{"uid":"cap_md9Fv_sbSXlKr2fTUJgGJ","slug":"telnyx-x402-gateway-llama-3-3-70b-chat-completions-c52169b8","name":"Telnyx x402 Gateway – Llama 3.3 70B Chat Completions","description":"Pay USDC per request for Telnyx Inference and Audio (text-to-speech, speech-to-text) through x402.","url":"https://x402.telnyx.com/v1/chat/completions/_t/llama-3.3-70b?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":"meta-llama/Llama-3.3-70B-Instruct","description":"Model identifier; fixed to meta-llama/Llama-3.3-70B-Instruct on this route."},"tools":{"type":"array","items":{"type":"object"},"maxItems":16},"messages":{"type":"array","items":{"type":"object","required":["role","content"],"properties":{"role":{"enum":["system","user","assistant","tool"],"type":"string"},"content":{"type":"string","maxLength":8000}}},"maxItems":32,"description":"OpenAI-style chat messages."},"max_tokens":{"type":"integer","maximum":1024,"minimum":1},"temperature":{"type":"number","maximum":2,"minimum":0}}},"responseSchema":{"type":"json","example":{"id":"chatcmpl-xxx","usage":{"total_tokens":16,"prompt_tokens":12,"completion_tokens":4},"object":"chat.completion","choices":[{"index":0,"message":{"role":"assistant","content":"Hello!"},"finish_reason":"stop"}]}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.007016","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":"$0.007016/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.007016","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.007016","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_CERVFYdccFpS9nkFFewOE","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.007016","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 against Meta's Llama-3.3-70B-Instruct model, billed per-request in USDC via the x402 payment protocol.","exampleAgentPrompt":"Ask Llama 3.3 70B to draft a concise three-paragraph executive summary of the following meeting notes, keeping the tone professional — pay for it per-request with USDC: [paste notes here].","exampleUseCases":[{"title":"Pay-per-call AI coding assistant","prompt":"Use Llama 3.3 70B to review this Python function and suggest improvements — I want to pay just for this one call in USDC rather than sign up for a subscription: [paste code here]."},{"title":"Tool-calling agent reasoning step","prompt":"Send the following conversation thread to Llama 3.3 70B with the search_web tool attached and let it decide whether to call the tool or answer directly — bill it to my USDC wallet: [paste messages]."},{"title":"On-demand customer email drafting","prompt":"Have Llama 3.3 70B write a polite, empathetic reply to this customer complaint email, keeping the response under 150 words — run it as a one-off USDC-billed inference: [paste email]."}],"resultDescription":"Returns an OpenAI-compatible chat.completion JSON object containing the assistant's reply message, finish reason (e.g. 'stop'), and token usage breakdown (prompt, completion, total tokens). The completion ID and object type are also included for logging.","failureModes":["Payment not attached or insufficient USDC balance — 402 Payment Required","messages array exceeds 32 items or content exceeds 8000 characters — 400 validation error","max_tokens out of range [1–1024] — 400 validation error","Model identifier mismatch (must be meta-llama/Llama-3.3-70B-Instruct) — 400 error","Telnyx inference backend timeout or overload — 503 or 504","Malformed message role (must be system/user/assistant/tool) — 400 validation error"],"whenToPreferThis":"Choose this endpoint when you need a capable 70B-parameter open-weight LLM (Llama 3.3) with OpenAI-compatible chat format, want pay-per-request billing in USDC without a monthly subscription, and are operating in an agentic or automated context where x402 micropayment headers can be attached. Prefer it over subscription-based LLM APIs for sporadic or burstable workloads, or when crypto-native payment rails are required. Also suitable when you need tool-calling support (up to 16 tools) at a predictable per-call cost.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-10T12:37:14.658Z","isFirstParty":false,"canonicalSlug":"telnyx-x402-gateway-llama-3-3-70b-chat-completions-c52169b8"}