{"uid":"cap_StHg_DFz3H2zKVLy2Kpyw","slug":"jatevo-ai-38a1cd9f","name":"Jatevo GPT-OSS 120B LLM Inference","description":"Hosted GPT-OSS 120B open-source language model via Jatevo for chat and completion inference (JSON POST with optional streaming); paid access via USDC on EIP-8453.","url":"https://jatevo.ai/api/x402/llm/gpt-oss","method":"POST","headers":{},"bodySchema":{"type":"object","required":["stream","messages"],"properties":{"stream":{"type":"boolean"},"messages":{"type":"array","items":{"type":"object","required":["role","content"],"properties":{"role":{"type":"string"},"content":{"type":"string"}}}}}},"responseSchema":null,"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.01","displayCostAsset":"USDC","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"unknown","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":"$0.01/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.01","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.01","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_aC3V-ZrFnaQ9YX_TDqJhN","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.01","costPer":"request","priority":0,"asset":null,"unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Runs chat and completion inference on a hosted 120B open-source language model with optional streaming, paid per-call in USDC.","exampleAgentPrompt":"Send a message to the GPT-OSS 120B model on Jatevo asking: 'Explain the concept of transformer attention in simple terms' — stream the response back as it's generated.","exampleUseCases":null,"resultDescription":"Returns a chat completion or streamed token sequence from the GPT-OSS 120B open-source language model, containing the assistant's generated response to the provided message history.","failureModes":["Missing required 'messages' or 'stream' fields returns 400 Bad Request","Insufficient USDC balance or failed x402 payment returns 402 Payment Required","Malformed message objects (missing role or content) cause validation errors","Model overload or upstream inference failure may return 503 Service Unavailable","Invalid boolean for 'stream' field causes request rejection"],"whenToPreferThis":"Choose this endpoint when you need inference from a large (120B) open-source language model with pay-per-call USDC pricing and no subscription commitment, especially when streaming responses are desirable and you want an alternative to proprietary LLMs.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-14T06:37:35.413Z","isFirstParty":false}