{"uid":"cap_wTR8ks-Fl0utItqXSANI0","slug":"agent-toolbox-gpt-oss-120b-chat-completion-00a02ffc","name":"Agent Toolbox: GPT-OSS-120B Chat Completion","description":"OpenAI-compatible chat completion with gpt-oss-120b (OpenAI's open-weight reasoning model): set the base URL to /v1/llm/gpt-oss-120b in any OpenAI SDK. Up to 32,000 characters in and 2,048 tokens out per call, a fixed price per call, no streaming.","url":"https://agent-toolbox.zafermemon87.workers.dev/mcp?utm_source=zero.xyz#chat_gpt_oss_120b#chat_gpt_oss_120b","method":"POST","headers":{},"bodySchema":null,"responseSchema":null,"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.005","displayCostAsset":"USDC","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"registry","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":"$0.005/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.005","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.005","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_21jTLgTDqQwj8VvQM-9Xk","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.005","costPer":"request","priority":0,"asset":null,"unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Runs a single non-streaming OpenAI-compatible chat completion using OpenAI's 120B open-weight reasoning model (gpt-oss-120b), returning up to 2,048 tokens per call.","exampleAgentPrompt":"Ask the 120B open-weight reasoning model: 'Given the following legal contract clause, identify any ambiguous terms and suggest clearer alternatives' — use up to 32,000 characters of input and return the full analysis.","exampleUseCases":[{"title":"Complex multi-step reasoning task","prompt":"I need to analyze this 10-page business strategy document and identify logical inconsistencies, risks, and missing assumptions — use the most powerful reasoning model you have access to."},{"title":"Code architecture review","prompt":"Take this 500-line Python codebase and give me a thorough architectural review: identify anti-patterns, suggest refactors, and flag any security issues. Use a strong reasoning LLM for this."},{"title":"Agentic sub-task delegation","prompt":"I'm building an agent pipeline and need to delegate the hardest reasoning sub-tasks to a capable LLM — call gpt-oss-120b with this prompt about causal inference in clinical trial data and return the response."}],"resultDescription":"Returns an OpenAI-compatible chat completion response object containing the assistant's generated message text, finish reason, and token usage statistics (prompt tokens, completion tokens, total tokens). Maximum output is 2,048 tokens per call. Response is not streamed.","failureModes":["Input exceeds 32,000 character limit — request rejected","Output truncated at 2,048 tokens if generation is longer","Payment failure (x402 protocol) if USDC balance is insufficient","Model unavailability or Cloudflare Worker timeout","Malformed messages array causes 400-level error","Rate limiting if too many concurrent requests"],"whenToPreferThis":"Choose this endpoint when you need a high-capability, large-parameter reasoning model (120B) via a drop-in OpenAI SDK-compatible interface at a fixed per-call price of $0.005 USDC, without managing API keys or infrastructure. Prefer over smaller models (e.g. Qwen3 30B sibling) when task complexity demands deep reasoning, multi-step analysis, or nuanced judgment. Prefer over hosted OpenAI endpoints when you want open-weight model transparency or pay-per-call billing without a subscription.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-29T12:36:12.046Z","isFirstParty":false,"canonicalSlug":"agent-toolbox-gpt-oss-120b-chat-completion-00a02ffc"}