{"uid":"cap_JVn7O-4Gs75V6Ci9m-oMZ","slug":"agent-hub-gpt-oss-20b-chat-completions-d21f6a04","name":"Agent Hub GPT-OSS-20B Chat Completions","description":"OpenAI-compatible chat completions on OpenAI gpt-oss-20b open-weight reasoning model with tool calling. Set your OpenAI SDK base URL to https://agents.torbrooknews.com/v1/gpt-oss-20b and pay $0.003 per request with x402 instead of an API key. Same request/response shape as OpenAI (tool calling, reasoning, streaming supported), up to 4096 output tokens. Also callable as GET with the same fields as query parameters.","url":"https://agents.torbrooknews.com/v1/gpt-oss-20b/chat/completions?utm_source=zero.xyz","method":"GET","headers":{},"bodySchema":{"type":"object","$schema":"https://json-schema.org/draft/2020-12/schema","required":["input"],"properties":{"input":{"type":"object","required":["type","method"],"properties":{"type":{"type":"string","const":"http"},"method":{"enum":["GET"],"type":"string"},"queryParams":{"type":"object","required":["prompt"],"properties":{"prompt":{"type":"string","description":"User message"},"system":{"type":"string","description":"Optional system message"},"max_tokens":{"type":"integer"},"temperature":{"type":"number"}}}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object"}}}}},"responseSchema":null,"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.003","displayCostAsset":"USDC","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"probe","requiresHandshake":false,"reviewCount":0,"rating":{"score":"0.00","successRate":"0.00","reviews":0,"stars":null,"state":"unrated"},"availabilityStatus":"unknown","priceObserved":null,"sessionDeposit":null,"pricing":{"kind":"static","summary":"$0.003/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.003","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.003","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_88eNzwHT5NG_-KCMS8hJE","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.003","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Runs OpenAI-compatible chat completions with tool calling and reasoning on the gpt-oss-20b open-weight model, payable per-request via x402 micropayments instead of an API key.","exampleAgentPrompt":"Ask gpt-oss-20b: 'Explain the difference between supervised and unsupervised learning in three sentences' — use up to 300 tokens and keep the temperature at 0.7.","exampleUseCases":[{"title":"Keyless LLM for agentic pipeline","prompt":"I need to call a reasoning-capable LLM in my agent without setting up an OpenAI API key — send the prompt 'Summarize the pros and cons of microservices architecture' to gpt-oss-20b with a system message saying 'You are a senior software architect' and max 512 tokens."},{"title":"Tool-calling step in automation","prompt":"Use the gpt-oss-20b model to decide which tool to call next given this context: 'The user wants to check the weather in Paris tomorrow' — enable tool calling and keep temperature at 0."},{"title":"Quick reasoning answer on demand","prompt":"Ask the open-weight reasoning model: 'A train leaves at 9am going 80mph and another at 10am going 100mph from the same station — when does the second train catch up?' and give me the step-by-step answer, up to 256 tokens."}],"resultDescription":"Returns an OpenAI-compatible chat completion object containing the assistant's message, optional tool call specifications, reasoning traces, and token usage counts — identical in shape to the OpenAI API response, up to 4096 output tokens.","failureModes":["Payment not included or insufficient USDC (402 Payment Required)","Prompt parameter missing (400 Bad Request)","Model context length exceeded if prompt is very long","Streaming not supported on GET method variant","Rate limiting or capacity errors from underlying inference provider","Malformed query parameters returning 422 validation error"],"whenToPreferThis":"Choose this endpoint when you need an OpenAI-compatible LLM with tool calling and reasoning but want to avoid managing API keys or subscriptions — paying $0.003 USDC per request via x402. Ideal for agentic pipelines that need per-call micropayment billing, or for accessing gpt-oss-20b specifically.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-13T12:45:37.388Z","isFirstParty":false,"canonicalSlug":"agent-hub-gpt-oss-20b-chat-completions-d21f6a04"}