222,"children":223},{},[224,226],{"type":45,"value":225},"Read ",{"type":40,"tag":198,"props":227,"children":229},{"href":228},"references\u002Fapi-reference.md",[230],{"type":45,"value":228},{"type":40,"tag":70,"props":232,"children":233},{},[234,239],{"type":40,"tag":184,"props":235,"children":236},{},[237],{"type":45,"value":238},"Operational guidance and batch sizing",{"type":40,"tag":66,"props":240,"children":241},{},[242],{"type":40,"tag":70,"props":243,"children":244},{},[245,246],{"type":45,"value":225},{"type":40,"tag":198,"props":247,"children":248},{"href":228},[249],{"type":45,"value":228},{"type":40,"tag":48,"props":251,"children":253},{"id":252},"workflow",[254],{"type":45,"value":255},"Workflow",{"type":40,"tag":257,"props":258,"children":259},"ol",{},[260,281,293,306,311],{"type":40,"tag":70,"props":261,"children":262},{},[263,265,271,273,279],{"type":45,"value":264},"Build a JSONL file where each line contains ",{"type":40,"tag":139,"props":266,"children":268},{"className":267},[],[269],{"type":45,"value":270},"custom_id",{"type":45,"value":272}," and ",{"type":40,"tag":139,"props":274,"children":276},{"className":275},[],[277],{"type":45,"value":278},"body",{"type":45,"value":280},".",{"type":40,"tag":70,"props":282,"children":283},{},[284,286,292],{"type":45,"value":285},"Upload the file with ",{"type":40,"tag":139,"props":287,"children":289},{"className":288},[],[290],{"type":45,"value":291},"purpose=\"batch-api\"",{"type":45,"value":280},{"type":40,"tag":70,"props":294,"children":295},{},[296,298,304],{"type":45,"value":297},"Create the batch with ",{"type":40,"tag":139,"props":299,"children":301},{"className":300},[],[302],{"type":45,"value":303},"input_file_id=...",{"type":45,"value":305}," and the target endpoint.",{"type":40,"tag":70,"props":307,"children":308},{},[309],{"type":45,"value":310},"Poll until the job is terminal.",{"type":40,"tag":70,"props":312,"children":313},{},[314,316,321],{"type":45,"value":315},"Download output and error files, then reconcile by ",{"type":40,"tag":139,"props":317,"children":319},{"className":318},[],[320],{"type":45,"value":270},{"type":45,"value":280},{"type":40,"tag":48,"props":323,"children":325},{"id":324},"high-signal-rules",[326],{"type":45,"value":327},"High-Signal Rules",{"type":40,"tag":66,"props":329,"children":330},{},[331,351,363,375,380,385,420,441],{"type":40,"tag":70,"props":332,"children":333},{},[334,336,342,344,350],{"type":45,"value":335},"Python scripts require the Together v2 SDK (",{"type":40,"tag":139,"props":337,"children":339},{"className":338},[],[340],{"type":45,"value":341},"together>=2.0.0",{"type":45,"value":343},"). If the user is on an older version, they must upgrade first: ",{"type":40,"tag":139,"props":345,"children":347},{"className":346},[],[348],{"type":45,"value":349},"uv pip install --upgrade \"together>=2.0.0\"",{"type":45,"value":280},{"type":40,"tag":70,"props":352,"children":353},{},[354,355,361],{"type":45,"value":137},{"type":40,"tag":139,"props":356,"children":358},{"className":357},[],[359],{"type":45,"value":360},"input_file_id",{"type":45,"value":362},", not legacy file parameters.",{"type":40,"tag":70,"props":364,"children":365},{},[366,368,373],{"type":45,"value":367},"Keep ",{"type":40,"tag":139,"props":369,"children":371},{"className":370},[],[372],{"type":45,"value":270},{"type":45,"value":374}," stable and meaningful so result reconciliation is easy.",{"type":40,"tag":70,"props":376,"children":377},{},[378],{"type":45,"value":379},"Batch is for independent requests. If the workload depends on shared conversation state, it is probably the wrong tool.",{"type":40,"tag":70,"props":381,"children":382},{},[383],{"type":45,"value":384},"Always inspect the error file in addition to the success output.",{"type":40,"tag":70,"props":386,"children":387},{},[388,394,396,402,404,410,412,418],{"type":40,"tag":139,"props":389,"children":391},{"className":390},[],[392],{"type":45,"value":393},"client.batches.create()",{"type":45,"value":395}," returns a wrapper; access the batch object via ",{"type":40,"tag":139,"props":397,"children":399},{"className":398},[],[400],{"type":45,"value":401},"response.job",{"type":45,"value":403}," (e.g., ",{"type":40,"tag":139,"props":405,"children":407},{"className":406},[],[408],{"type":45,"value":409},"response.job.id",{"type":45,"value":411},"). ",{"type":40,"tag":139,"props":413,"children":415},{"className":414},[],[416],{"type":45,"value":417},"client.batches.retrieve()",{"type":45,"value":419}," returns the batch object directly.",{"type":40,"tag":70,"props":421,"children":422},{},[423,425,431,433,439],{"type":45,"value":424},"For classification or labeling workloads, set ",{"type":40,"tag":139,"props":426,"children":428},{"className":427},[],[429],{"type":45,"value":430},"max_tokens",{"type":45,"value":432}," low (e.g., 4), use ",{"type":40,"tag":139,"props":434,"children":436},{"className":435},[],[437],{"type":45,"value":438},"temperature: 0",{"type":45,"value":440},", and constrain the system prompt to return only the label. This minimizes output tokens and cost.",{"type":40,"tag":70,"props":442,"children":443},{},[444],{"type":45,"value":445},"Small batches (under 1K requests) typically complete in minutes. The 24-hour completion window is a maximum, not typical.",{"type":40,"tag":48,"props":447,"children":449},{"id":448},"resource-map",[450],{"type":45,"value":451},"Resource Map",{"type":40,"tag":66,"props":453,"children":454},{},[455,469,482],{"type":40,"tag":70,"props":456,"children":457},{},[458,463,465],{"type":40,"tag":184,"props":459,"children":460},{},[461],{"type":45,"value":462},"API reference and operational guidance",{"type":45,"value":464},": ",{"type":40,"tag":198,"props":466,"children":467},{"href":228},[468],{"type":45,"value":228},{"type":40,"tag":70,"props":470,"children":471},{},[472,477,478],{"type":40,"tag":184,"props":473,"children":474},{},[475],{"type":45,"value":476},"Python workflow",{"type":45,"value":464},{"type":40,"tag":198,"props":479,"children":480},{"href":200},[481],{"type":45,"value":200},{"type":40,"tag":70,"props":483,"children":484},{},[485,490,491],{"type":40,"tag":184,"props":486,"children":487},{},[488],{"type":45,"value":489},"TypeScript workflow",{"type":45,"value":464},{"type":40,"tag":198,"props":492,"children":493},{"href":207},[494],{"type":45,"value":207},{"type":40,"tag":48,"props":496,"children":498},{"id":497},"official-docs",[499],{"type":45,"value":500},"Official Docs",{"type":40,"tag":66,"props":502,"children":503},{},[504,515],{"type":40,"tag":70,"props":505,"children":506},{},[507],{"type":40,"tag":198,"props":508,"children":512},{"href":509,"rel":510},"https:\u002F\u002Fdocs.together.ai\u002Fdocs\u002Fbatch-inference",[511],"nofollow",[513],{"type":45,"value":514},"Batch Inference",{"type":40,"tag":70,"props":516,"children":517},{},[518],{"type":40,"tag":198,"props":519,"children":522},{"href":520,"rel":521},"https:\u002F\u002Fdocs.together.ai\u002Freference\u002Fbatch-create",[511],[523],{"type":45,"value":524},"Batch API",{"items":526,"total":698},[527,548,560,579,585,598,617,627,641,654,664,679],{"slug":528,"name":528,"fn":529,"description":530,"org":531,"tags":532,"stars":545,"repoUrl":546,"updatedAt":547},"blog-post","write structured blog posts","Write structured long-form blog posts with a consistent structure and SEO optimization.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[533,536,539,542],{"name":534,"slug":535,"type":16},"Content Creation","content-creation",{"name":537,"slug":538,"type":16},"Marketing","marketing",{"name":540,"slug":541,"type":16},"SEO","seo",{"name":543,"slug":544,"type":16},"Writing","writing",1151,"https:\u002F\u002Fgithub.com\u002Ftogethercomputer\u002Ftogether-cookbook","2026-07-17T06:07:39.475433",{"slug":549,"name":549,"fn":550,"description":551,"org":552,"tags":553,"stars":545,"repoUrl":546,"updatedAt":559},"social-media","create social media content","Create social media content including Twitter\u002FX threads, LinkedIn posts, and short-form updates.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[554,555,556,558],{"name":534,"slug":535,"type":16},{"name":537,"slug":538,"type":16},{"name":557,"slug":549,"type":16},"Social Media",{"name":543,"slug":544,"type":16},"2026-07-17T06:07:38.455058",{"slug":561,"name":561,"fn":562,"description":563,"org":564,"tags":565,"stars":23,"repoUrl":24,"updatedAt":578},"together-audio","process audio with Together AI","Text-to-speech and speech-to-text via Together AI, including REST, streaming, and realtime WebSocket TTS, plus transcription, translation, diarization, timestamps, and live STT. Reach for it whenever the user needs audio in or audio out on Together AI rather than chat generation, image or video creation, or model training.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[566,569,572,575],{"name":567,"slug":568,"type":16},"Audio","audio",{"name":570,"slug":571,"type":16},"Speech","speech",{"name":573,"slug":574,"type":16},"Text-to-Speech","text-to-speech",{"name":576,"slug":577,"type":16},"Transcription","transcription","2026-07-26T05:49:08.246858",{"slug":4,"name":4,"fn":5,"description":6,"org":580,"tags":581,"stars":23,"repoUrl":24,"updatedAt":25},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[582,583,584],{"name":21,"slug":22,"type":16},{"name":18,"slug":19,"type":16},{"name":14,"slug":15,"type":16},{"slug":144,"name":144,"fn":586,"description":587,"org":588,"tags":589,"stars":23,"repoUrl":24,"updatedAt":597},"generate text with Together AI","Real-time and streaming text generation via Together AI's OpenAI-compatible chat\u002Fcompletions API, including multi-turn conversations, tool and function calling, structured JSON outputs, and reasoning models. Reach for it whenever the user wants to build or debug text generation on Together AI, unless they specifically need batch jobs, embeddings, fine-tuning, dedicated endpoints, dedicated containers, or GPU clusters.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[590,593,596],{"name":591,"slug":592,"type":16},"AI","ai",{"name":594,"slug":595,"type":16},"API Development","api-development",{"name":18,"slug":19,"type":16},"2026-07-26T05:49:11.244104",{"slug":599,"name":599,"fn":600,"description":601,"org":602,"tags":603,"stars":23,"repoUrl":24,"updatedAt":616},"together-dedicated-containers","deploy custom inference containers on Together AI","Custom Dockerized inference workers on Together AI's managed GPU infrastructure. Build with Sprocket SDK, configure with Jig CLI, submit async queue jobs, and poll results. Reach for it whenever the user needs container-level control rather than a standard model endpoint or raw cluster.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[604,607,610,613],{"name":605,"slug":606,"type":16},"AI Infrastructure","ai-infrastructure",{"name":608,"slug":609,"type":16},"Deployment","deployment",{"name":611,"slug":612,"type":16},"Docker","docker",{"name":614,"slug":615,"type":16},"Machine Learning","machine-learning","2026-07-26T05:49:09.267892",{"slug":618,"name":618,"fn":619,"description":620,"org":621,"tags":622,"stars":23,"repoUrl":24,"updatedAt":626},"together-dedicated-model-inference","deploy and operate Together AI models","Deploy and operate models on dedicated GPUs with Together AI's Dedicated Model Inference (DMI, the v2 dedicated endpoints API): beta endpoints, deployments, deployment profiles and hardware configs, autoscaling, traffic splitting, A\u002FB tests, shadow experiments, Prometheus metrics, and custom model or LoRA adapter uploads. Reach for it whenever the user mentions together beta endpoints or tg beta commands, client.beta.endpoints, DMI resources like ep_\u002Fdep_\u002Fcr_\u002Fml_ IDs, or wants production model serving with traffic management on Together AI. This is the current dedicated-hosting API and also covers migrating off the retired legacy v1 endpoints API (non-beta client.endpoints \u002F together endpoints), whose create and restart now return HTTP 403.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[623,624,625],{"name":605,"slug":606,"type":16},{"name":608,"slug":609,"type":16},{"name":18,"slug":19,"type":16},"2026-07-26T06:08:44.044039",{"slug":168,"name":168,"fn":628,"description":629,"org":630,"tags":631,"stars":23,"repoUrl":24,"updatedAt":640},"generate embeddings and build RAG pipelines","Dense vector embeddings, semantic search, RAG pipelines, and reranking via Together AI. Generate embeddings with open-source models and rerank results behind dedicated endpoints. Reach for it whenever the user needs vector representations or retrieval quality improvements rather than direct text generation.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[632,633,634,637],{"name":591,"slug":592,"type":16},{"name":18,"slug":19,"type":16},{"name":635,"slug":636,"type":16},"RAG","rag",{"name":638,"slug":639,"type":16},"Search","search","2026-07-26T05:49:06.247906",{"slug":156,"name":156,"fn":642,"description":643,"org":644,"tags":645,"stars":23,"repoUrl":24,"updatedAt":653},"evaluate LLM outputs with Together AI","LLM-as-a-judge evaluation framework on Together AI. Classify, score, and compare model outputs, select judge models, use external-provider judges or targets, poll results and download reports. Reach for it whenever the user wants to benchmark outputs, grade responses, compare A\u002FB variants, or operationalize automated evaluations.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[646,649,652],{"name":647,"slug":648,"type":16},"Benchmarking","benchmarking",{"name":650,"slug":651,"type":16},"Evals","evals",{"name":18,"slug":19,"type":16},"2026-07-26T05:49:07.241553",{"slug":655,"name":655,"fn":656,"description":657,"org":658,"tags":659,"stars":23,"repoUrl":24,"updatedAt":663},"together-fine-tuning","fine-tune and adapt models on Together AI","LoRA, full fine-tuning, DPO preference tuning, VLM training, function-calling tuning, reasoning tuning, and BYOM uploads on Together AI. Reach for it whenever the user wants to adapt a model on custom data rather than only run inference, evaluate outputs, or host an existing model.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[660,661,662],{"name":591,"slug":592,"type":16},{"name":18,"slug":19,"type":16},{"name":614,"slug":615,"type":16},"2026-07-26T05:49:10.243114",{"slug":665,"name":665,"fn":666,"description":667,"org":668,"tags":669,"stars":23,"repoUrl":24,"updatedAt":678},"together-gpu-clusters","orchestrate GPU clusters on Together AI","On-demand and reserved GPU clusters (H100, H200, B200) on Together AI with Kubernetes or Slurm orchestration, shared storage, credential management, and cluster scaling for ML and HPC jobs. Reach for it when the user needs multi-node compute or infrastructure control rather than a managed model endpoint.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[670,671,674,677],{"name":605,"slug":606,"type":16},{"name":672,"slug":673,"type":16},"Cloud","cloud",{"name":675,"slug":676,"type":16},"Kubernetes","kubernetes",{"name":614,"slug":615,"type":16},"2026-07-26T05:49:05.252646",{"slug":680,"name":680,"fn":681,"description":682,"org":683,"tags":684,"stars":23,"repoUrl":24,"updatedAt":697},"together-images","generate and edit images with Together AI","Text-to-image generation and image editing via Together AI, including FLUX and Kontext models, LoRA-based styling, reference-image guidance, and local image downloads. Reach for it whenever the user wants to generate or edit images on Together AI rather than create videos or build text-only chat applications.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[685,688,691,694],{"name":686,"slug":687,"type":16},"Creative","creative",{"name":689,"slug":690,"type":16},"Design","design",{"name":692,"slug":693,"type":16},"Image Generation","image-generation",{"name":695,"slug":696,"type":16},"Multimodal","multimodal","2026-07-17T06:04:23.067755",16,{"items":700,"total":746},[701,708,714,720,727,733,740],{"slug":561,"name":561,"fn":562,"description":563,"org":702,"tags":703,"stars":23,"repoUrl":24,"updatedAt":578},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[704,705,706,707],{"name":567,"slug":568,"type":16},{"name":570,"slug":571,"type":16},{"name":573,"slug":574,"type":16},{"name":576,"slug":577,"type":16},{"slug":4,"name":4,"fn":5,"description":6,"org":709,"tags":710,"stars":23,"repoUrl":24,"updatedAt":25},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[711,712,713],{"name":21,"slug":22,"type":16},{"name":18,"slug":19,"type":16},{"name":14,"slug":15,"type":16},{"slug":144,"name":144,"fn":586,"description":587,"org":715,"tags":716,"stars":23,"repoUrl":24,"updatedAt":597},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[717,718,719],{"name":591,"slug":592,"type":16},{"name":594,"slug":595,"type":16},{"name":18,"slug":19,"type":16},{"slug":599,"name":599,"fn":600,"description":601,"org":721,"tags":722,"stars":23,"repoUrl":24,"updatedAt":616},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[723,724,725,726],{"name":605,"slug":606,"type":16},{"name":608,"slug":609,"type":16},{"name":611,"slug":612,"type":16},{"name":614,"slug":615,"type":16},{"slug":618,"name":618,"fn":619,"description":620,"org":728,"tags":729,"stars":23,"repoUrl":24,"updatedAt":626},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[730,731,732],{"name":605,"slug":606,"type":16},{"name":608,"slug":609,"type":16},{"name":18,"slug":19,"type":16},{"slug":168,"name":168,"fn":628,"description":629,"org":734,"tags":735,"stars":23,"repoUrl":24,"updatedAt":640},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[736,737,738,739],{"name":591,"slug":592,"type":16},{"name":18,"slug":19,"type":16},{"name":635,"slug":636,"type":16},{"name":638,"slug":639,"type":16},{"slug":156,"name":156,"fn":642,"description":643,"org":741,"tags":742,"stars":23,"repoUrl":24,"updatedAt":653},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[743,744,745],{"name":647,"slug":648,"type":16},{"name":650,"slug":651,"type":16},{"name":18,"slug":19,"type":16},14]