[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-together-ai-together-images":3,"mdc-cl0ugy-key":37,"related-repo-together-ai-together-images":593,"related-org-together-ai-together-images":701},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":12,"stars":26,"repoUrl":27,"updatedAt":28,"license":29,"forks":30,"topics":31,"repo":32,"sourceUrl":35,"mdContent":36},"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},"together-ai","Together AI","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Ftogether-ai.jpg","togethercomputer",[13,17,20,23],{"name":14,"slug":15,"type":16},"Creative","creative","tag",{"name":18,"slug":19,"type":16},"Multimodal","multimodal",{"name":21,"slug":22,"type":16},"Image Generation","image-generation",{"name":24,"slug":25,"type":16},"Design","design",31,"https:\u002F\u002Fgithub.com\u002Ftogethercomputer\u002Fskills","2026-07-17T06:04:23.067755",null,4,[],{"repoUrl":27,"stars":26,"forks":30,"topics":33,"description":34},[],"Skills to help your coding agents use Together AI products.","https:\u002F\u002Fgithub.com\u002Ftogethercomputer\u002Fskills\u002Ftree\u002FHEAD\u002Fskills\u002Ftogether-images","---\nname: together-images\ndescription: \"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.\"\n---\n\n# Together Images\n\n## Overview\n\nUse Together AI image APIs for:\n\n- text-to-image generation\n- image editing with Kontext\n- FLUX.2-specific options\n- LoRA adapters\n- reference-image guidance\n\n## When This Skill Wins\n\n- Generate still images from prompts\n- Edit an existing image with text guidance\n- Apply LoRA styles to FLUX models\n- Choose image models or dimensions for a product workflow\n\n## Hand Off To Another Skill\n\n- Use `together-video` for motion or video generation\n- Use `together-chat-completions` for text-only generation\n- Use `together-dedicated-containers` only when the user needs a custom image runtime rather than the managed API\n\n## Quick Routing\n\n- **Basic text-to-image**\n  - Start with [scripts\u002Fgenerate_image.py](scripts\u002Fgenerate_image.py) or [scripts\u002Fgenerate_image.ts](scripts\u002Fgenerate_image.ts)\n  - Read [references\u002Fapi-reference.md](references\u002Fapi-reference.md)\n- **Multiple variations, base64 output, or seeded runs**\n  - Start with [scripts\u002Fgenerate_image.py](scripts\u002Fgenerate_image.py) or [scripts\u002Fgenerate_image.ts](scripts\u002Fgenerate_image.ts)\n  - Read [references\u002Fapi-reference.md](references\u002Fapi-reference.md)\n- **Image editing with Kontext**\n  - Start with [scripts\u002Fkontext_editing.py](scripts\u002Fkontext_editing.py)\n  - Read [references\u002Fapi-reference.md](references\u002Fapi-reference.md)\n- **Generate then edit (e.g. product photos)**\n  - Start with [scripts\u002Fkontext_editing.py](scripts\u002Fkontext_editing.py) (Example 7)\n  - Generate with FLUX, feed the URL to Kontext, save both locally\n- **LoRA styling**\n  - Start with [scripts\u002Flora_generation.py](scripts\u002Flora_generation.py)\n  - Read [references\u002Fapi-reference.md](references\u002Fapi-reference.md)\n- **Model and dimension selection**\n  - Read [references\u002Fmodels.md](references\u002Fmodels.md)\n\n## Workflow\n\n1. Confirm whether the task is generation, editing, or style transfer.\n2. Choose the model family and output dimensions first.\n3. Add reference images, LoRAs, or FLUX.2-only parameters only when the use case needs them.\n4. Generate the asset, then download or decode it into the expected local format.\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- Match the script to the workflow type instead of packing every image feature into one request path.\n- Keep model selection explicit because FLUX, Kontext, and partner models differ in capabilities.\n- Preserve reproducibility with seeds when the user needs stable outputs.\n- For editing or reference-image flows, validate that the chosen model actually supports the feature.\n\n## Resource Map\n\n- **API reference**: [references\u002Fapi-reference.md](references\u002Fapi-reference.md)\n- **Troubleshooting and generation tuning**: [references\u002Fapi-reference.md](references\u002Fapi-reference.md)\n- **Model guide**: [references\u002Fmodels.md](references\u002Fmodels.md)\n- **Python image generation**: [scripts\u002Fgenerate_image.py](scripts\u002Fgenerate_image.py)\n- **TypeScript image generation**: [scripts\u002Fgenerate_image.ts](scripts\u002Fgenerate_image.ts)\n- **Python Kontext editing**: [scripts\u002Fkontext_editing.py](scripts\u002Fkontext_editing.py)\n- **Python LoRA generation**: [scripts\u002Flora_generation.py](scripts\u002Flora_generation.py)\n\n## Official Docs\n\n- [Images Overview](https:\u002F\u002Fdocs.together.ai\u002Fdocs\u002Fimages-overview)\n- [FLUX.2 Quickstart](https:\u002F\u002Fdocs.together.ai\u002Fdocs\u002Fquickstart-flux)\n- [FLUX Kontext](https:\u002F\u002Fdocs.together.ai\u002Fdocs\u002Fquickstart-flux-kontext)\n- [FLUX LoRA](https:\u002F\u002Fdocs.together.ai\u002Fdocs\u002Fquickstart-flux-lora)\n- [Image Generation API](https:\u002F\u002Fdocs.together.ai\u002Freference\u002Fpost-images-generations)\n",{"data":38,"body":39},{"name":4,"description":6},{"type":40,"children":41},"root",[42,50,57,63,93,99,122,128,169,175,352,358,382,388,432,438,533,539],{"type":43,"tag":44,"props":45,"children":46},"element","h1",{"id":4},[47],{"type":48,"value":49},"text","Together Images",{"type":43,"tag":51,"props":52,"children":54},"h2",{"id":53},"overview",[55],{"type":48,"value":56},"Overview",{"type":43,"tag":58,"props":59,"children":60},"p",{},[61],{"type":48,"value":62},"Use Together AI image APIs for:",{"type":43,"tag":64,"props":65,"children":66},"ul",{},[67,73,78,83,88],{"type":43,"tag":68,"props":69,"children":70},"li",{},[71],{"type":48,"value":72},"text-to-image generation",{"type":43,"tag":68,"props":74,"children":75},{},[76],{"type":48,"value":77},"image editing with Kontext",{"type":43,"tag":68,"props":79,"children":80},{},[81],{"type":48,"value":82},"FLUX.2-specific options",{"type":43,"tag":68,"props":84,"children":85},{},[86],{"type":48,"value":87},"LoRA adapters",{"type":43,"tag":68,"props":89,"children":90},{},[91],{"type":48,"value":92},"reference-image guidance",{"type":43,"tag":51,"props":94,"children":96},{"id":95},"when-this-skill-wins",[97],{"type":48,"value":98},"When This Skill Wins",{"type":43,"tag":64,"props":100,"children":101},{},[102,107,112,117],{"type":43,"tag":68,"props":103,"children":104},{},[105],{"type":48,"value":106},"Generate still images from prompts",{"type":43,"tag":68,"props":108,"children":109},{},[110],{"type":48,"value":111},"Edit an existing image with text guidance",{"type":43,"tag":68,"props":113,"children":114},{},[115],{"type":48,"value":116},"Apply LoRA styles to FLUX models",{"type":43,"tag":68,"props":118,"children":119},{},[120],{"type":48,"value":121},"Choose image models or dimensions for a product workflow",{"type":43,"tag":51,"props":123,"children":125},{"id":124},"hand-off-to-another-skill",[126],{"type":48,"value":127},"Hand Off To Another Skill",{"type":43,"tag":64,"props":129,"children":130},{},[131,145,157],{"type":43,"tag":68,"props":132,"children":133},{},[134,136,143],{"type":48,"value":135},"Use ",{"type":43,"tag":137,"props":138,"children":140},"code",{"className":139},[],[141],{"type":48,"value":142},"together-video",{"type":48,"value":144}," for motion or video generation",{"type":43,"tag":68,"props":146,"children":147},{},[148,149,155],{"type":48,"value":135},{"type":43,"tag":137,"props":150,"children":152},{"className":151},[],[153],{"type":48,"value":154},"together-chat-completions",{"type":48,"value":156}," for text-only generation",{"type":43,"tag":68,"props":158,"children":159},{},[160,161,167],{"type":48,"value":135},{"type":43,"tag":137,"props":162,"children":164},{"className":163},[],[165],{"type":48,"value":166},"together-dedicated-containers",{"type":48,"value":168}," only when the user needs a custom image runtime rather than the managed API",{"type":43,"tag":51,"props":170,"children":172},{"id":171},"quick-routing",[173],{"type":48,"value":174},"Quick Routing",{"type":43,"tag":64,"props":176,"children":177},{},[178,218,250,278,304,332],{"type":43,"tag":68,"props":179,"children":180},{},[181,187],{"type":43,"tag":182,"props":183,"children":184},"strong",{},[185],{"type":48,"value":186},"Basic text-to-image",{"type":43,"tag":64,"props":188,"children":189},{},[190,208],{"type":43,"tag":68,"props":191,"children":192},{},[193,195,201,203],{"type":48,"value":194},"Start with ",{"type":43,"tag":196,"props":197,"children":199},"a",{"href":198},"scripts\u002Fgenerate_image.py",[200],{"type":48,"value":198},{"type":48,"value":202}," or ",{"type":43,"tag":196,"props":204,"children":206},{"href":205},"scripts\u002Fgenerate_image.ts",[207],{"type":48,"value":205},{"type":43,"tag":68,"props":209,"children":210},{},[211,213],{"type":48,"value":212},"Read ",{"type":43,"tag":196,"props":214,"children":216},{"href":215},"references\u002Fapi-reference.md",[217],{"type":48,"value":215},{"type":43,"tag":68,"props":219,"children":220},{},[221,226],{"type":43,"tag":182,"props":222,"children":223},{},[224],{"type":48,"value":225},"Multiple variations, base64 output, or seeded runs",{"type":43,"tag":64,"props":227,"children":228},{},[229,242],{"type":43,"tag":68,"props":230,"children":231},{},[232,233,237,238],{"type":48,"value":194},{"type":43,"tag":196,"props":234,"children":235},{"href":198},[236],{"type":48,"value":198},{"type":48,"value":202},{"type":43,"tag":196,"props":239,"children":240},{"href":205},[241],{"type":48,"value":205},{"type":43,"tag":68,"props":243,"children":244},{},[245,246],{"type":48,"value":212},{"type":43,"tag":196,"props":247,"children":248},{"href":215},[249],{"type":48,"value":215},{"type":43,"tag":68,"props":251,"children":252},{},[253,258],{"type":43,"tag":182,"props":254,"children":255},{},[256],{"type":48,"value":257},"Image editing with Kontext",{"type":43,"tag":64,"props":259,"children":260},{},[261,270],{"type":43,"tag":68,"props":262,"children":263},{},[264,265],{"type":48,"value":194},{"type":43,"tag":196,"props":266,"children":268},{"href":267},"scripts\u002Fkontext_editing.py",[269],{"type":48,"value":267},{"type":43,"tag":68,"props":271,"children":272},{},[273,274],{"type":48,"value":212},{"type":43,"tag":196,"props":275,"children":276},{"href":215},[277],{"type":48,"value":215},{"type":43,"tag":68,"props":279,"children":280},{},[281,286],{"type":43,"tag":182,"props":282,"children":283},{},[284],{"type":48,"value":285},"Generate then edit (e.g. product photos)",{"type":43,"tag":64,"props":287,"children":288},{},[289,299],{"type":43,"tag":68,"props":290,"children":291},{},[292,293,297],{"type":48,"value":194},{"type":43,"tag":196,"props":294,"children":295},{"href":267},[296],{"type":48,"value":267},{"type":48,"value":298}," (Example 7)",{"type":43,"tag":68,"props":300,"children":301},{},[302],{"type":48,"value":303},"Generate with FLUX, feed the URL to Kontext, save both locally",{"type":43,"tag":68,"props":305,"children":306},{},[307,312],{"type":43,"tag":182,"props":308,"children":309},{},[310],{"type":48,"value":311},"LoRA styling",{"type":43,"tag":64,"props":313,"children":314},{},[315,324],{"type":43,"tag":68,"props":316,"children":317},{},[318,319],{"type":48,"value":194},{"type":43,"tag":196,"props":320,"children":322},{"href":321},"scripts\u002Flora_generation.py",[323],{"type":48,"value":321},{"type":43,"tag":68,"props":325,"children":326},{},[327,328],{"type":48,"value":212},{"type":43,"tag":196,"props":329,"children":330},{"href":215},[331],{"type":48,"value":215},{"type":43,"tag":68,"props":333,"children":334},{},[335,340],{"type":43,"tag":182,"props":336,"children":337},{},[338],{"type":48,"value":339},"Model and dimension selection",{"type":43,"tag":64,"props":341,"children":342},{},[343],{"type":43,"tag":68,"props":344,"children":345},{},[346,347],{"type":48,"value":212},{"type":43,"tag":196,"props":348,"children":350},{"href":349},"references\u002Fmodels.md",[351],{"type":48,"value":349},{"type":43,"tag":51,"props":353,"children":355},{"id":354},"workflow",[356],{"type":48,"value":357},"Workflow",{"type":43,"tag":359,"props":360,"children":361},"ol",{},[362,367,372,377],{"type":43,"tag":68,"props":363,"children":364},{},[365],{"type":48,"value":366},"Confirm whether the task is generation, editing, or style transfer.",{"type":43,"tag":68,"props":368,"children":369},{},[370],{"type":48,"value":371},"Choose the model family and output dimensions first.",{"type":43,"tag":68,"props":373,"children":374},{},[375],{"type":48,"value":376},"Add reference images, LoRAs, or FLUX.2-only parameters only when the use case needs them.",{"type":43,"tag":68,"props":378,"children":379},{},[380],{"type":48,"value":381},"Generate the asset, then download or decode it into the expected local format.",{"type":43,"tag":51,"props":383,"children":385},{"id":384},"high-signal-rules",[386],{"type":48,"value":387},"High-Signal Rules",{"type":43,"tag":64,"props":389,"children":390},{},[391,412,417,422,427],{"type":43,"tag":68,"props":392,"children":393},{},[394,396,402,404,410],{"type":48,"value":395},"Python scripts require the Together v2 SDK (",{"type":43,"tag":137,"props":397,"children":399},{"className":398},[],[400],{"type":48,"value":401},"together>=2.0.0",{"type":48,"value":403},"). If the user is on an older version, they must upgrade first: ",{"type":43,"tag":137,"props":405,"children":407},{"className":406},[],[408],{"type":48,"value":409},"uv pip install --upgrade \"together>=2.0.0\"",{"type":48,"value":411},".",{"type":43,"tag":68,"props":413,"children":414},{},[415],{"type":48,"value":416},"Match the script to the workflow type instead of packing every image feature into one request path.",{"type":43,"tag":68,"props":418,"children":419},{},[420],{"type":48,"value":421},"Keep model selection explicit because FLUX, Kontext, and partner models differ in capabilities.",{"type":43,"tag":68,"props":423,"children":424},{},[425],{"type":48,"value":426},"Preserve reproducibility with seeds when the user needs stable outputs.",{"type":43,"tag":68,"props":428,"children":429},{},[430],{"type":48,"value":431},"For editing or reference-image flows, validate that the chosen model actually supports the feature.",{"type":43,"tag":51,"props":433,"children":435},{"id":434},"resource-map",[436],{"type":48,"value":437},"Resource Map",{"type":43,"tag":64,"props":439,"children":440},{},[441,455,468,481,494,507,520],{"type":43,"tag":68,"props":442,"children":443},{},[444,449,451],{"type":43,"tag":182,"props":445,"children":446},{},[447],{"type":48,"value":448},"API reference",{"type":48,"value":450},": ",{"type":43,"tag":196,"props":452,"children":453},{"href":215},[454],{"type":48,"value":215},{"type":43,"tag":68,"props":456,"children":457},{},[458,463,464],{"type":43,"tag":182,"props":459,"children":460},{},[461],{"type":48,"value":462},"Troubleshooting and generation tuning",{"type":48,"value":450},{"type":43,"tag":196,"props":465,"children":466},{"href":215},[467],{"type":48,"value":215},{"type":43,"tag":68,"props":469,"children":470},{},[471,476,477],{"type":43,"tag":182,"props":472,"children":473},{},[474],{"type":48,"value":475},"Model guide",{"type":48,"value":450},{"type":43,"tag":196,"props":478,"children":479},{"href":349},[480],{"type":48,"value":349},{"type":43,"tag":68,"props":482,"children":483},{},[484,489,490],{"type":43,"tag":182,"props":485,"children":486},{},[487],{"type":48,"value":488},"Python image generation",{"type":48,"value":450},{"type":43,"tag":196,"props":491,"children":492},{"href":198},[493],{"type":48,"value":198},{"type":43,"tag":68,"props":495,"children":496},{},[497,502,503],{"type":43,"tag":182,"props":498,"children":499},{},[500],{"type":48,"value":501},"TypeScript image generation",{"type":48,"value":450},{"type":43,"tag":196,"props":504,"children":505},{"href":205},[506],{"type":48,"value":205},{"type":43,"tag":68,"props":508,"children":509},{},[510,515,516],{"type":43,"tag":182,"props":511,"children":512},{},[513],{"type":48,"value":514},"Python Kontext editing",{"type":48,"value":450},{"type":43,"tag":196,"props":517,"children":518},{"href":267},[519],{"type":48,"value":267},{"type":43,"tag":68,"props":521,"children":522},{},[523,528,529],{"type":43,"tag":182,"props":524,"children":525},{},[526],{"type":48,"value":527},"Python LoRA generation",{"type":48,"value":450},{"type":43,"tag":196,"props":530,"children":531},{"href":321},[532],{"type":48,"value":321},{"type":43,"tag":51,"props":534,"children":536},{"id":535},"official-docs",[537],{"type":48,"value":538},"Official Docs",{"type":43,"tag":64,"props":540,"children":541},{},[542,553,563,573,583],{"type":43,"tag":68,"props":543,"children":544},{},[545],{"type":43,"tag":196,"props":546,"children":550},{"href":547,"rel":548},"https:\u002F\u002Fdocs.together.ai\u002Fdocs\u002Fimages-overview",[549],"nofollow",[551],{"type":48,"value":552},"Images Overview",{"type":43,"tag":68,"props":554,"children":555},{},[556],{"type":43,"tag":196,"props":557,"children":560},{"href":558,"rel":559},"https:\u002F\u002Fdocs.together.ai\u002Fdocs\u002Fquickstart-flux",[549],[561],{"type":48,"value":562},"FLUX.2 Quickstart",{"type":43,"tag":68,"props":564,"children":565},{},[566],{"type":43,"tag":196,"props":567,"children":570},{"href":568,"rel":569},"https:\u002F\u002Fdocs.together.ai\u002Fdocs\u002Fquickstart-flux-kontext",[549],[571],{"type":48,"value":572},"FLUX Kontext",{"type":43,"tag":68,"props":574,"children":575},{},[576],{"type":43,"tag":196,"props":577,"children":580},{"href":578,"rel":579},"https:\u002F\u002Fdocs.together.ai\u002Fdocs\u002Fquickstart-flux-lora",[549],[581],{"type":48,"value":582},"FLUX LoRA",{"type":43,"tag":68,"props":584,"children":585},{},[586],{"type":43,"tag":196,"props":587,"children":590},{"href":588,"rel":589},"https:\u002F\u002Fdocs.together.ai\u002Freference\u002Fpost-images-generations",[549],[591],{"type":48,"value":592},"Image Generation API",{"items":594,"total":700},[595,614,630,643,661,671,686],{"slug":596,"name":596,"fn":597,"description":598,"org":599,"tags":600,"stars":26,"repoUrl":27,"updatedAt":613},"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},[601,604,607,610],{"name":602,"slug":603,"type":16},"Audio","audio",{"name":605,"slug":606,"type":16},"Speech","speech",{"name":608,"slug":609,"type":16},"Text-to-Speech","text-to-speech",{"name":611,"slug":612,"type":16},"Transcription","transcription","2026-07-26T05:49:08.246858",{"slug":615,"name":615,"fn":616,"description":617,"org":618,"tags":619,"stars":26,"repoUrl":27,"updatedAt":629},"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},[620,623,626],{"name":621,"slug":622,"type":16},"Automation","automation",{"name":624,"slug":625,"type":16},"LLM","llm",{"name":627,"slug":628,"type":16},"Performance","performance","2026-07-17T06:08:23.919602",{"slug":154,"name":154,"fn":631,"description":632,"org":633,"tags":634,"stars":26,"repoUrl":27,"updatedAt":642},"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},[635,638,641],{"name":636,"slug":637,"type":16},"AI","ai",{"name":639,"slug":640,"type":16},"API Development","api-development",{"name":624,"slug":625,"type":16},"2026-07-26T05:49:11.244104",{"slug":166,"name":166,"fn":644,"description":645,"org":646,"tags":647,"stars":26,"repoUrl":27,"updatedAt":660},"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},[648,651,654,657],{"name":649,"slug":650,"type":16},"AI Infrastructure","ai-infrastructure",{"name":652,"slug":653,"type":16},"Deployment","deployment",{"name":655,"slug":656,"type":16},"Docker","docker",{"name":658,"slug":659,"type":16},"Machine Learning","machine-learning","2026-07-26T05:49:09.267892",{"slug":662,"name":662,"fn":663,"description":664,"org":665,"tags":666,"stars":26,"repoUrl":27,"updatedAt":670},"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},[667,668,669],{"name":649,"slug":650,"type":16},{"name":652,"slug":653,"type":16},{"name":624,"slug":625,"type":16},"2026-07-26T06:08:44.044039",{"slug":672,"name":672,"fn":673,"description":674,"org":675,"tags":676,"stars":26,"repoUrl":27,"updatedAt":685},"together-embeddings","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},[677,678,679,682],{"name":636,"slug":637,"type":16},{"name":624,"slug":625,"type":16},{"name":680,"slug":681,"type":16},"RAG","rag",{"name":683,"slug":684,"type":16},"Search","search","2026-07-26T05:49:06.247906",{"slug":687,"name":687,"fn":688,"description":689,"org":690,"tags":691,"stars":26,"repoUrl":27,"updatedAt":699},"together-evaluations","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},[692,695,698],{"name":693,"slug":694,"type":16},"Benchmarking","benchmarking",{"name":696,"slug":697,"type":16},"Evals","evals",{"name":624,"slug":625,"type":16},"2026-07-26T05:49:07.241553",14,{"items":702,"total":813},[703,724,736,743,749,755,762,768,775,781,791,806],{"slug":704,"name":704,"fn":705,"description":706,"org":707,"tags":708,"stars":721,"repoUrl":722,"updatedAt":723},"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},[709,712,715,718],{"name":710,"slug":711,"type":16},"Content Creation","content-creation",{"name":713,"slug":714,"type":16},"Marketing","marketing",{"name":716,"slug":717,"type":16},"SEO","seo",{"name":719,"slug":720,"type":16},"Writing","writing",1151,"https:\u002F\u002Fgithub.com\u002Ftogethercomputer\u002Ftogether-cookbook","2026-07-17T06:07:39.475433",{"slug":725,"name":725,"fn":726,"description":727,"org":728,"tags":729,"stars":721,"repoUrl":722,"updatedAt":735},"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},[730,731,732,734],{"name":710,"slug":711,"type":16},{"name":713,"slug":714,"type":16},{"name":733,"slug":725,"type":16},"Social Media",{"name":719,"slug":720,"type":16},"2026-07-17T06:07:38.455058",{"slug":596,"name":596,"fn":597,"description":598,"org":737,"tags":738,"stars":26,"repoUrl":27,"updatedAt":613},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[739,740,741,742],{"name":602,"slug":603,"type":16},{"name":605,"slug":606,"type":16},{"name":608,"slug":609,"type":16},{"name":611,"slug":612,"type":16},{"slug":615,"name":615,"fn":616,"description":617,"org":744,"tags":745,"stars":26,"repoUrl":27,"updatedAt":629},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[746,747,748],{"name":621,"slug":622,"type":16},{"name":624,"slug":625,"type":16},{"name":627,"slug":628,"type":16},{"slug":154,"name":154,"fn":631,"description":632,"org":750,"tags":751,"stars":26,"repoUrl":27,"updatedAt":642},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[752,753,754],{"name":636,"slug":637,"type":16},{"name":639,"slug":640,"type":16},{"name":624,"slug":625,"type":16},{"slug":166,"name":166,"fn":644,"description":645,"org":756,"tags":757,"stars":26,"repoUrl":27,"updatedAt":660},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[758,759,760,761],{"name":649,"slug":650,"type":16},{"name":652,"slug":653,"type":16},{"name":655,"slug":656,"type":16},{"name":658,"slug":659,"type":16},{"slug":662,"name":662,"fn":663,"description":664,"org":763,"tags":764,"stars":26,"repoUrl":27,"updatedAt":670},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[765,766,767],{"name":649,"slug":650,"type":16},{"name":652,"slug":653,"type":16},{"name":624,"slug":625,"type":16},{"slug":672,"name":672,"fn":673,"description":674,"org":769,"tags":770,"stars":26,"repoUrl":27,"updatedAt":685},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[771,772,773,774],{"name":636,"slug":637,"type":16},{"name":624,"slug":625,"type":16},{"name":680,"slug":681,"type":16},{"name":683,"slug":684,"type":16},{"slug":687,"name":687,"fn":688,"description":689,"org":776,"tags":777,"stars":26,"repoUrl":27,"updatedAt":699},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[778,779,780],{"name":693,"slug":694,"type":16},{"name":696,"slug":697,"type":16},{"name":624,"slug":625,"type":16},{"slug":782,"name":782,"fn":783,"description":784,"org":785,"tags":786,"stars":26,"repoUrl":27,"updatedAt":790},"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},[787,788,789],{"name":636,"slug":637,"type":16},{"name":624,"slug":625,"type":16},{"name":658,"slug":659,"type":16},"2026-07-26T05:49:10.243114",{"slug":792,"name":792,"fn":793,"description":794,"org":795,"tags":796,"stars":26,"repoUrl":27,"updatedAt":805},"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},[797,798,801,804],{"name":649,"slug":650,"type":16},{"name":799,"slug":800,"type":16},"Cloud","cloud",{"name":802,"slug":803,"type":16},"Kubernetes","kubernetes",{"name":658,"slug":659,"type":16},"2026-07-26T05:49:05.252646",{"slug":4,"name":4,"fn":5,"description":6,"org":807,"tags":808,"stars":26,"repoUrl":27,"updatedAt":28},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[809,810,811,812],{"name":14,"slug":15,"type":16},{"name":24,"slug":25,"type":16},{"name":21,"slug":22,"type":16},{"name":18,"slug":19,"type":16},16]