[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-replicate-find-models":3,"mdc-rl0877-key":33,"related-repo-replicate-find-models":459,"related-org-replicate-find-models":540},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":11,"stars":22,"repoUrl":23,"updatedAt":24,"license":25,"forks":26,"topics":27,"repo":28,"sourceUrl":31,"mdContent":32},"find-models","find AI models on Replicate","Find AI models on Replicate using search and curated collections.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},"replicate","Replicate","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Freplicate.jpg",[12,16,19],{"name":13,"slug":14,"type":15},"LLM","llm","tag",{"name":17,"slug":18,"type":15},"Machine Learning","machine-learning",{"name":20,"slug":21,"type":15},"AI Infrastructure","ai-infrastructure",51,"https:\u002F\u002Fgithub.com\u002Freplicate\u002Fskills","2026-07-16T06:01:52.508562",null,6,[],{"repoUrl":23,"stars":22,"forks":26,"topics":29,"description":30},[],"A collection of Agent Skills for building AI-powered apps with Replicate","https:\u002F\u002Fgithub.com\u002Freplicate\u002Fskills\u002Ftree\u002FHEAD\u002Fskills\u002Ffind-models","---\nname: find-models\ndescription: Find AI models on Replicate using search and curated collections.\n---\n\n## Always search the API for current models\n\nThe AI model landscape changes weekly. New models ship constantly and older ones are deprecated or surpassed. Don't rely on model names you've seen before, including names from past conversations or training data. A specific model you \"know\" may no longer be the best choice, may be slower than newer alternatives, or may not exist anymore.\n\nAlways start by querying the Replicate API. Use search and collections to discover what's currently available, then read schemas to understand inputs and outputs before running anything.\n\n## Docs\n\n- Reference: \u003Chttps:\u002F\u002Freplicate.com\u002Fdocs\u002Fllms.txt>\n- OpenAPI schema: \u003Chttps:\u002F\u002Fapi.replicate.com\u002Fopenapi.json>\n- MCP server: \u003Chttps:\u002F\u002Fmcp.replicate.com>\n- Per-model docs: `https:\u002F\u002Freplicate.com\u002F{owner}\u002F{model}\u002Fllms.txt`\n- Set `Accept: text\u002Fmarkdown` when requesting docs pages for Markdown responses.\n\n## Search\n\n- Use the search API (`GET \u002Fv1\u002Fsearch?query=...`) to find models by task. Returns models, collections, and docs.\n- Search returns metadata for each model including `tags`, `generated_description`, and `run_count`.\n- The search API also returns matching collections alongside model results.\n- Avoid listing all models via API. It's a firehose. Use targeted queries.\n\n## Collections\n\n- Collections are curated groups of models maintained by Replicate staff.\n- The `official` collection contains always-warm models with stable APIs and predictable pricing.\n- Use collections to narrow a shortlist before deep comparison.\n- List collections with `GET \u002Fv1\u002Fcollections`. Get one by slug with `GET \u002Fv1\u002Fcollections\u002F{slug}`.\n\n## Reading model schemas\n\n- Every model exposes its input\u002Foutput schema via the models API (`GET \u002Fv1\u002Fmodels\u002F{owner}\u002F{name}`).\n- Schema path: `model.latest_version.openapi_schema.components.schemas.Input.properties`\n- Each property may include: `type`, `description`, `default`, `minimum`\u002F`maximum`, `enum`, `format` (e.g. `uri` for file inputs).\n- Always fetch the schema before running a model. Schemas change.\n\n## Picking the right model\n\n- Prefer official models. They're always warm (no cold boot), have stable APIs, and predictable pricing.\n- Prefer the latest version. If search returns v2.5 and v3.0, use v3.\n- Run count can be misleading. Old models accumulate runs over time but may be outdated. A model with 10M runs from 2023 is likely worse than a model with 100K runs from 2025.\n- Prefer recently released models. The AI space moves fast.\n- Check model tags to help filter by task (`image-generation`, `video`, `audio`, etc.).\n\n## Model identifiers\n\n- **Official models** use `owner\u002Fname` format (e.g. `owner\u002Fmodel-name`). Routes to the latest version automatically.\n- **Community models** require `owner\u002Fname:version_id`. You must pin a specific version. Community models can cold-boot and take time to start.\n- If you must use a community model, be aware that it can take a long time to boot. You can create always-on deployments, but you pay for model uptime.\n",{"data":34,"body":35},{"name":4,"description":6},{"type":36,"children":37},"root",[38,47,53,58,64,129,135,190,196,242,248,344,350,400,406],{"type":39,"tag":40,"props":41,"children":43},"element","h2",{"id":42},"always-search-the-api-for-current-models",[44],{"type":45,"value":46},"text","Always search the API for current models",{"type":39,"tag":48,"props":49,"children":50},"p",{},[51],{"type":45,"value":52},"The AI model landscape changes weekly. New models ship constantly and older ones are deprecated or surpassed. Don't rely on model names you've seen before, including names from past conversations or training data. A specific model you \"know\" may no longer be the best choice, may be slower than newer alternatives, or may not exist anymore.",{"type":39,"tag":48,"props":54,"children":55},{},[56],{"type":45,"value":57},"Always start by querying the Replicate API. Use search and collections to discover what's currently available, then read schemas to understand inputs and outputs before running anything.",{"type":39,"tag":40,"props":59,"children":61},{"id":60},"docs",[62],{"type":45,"value":63},"Docs",{"type":39,"tag":65,"props":66,"children":67},"ul",{},[68,82,93,104,116],{"type":39,"tag":69,"props":70,"children":71},"li",{},[72,74],{"type":45,"value":73},"Reference: ",{"type":39,"tag":75,"props":76,"children":80},"a",{"href":77,"rel":78},"https:\u002F\u002Freplicate.com\u002Fdocs\u002Fllms.txt",[79],"nofollow",[81],{"type":45,"value":77},{"type":39,"tag":69,"props":83,"children":84},{},[85,87],{"type":45,"value":86},"OpenAPI schema: ",{"type":39,"tag":75,"props":88,"children":91},{"href":89,"rel":90},"https:\u002F\u002Fapi.replicate.com\u002Fopenapi.json",[79],[92],{"type":45,"value":89},{"type":39,"tag":69,"props":94,"children":95},{},[96,98],{"type":45,"value":97},"MCP server: ",{"type":39,"tag":75,"props":99,"children":102},{"href":100,"rel":101},"https:\u002F\u002Fmcp.replicate.com",[79],[103],{"type":45,"value":100},{"type":39,"tag":69,"props":105,"children":106},{},[107,109],{"type":45,"value":108},"Per-model docs: ",{"type":39,"tag":110,"props":111,"children":113},"code",{"className":112},[],[114],{"type":45,"value":115},"https:\u002F\u002Freplicate.com\u002F{owner}\u002F{model}\u002Fllms.txt",{"type":39,"tag":69,"props":117,"children":118},{},[119,121,127],{"type":45,"value":120},"Set ",{"type":39,"tag":110,"props":122,"children":124},{"className":123},[],[125],{"type":45,"value":126},"Accept: text\u002Fmarkdown",{"type":45,"value":128}," when requesting docs pages for Markdown responses.",{"type":39,"tag":40,"props":130,"children":132},{"id":131},"search",[133],{"type":45,"value":134},"Search",{"type":39,"tag":65,"props":136,"children":137},{},[138,151,180,185],{"type":39,"tag":69,"props":139,"children":140},{},[141,143,149],{"type":45,"value":142},"Use the search API (",{"type":39,"tag":110,"props":144,"children":146},{"className":145},[],[147],{"type":45,"value":148},"GET \u002Fv1\u002Fsearch?query=...",{"type":45,"value":150},") to find models by task. Returns models, collections, and docs.",{"type":39,"tag":69,"props":152,"children":153},{},[154,156,162,164,170,172,178],{"type":45,"value":155},"Search returns metadata for each model including ",{"type":39,"tag":110,"props":157,"children":159},{"className":158},[],[160],{"type":45,"value":161},"tags",{"type":45,"value":163},", ",{"type":39,"tag":110,"props":165,"children":167},{"className":166},[],[168],{"type":45,"value":169},"generated_description",{"type":45,"value":171},", and ",{"type":39,"tag":110,"props":173,"children":175},{"className":174},[],[176],{"type":45,"value":177},"run_count",{"type":45,"value":179},".",{"type":39,"tag":69,"props":181,"children":182},{},[183],{"type":45,"value":184},"The search API also returns matching collections alongside model results.",{"type":39,"tag":69,"props":186,"children":187},{},[188],{"type":45,"value":189},"Avoid listing all models via API. It's a firehose. Use targeted queries.",{"type":39,"tag":40,"props":191,"children":193},{"id":192},"collections",[194],{"type":45,"value":195},"Collections",{"type":39,"tag":65,"props":197,"children":198},{},[199,204,217,222],{"type":39,"tag":69,"props":200,"children":201},{},[202],{"type":45,"value":203},"Collections are curated groups of models maintained by Replicate staff.",{"type":39,"tag":69,"props":205,"children":206},{},[207,209,215],{"type":45,"value":208},"The ",{"type":39,"tag":110,"props":210,"children":212},{"className":211},[],[213],{"type":45,"value":214},"official",{"type":45,"value":216}," collection contains always-warm models with stable APIs and predictable pricing.",{"type":39,"tag":69,"props":218,"children":219},{},[220],{"type":45,"value":221},"Use collections to narrow a shortlist before deep comparison.",{"type":39,"tag":69,"props":223,"children":224},{},[225,227,233,235,241],{"type":45,"value":226},"List collections with ",{"type":39,"tag":110,"props":228,"children":230},{"className":229},[],[231],{"type":45,"value":232},"GET \u002Fv1\u002Fcollections",{"type":45,"value":234},". Get one by slug with ",{"type":39,"tag":110,"props":236,"children":238},{"className":237},[],[239],{"type":45,"value":240},"GET \u002Fv1\u002Fcollections\u002F{slug}",{"type":45,"value":179},{"type":39,"tag":40,"props":243,"children":245},{"id":244},"reading-model-schemas",[246],{"type":45,"value":247},"Reading model schemas",{"type":39,"tag":65,"props":249,"children":250},{},[251,264,275,339],{"type":39,"tag":69,"props":252,"children":253},{},[254,256,262],{"type":45,"value":255},"Every model exposes its input\u002Foutput schema via the models API (",{"type":39,"tag":110,"props":257,"children":259},{"className":258},[],[260],{"type":45,"value":261},"GET \u002Fv1\u002Fmodels\u002F{owner}\u002F{name}",{"type":45,"value":263},").",{"type":39,"tag":69,"props":265,"children":266},{},[267,269],{"type":45,"value":268},"Schema path: ",{"type":39,"tag":110,"props":270,"children":272},{"className":271},[],[273],{"type":45,"value":274},"model.latest_version.openapi_schema.components.schemas.Input.properties",{"type":39,"tag":69,"props":276,"children":277},{},[278,280,286,287,293,294,300,301,307,309,315,316,322,323,329,331,337],{"type":45,"value":279},"Each property may include: ",{"type":39,"tag":110,"props":281,"children":283},{"className":282},[],[284],{"type":45,"value":285},"type",{"type":45,"value":163},{"type":39,"tag":110,"props":288,"children":290},{"className":289},[],[291],{"type":45,"value":292},"description",{"type":45,"value":163},{"type":39,"tag":110,"props":295,"children":297},{"className":296},[],[298],{"type":45,"value":299},"default",{"type":45,"value":163},{"type":39,"tag":110,"props":302,"children":304},{"className":303},[],[305],{"type":45,"value":306},"minimum",{"type":45,"value":308},"\u002F",{"type":39,"tag":110,"props":310,"children":312},{"className":311},[],[313],{"type":45,"value":314},"maximum",{"type":45,"value":163},{"type":39,"tag":110,"props":317,"children":319},{"className":318},[],[320],{"type":45,"value":321},"enum",{"type":45,"value":163},{"type":39,"tag":110,"props":324,"children":326},{"className":325},[],[327],{"type":45,"value":328},"format",{"type":45,"value":330}," (e.g. ",{"type":39,"tag":110,"props":332,"children":334},{"className":333},[],[335],{"type":45,"value":336},"uri",{"type":45,"value":338}," for file inputs).",{"type":39,"tag":69,"props":340,"children":341},{},[342],{"type":45,"value":343},"Always fetch the schema before running a model. Schemas change.",{"type":39,"tag":40,"props":345,"children":347},{"id":346},"picking-the-right-model",[348],{"type":45,"value":349},"Picking the right model",{"type":39,"tag":65,"props":351,"children":352},{},[353,358,363,368,373],{"type":39,"tag":69,"props":354,"children":355},{},[356],{"type":45,"value":357},"Prefer official models. They're always warm (no cold boot), have stable APIs, and predictable pricing.",{"type":39,"tag":69,"props":359,"children":360},{},[361],{"type":45,"value":362},"Prefer the latest version. If search returns v2.5 and v3.0, use v3.",{"type":39,"tag":69,"props":364,"children":365},{},[366],{"type":45,"value":367},"Run count can be misleading. Old models accumulate runs over time but may be outdated. A model with 10M runs from 2023 is likely worse than a model with 100K runs from 2025.",{"type":39,"tag":69,"props":369,"children":370},{},[371],{"type":45,"value":372},"Prefer recently released models. The AI space moves fast.",{"type":39,"tag":69,"props":374,"children":375},{},[376,378,384,385,391,392,398],{"type":45,"value":377},"Check model tags to help filter by task (",{"type":39,"tag":110,"props":379,"children":381},{"className":380},[],[382],{"type":45,"value":383},"image-generation",{"type":45,"value":163},{"type":39,"tag":110,"props":386,"children":388},{"className":387},[],[389],{"type":45,"value":390},"video",{"type":45,"value":163},{"type":39,"tag":110,"props":393,"children":395},{"className":394},[],[396],{"type":45,"value":397},"audio",{"type":45,"value":399},", etc.).",{"type":39,"tag":40,"props":401,"children":403},{"id":402},"model-identifiers",[404],{"type":45,"value":405},"Model identifiers",{"type":39,"tag":65,"props":407,"children":408},{},[409,436,454],{"type":39,"tag":69,"props":410,"children":411},{},[412,418,420,426,428,434],{"type":39,"tag":413,"props":414,"children":415},"strong",{},[416],{"type":45,"value":417},"Official models",{"type":45,"value":419}," use ",{"type":39,"tag":110,"props":421,"children":423},{"className":422},[],[424],{"type":45,"value":425},"owner\u002Fname",{"type":45,"value":427}," format (e.g. ",{"type":39,"tag":110,"props":429,"children":431},{"className":430},[],[432],{"type":45,"value":433},"owner\u002Fmodel-name",{"type":45,"value":435},"). Routes to the latest version automatically.",{"type":39,"tag":69,"props":437,"children":438},{},[439,444,446,452],{"type":39,"tag":413,"props":440,"children":441},{},[442],{"type":45,"value":443},"Community models",{"type":45,"value":445}," require ",{"type":39,"tag":110,"props":447,"children":449},{"className":448},[],[450],{"type":45,"value":451},"owner\u002Fname:version_id",{"type":45,"value":453},". You must pin a specific version. Community models can cold-boot and take time to start.",{"type":39,"tag":69,"props":455,"children":456},{},[457],{"type":45,"value":458},"If you must use a community model, be aware that it can take a long time to boot. You can create always-on deployments, but you pay for model uptime.",{"items":460,"total":539},[461,473,487,493,506,517,529],{"slug":462,"name":462,"fn":463,"description":464,"org":465,"tags":466,"stars":22,"repoUrl":23,"updatedAt":472},"build-models","build and package custom AI models","Package and build custom AI models with Cog for deployment on Replicate. Use when creating a cog.yaml or predict.py, defining model inputs and outputs, loading model weights at setup time, building Docker images for ML models, serving locally with cog serve or cog predict, or porting a HuggingFace, GitHub, or ComfyUI model to run on Replicate. Trigger on phrases like \"build a model\", \"package a model\", \"create a Cog model\", \"wrap a model\", \"containerize an AI model\", \"predict.py\", \"cog.yaml\", \"BasePredictor\", or \"Cog container\", and when referencing cog.run, github.com\u002Freplicate\u002Fcog, or github.com\u002Freplicate\u002Fcog-examples. Covers GPU and CUDA setup, pget for fast weight downloads, async predictors with continuous batching, streaming outputs, and cold-boot optimization for image, video, audio, and LLM models. For pushing built models to Replicate, see publish-models. For running existing models, see run-models.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[467,468,471],{"name":20,"slug":21,"type":15},{"name":469,"slug":470,"type":15},"Deployment","deployment",{"name":17,"slug":18,"type":15},"2026-07-16T06:02:28.318441",{"slug":474,"name":474,"fn":475,"description":476,"org":477,"tags":478,"stars":22,"repoUrl":23,"updatedAt":486},"compare-models","compare Replicate AI models","Compare Replicate models by cost, speed, quality, and capabilities.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[479,482,485],{"name":480,"slug":481,"type":15},"Analysis","analysis",{"name":483,"slug":484,"type":15},"Benchmarking","benchmarking",{"name":13,"slug":14,"type":15},"2026-07-16T06:03:10.401096",{"slug":4,"name":4,"fn":5,"description":6,"org":488,"tags":489,"stars":22,"repoUrl":23,"updatedAt":24},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[490,491,492],{"name":20,"slug":21,"type":15},{"name":13,"slug":14,"type":15},{"name":17,"slug":18,"type":15},{"slug":494,"name":494,"fn":495,"description":496,"org":497,"tags":498,"stars":22,"repoUrl":23,"updatedAt":505},"prompt-images","generate prompts for image models","Prompting techniques for AI image generation and editing models on Replicate. Use when writing prompts for image models or building image generation features.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[499,502,504],{"name":500,"slug":501,"type":15},"Creative","creative",{"name":503,"slug":383,"type":15},"Image Generation",{"name":13,"slug":14,"type":15},"2026-07-16T06:01:52.867443",{"slug":507,"name":507,"fn":508,"description":509,"org":510,"tags":511,"stars":22,"repoUrl":23,"updatedAt":516},"prompt-videos","generate prompts for AI video models","Prompting techniques for AI video generation models on Replicate. Use when writing prompts for video models or building video generation features.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[512,513,514],{"name":500,"slug":501,"type":15},{"name":13,"slug":14,"type":15},{"name":515,"slug":390,"type":15},"Video","2026-07-16T06:03:10.065511",{"slug":518,"name":518,"fn":519,"description":520,"org":521,"tags":522,"stars":22,"repoUrl":23,"updatedAt":528},"publish-models","publish and deploy AI models to Replicate","Push and publish custom AI models to Replicate, and set up CI\u002FCD for releasing new model versions safely. Use when running cog push, deploying a model to Replicate, releasing a new version, validating a model with cog-safe-push before publishing, configuring a Replicate deployment, setting up GitHub Actions for model releases, or porting a community model to an official one. Trigger on phrases like \"push a model to Replicate\", \"publish a model\", \"deploy a model\", \"release a new version\", \"cog push\", \"cog-safe-push\", \"model CI\", \"r8.im\", or \"schema compatibility\", and when referencing github.com\u002Freplicate\u002Fcog-safe-push or github.com\u002Freplicate\u002Fmodel-ci-template. Covers cog push, the full cog-safe-push config (test cases, fuzz, deployment, official_model), GitHub Actions patterns, multi-model matrix pushes, and post-publish monitoring. Assumes you already have a working Cog project; see build-models if you need to package one first.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[523,524,527],{"name":20,"slug":21,"type":15},{"name":525,"slug":526,"type":15},"CI\u002FCD","ci-cd",{"name":469,"slug":470,"type":15},"2026-07-16T06:02:28.648245",{"slug":530,"name":530,"fn":531,"description":532,"org":533,"tags":534,"stars":22,"repoUrl":23,"updatedAt":538},"run-models","run AI models on Replicate","Run AI models on Replicate via predictions, webhooks, and streaming.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[535,536,537],{"name":20,"slug":21,"type":15},{"name":13,"slug":14,"type":15},{"name":17,"slug":18,"type":15},"2026-07-16T06:03:09.738392",7,{"items":541,"total":539},[542,548,554,560,566,572,578],{"slug":462,"name":462,"fn":463,"description":464,"org":543,"tags":544,"stars":22,"repoUrl":23,"updatedAt":472},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[545,546,547],{"name":20,"slug":21,"type":15},{"name":469,"slug":470,"type":15},{"name":17,"slug":18,"type":15},{"slug":474,"name":474,"fn":475,"description":476,"org":549,"tags":550,"stars":22,"repoUrl":23,"updatedAt":486},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[551,552,553],{"name":480,"slug":481,"type":15},{"name":483,"slug":484,"type":15},{"name":13,"slug":14,"type":15},{"slug":4,"name":4,"fn":5,"description":6,"org":555,"tags":556,"stars":22,"repoUrl":23,"updatedAt":24},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[557,558,559],{"name":20,"slug":21,"type":15},{"name":13,"slug":14,"type":15},{"name":17,"slug":18,"type":15},{"slug":494,"name":494,"fn":495,"description":496,"org":561,"tags":562,"stars":22,"repoUrl":23,"updatedAt":505},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[563,564,565],{"name":500,"slug":501,"type":15},{"name":503,"slug":383,"type":15},{"name":13,"slug":14,"type":15},{"slug":507,"name":507,"fn":508,"description":509,"org":567,"tags":568,"stars":22,"repoUrl":23,"updatedAt":516},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[569,570,571],{"name":500,"slug":501,"type":15},{"name":13,"slug":14,"type":15},{"name":515,"slug":390,"type":15},{"slug":518,"name":518,"fn":519,"description":520,"org":573,"tags":574,"stars":22,"repoUrl":23,"updatedAt":528},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[575,576,577],{"name":20,"slug":21,"type":15},{"name":525,"slug":526,"type":15},{"name":469,"slug":470,"type":15},{"slug":530,"name":530,"fn":531,"description":532,"org":579,"tags":580,"stars":22,"repoUrl":23,"updatedAt":538},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[581,582,583],{"name":20,"slug":21,"type":15},{"name":13,"slug":14,"type":15},{"name":17,"slug":18,"type":15}]