{"uid":"cap_QWawDnkJfTRjfAGGOBmW2","slug":"openrouter-withzero-xyz-openrouter-model-catalog-listing-fc0b8c62","name":"OpenRouter Model Catalog Listing","description":"List all models available via OpenRouter with per-token pricing. Use this to discover model IDs and their costs before calling POST /api/v1/chat. 📖 Full guide: https://openrouter.withzero.xyz/llms.txt","url":"https://openrouter.withzero.xyz/api/v1/models","method":"GET","headers":{},"bodySchema":null,"responseSchema":{"type":"object","$schema":"https://json-schema.org/draft/2020-12/schema","required":["data"],"properties":{"data":{"type":"array","items":{"type":"object","required":["id","name","context_length","pricing"],"properties":{"id":{"type":"string"},"name":{"type":"string"},"pricing":{"type":"object","required":["prompt","completion"],"properties":{"image":{"type":"string"},"prompt":{"type":"string"},"request":{"type":"string"},"completion":{"type":"string"}},"additionalProperties":false},"description":{"type":"string"},"architecture":{"type":"object","required":["modality","tokenizer"],"properties":{"modality":{"type":"string"},"tokenizer":{"type":"string"},"instruct_type":{"type":"string"}},"additionalProperties":false},"context_length":{"type":"number"}},"additionalProperties":false}}},"additionalProperties":false},"example":null,"exampleRequest":null,"tags":[],"displayCostAmount":"unknown","displayCostAsset":"USDC","priceDynamic":false,"priceHint":null,"priceStatus":"unknown_unparsed","priceSource":"registry","requiresHandshake":false,"reviewCount":0,"rating":{"score":"0.00","successRate":"1.00","reviews":0,"stars":null,"state":"rated"},"availabilityStatus":"unknown","priceObserved":null,"sessionDeposit":null,"pricing":{"kind":"unknown","summary":"price unknown","primary":{"kind":"unknown","protocol":"mpp","network":"tempo","amountUsd":null,"per":"call","confidence":"unknown"},"accepted":[{"kind":"unknown","protocol":"mpp","network":"tempo","amountUsd":null,"per":"call","confidence":"unknown"}]},"paymentMethods":[{"uid":"pm_vOjw7wGuEGTjiMuzqVwAq","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"unknown","costPer":"request","priority":0,"asset":null,"unit":"request","depositMicros":null,"planRef":null}],"brandName":"openrouter.withzero.xyz","brandSlug":"openrouter-withzero-xyz-mpp","brandBaseUrl":"https://openrouter.withzero.xyz","brandDocsUrl":null,"whatItDoes":"Returns the list of all available AI models on OpenRouter with their IDs, names, context lengths, pricing, and architecture details","exampleAgentPrompt":"What AI models are available through this OpenRouter proxy and what are their per-token prices for prompt and completion — I want to pick the cheapest one before sending my chat request.","exampleUseCases":[{"title":"Find cheapest model for budget constraints","prompt":"I need to summarize a bunch of customer feedback today but my API budget is tight. Can you check what models are available through OpenRouter and tell me which ones are cheapest per token so I can pick the best deal?"},{"title":"Compare context windows for long documents","prompt":"I'm working with some really long documents that might be 20k+ tokens. Can you show me which OpenRouter models have the biggest context windows so I know what I can actually process?"},{"title":"Identify vision-capable models for images","prompt":"I want to start analyzing images in my workflow. Show me all the OpenRouter models that support vision or image inputs so I can see what's available before I start building."}],"resultDescription":"A JSON object with a 'data' array where each element describes one available model: its string ID and display name, numeric context_length, pricing object with prompt/completion/image/request rates as strings, optional description, and optional architecture object with modality, tokenizer, and instruct_type fields.","failureModes":["Upstream OpenRouter API unavailable — returns 5xx error","Network timeout if OpenRouter is slow to respond","Empty data array if no models are currently listed","Authentication or proxy misconfiguration returns 401/403"],"whenToPreferThis":"Use this endpoint before calling the chat completion endpoint to discover which model IDs are valid, understand their context limits, and compare per-token pricing. Prefer this over hardcoding model names since available models and prices may change. Ideal for cost-optimization workflows that need to select the cheapest suitable model dynamically.","instructions":"# Model catalog — lookup table for the chat-completion sibling\n\n## Workflow\n- Each returned `id` is a valid `model` value for the chat-completion sibling: POST /api/v1/chat/completions.\n- `pricing.prompt` / `pricing.completion` are the per-token rates that sibling charges at; `context_length` bounds your prompt + max_tokens.","reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":4,"lastUsedAt":"2026-07-29T00:21:26.137Z","lastSuccessfullyRanAt":"2026-07-29T00:21:26.137Z","lastHealthCheckAt":"2026-09-15T06:36:29.701Z","isFirstParty":true}