{"uid":"cap_6r6N0uxd9I0opWfMjcwnU","slug":"kimi-k3-1-pro-chat-telnyx-inference-72b19c83","name":"Kimi K3.1 Pro Chat (Telnyx Inference)","description":"Featured model. Chat completions via Telnyx Inference (moonshotai/Kimi-K3.1-Pro). OpenAI-compatible. Up to $0.05106 USDC per call, quoted to your request (input + max_tokens at list rates, no markup).","url":"https://x402.telnyx.com/v1/chat/completions/_t/kimi-k3.1-pro?utm_source=zero.xyz","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"n":{"type":"integer","const":1,"description":"Fixed to one completion per paid call."},"model":{"type":"string","const":"moonshotai/Kimi-K3.1-Pro","description":"Model identifier; fixed to moonshotai/Kimi-K3.1-Pro on this route."},"tools":{"type":"array","items":{"type":"object"},"maxItems":16},"messages":{"type":"array","items":{"type":"object","required":["role"],"properties":{"role":{"enum":["system","user","assistant","tool"],"type":"string"},"content":{"type":["string","null"],"maxLength":12000,"description":"Required, except null/omitted on assistant messages that carry tool_calls."},"reasoning":{"type":"string","maxLength":12000,"description":"Assistant messages only: the reasoning returned with that turn, sent back on multi-turn and tool-call loops. Counts toward the message character limits."},"reasoning_content":{"type":"string","maxLength":12000,"description":"Assistant messages only: alternative name for reasoning (as returned by GLM and gpt-oss)."}}},"maxItems":32,"description":"OpenAI-style chat messages."},"max_tokens":{"type":"integer","maximum":2048,"minimum":1},"temperature":{"type":"number","maximum":2,"minimum":0}}},"responseSchema":null,"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.05106","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":"$0.05106/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.05106","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.05106","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_dkiAohcfCVF0I6FafA9_w","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.05106","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Runs chat completions using the MoonshotAI Kimi K3.1 Pro model via Telnyx's OpenAI-compatible inference endpoint, billed per call via x402.","exampleAgentPrompt":"Using the Kimi K3.1 Pro model, respond to this user message: 'Explain the geopolitical implications of the Belt and Road Initiative in Southeast Asia' — keep the reply under 800 tokens and use a neutral, analytical tone (temperature 0.3).","exampleUseCases":[{"title":"Complex research question answering","prompt":"Ask Kimi K3.1 Pro to give me a thorough, well-structured explanation of how transformer attention mechanisms work, including the math behind scaled dot-product attention — keep it under 1500 tokens."},{"title":"Agentic tool-calling workflow","prompt":"I need Kimi K3.1 Pro to process this conversation history and decide which of my three tools to call next — here are the tool schemas and the last 10 messages from the session."},{"title":"Creative long-form content drafting","prompt":"Have Kimi K3.1 Pro write a detailed 3-section blog post outline on the future of edge computing, with a system prompt that says 'you are a senior technology analyst', temperature at 0.8, and max 2000 tokens."}],"resultDescription":"Returns an OpenAI-compatible chat completion response object containing the generated assistant message text, finish reason, token usage counts, and any tool call invocations requested by the model.","failureModes":["Payment failure or insufficient USDC balance — 402 Payment Required","Message array exceeds 32-item limit — 400 Bad Request","Individual message content exceeds 12,000 character limit — 400 validation error","max_tokens out of range (must be 1–2048) — 400 Bad Request","Model overloaded or unavailable — 503 Service Unavailable","Malformed tool definition in tools array — 400 Bad Request"],"whenToPreferThis":"Choose this endpoint when you need a high-capability frontier model (Kimi K3.1 Pro) for complex reasoning, nuanced instruction following, or multi-turn agentic workflows, and you want per-call x402 micropayment billing without a subscription. Prefer it over smaller siblings (Llama 3.1 8B, Gemma 4 26B) for tasks requiring deeper reasoning, and over the Thinking variant when you want direct answers without extended chain-of-thought overhead.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-11-19T06:35:59.506Z","isFirstParty":false,"canonicalSlug":"kimi-k3-1-pro-chat-telnyx-inference-72b19c83"}