{"uid":"cap_KNL4sY43vOszh7NGkc1ku","slug":"model-access-gateway-llama-3-3-70b-chat-completions-2eddece7","name":"Model Access Gateway – Llama 3.3 70B Chat Completions","description":"LLM inference API: OpenAI-compatible chat completions for 136 AI models (Claude, GPT, Gemini, Grok, DeepSeek, Qwen, Kimi, GLM), paid per call in USDC on Base with x402. No account, no API key, automatic refund if the model fails.","url":"https://agent402-arb.rosariovitale0096.workers.dev/llm/llama-3.3-70b?utm_source=zero.xyz","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"model":{"type":"string","description":"Optional: fixed by the route (meta-llama/llama-3.3-70b)"},"tools":{"type":"array"},"stream":{"type":"boolean","description":"true: server-sent events after payment"},"messages":{"type":"array","items":{"type":"object","required":["role"],"properties":{"role":{"enum":["system","user","assistant","tool","developer"],"type":"string"},"content":{"type":["string","array","null"]}}},"minItems":1},"max_tokens":{"type":"integer","maximum":16384,"minimum":1,"description":"Optional, default 4096"},"temperature":{"type":"number","maximum":2,"minimum":0},"response_format":{"type":"object"}}},"responseSchema":{"type":"json","example":{"id":"chatcmpl-7f3c2a91","model":"meta-llama/llama-3.3-70b","usage":{"total_tokens":10,"prompt_tokens":9,"completion_tokens":1},"object":"chat.completion","choices":[{"index":0,"message":{"role":"assistant","content":"OK"},"finish_reason":"stop"}],"created":1791979200}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.001","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":"$0.001/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.001","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.001","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_-Q90Orv8fyJ2q7pD9Zedv","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Serves OpenAI-compatible chat completion responses from Meta's Llama 3.3 70B model, billed per request in USDC via x402 with no account or API key required.","exampleAgentPrompt":"Ask the Llama 3.3 70B model this question and pay for it per-request in USDC: 'What are three creative names for a sustainable coffee brand?' — use the agent402 gateway so I don't need an API key.","exampleUseCases":[{"title":"Keyless LLM inference for autonomous agent","prompt":"I'm building an AI agent that needs to call a large language model on demand without managing API keys or subscriptions — run this prompt through Llama 3.3 70B via the agent402 pay-per-request gateway: 'Summarize the following meeting notes in 3 bullet points: [notes text].'"},{"title":"Per-request crypto-paid text generation","prompt":"Generate a short product description for my new hiking boot using Llama 3.3 70B, paying just for this one call in USDC — I don't want a monthly plan, just charge me for the single request."},{"title":"OpenAI-compatible swap for Llama backend","prompt":"I want to swap out my OpenAI calls for Llama 3.3 70B on a per-use basis — send this chat message to the agent402 Llama endpoint and give me the assistant's reply: system prompt is 'You are a helpful coding assistant', user message is 'Explain async/await in Python in one paragraph.'"}],"resultDescription":"Returns a JSON object in the OpenAI chat.completion format containing: a completion ID, the model name, an array of choices each with an assistant message and finish_reason, and a usage object reporting prompt_tokens, completion_tokens, and total_tokens.","failureModes":["Payment not included or insufficient USDC — returns HTTP 402 Payment Required","Malformed request body missing required fields — returns 400 Bad Request","Model temporarily unavailable on the gateway — returns 503 or timeout","Rate limit exceeded on the underlying worker — returns 429 Too Many Requests","Invalid or unsupported chat message format — may return 400 or garbled output"],"whenToPreferThis":"Choose this endpoint when you need OpenAI-compatible Llama 3.3 70B inference with no account signup, no API key management, and true pay-per-request billing in USDC via x402. Ideal for autonomous agents that need to spawn LLM calls dynamically, for developers prototyping without committing to a subscription, or for crypto-native workflows where on-chain micropayments are preferred over traditional billing. Prefer it over OpenAI or Anthropic endpoints when you specifically want an open-weight model or when cost-per-call transparency in stablecoin is important.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-15T12:34:28.135Z","isFirstParty":false,"canonicalSlug":"model-access-gateway-llama-3-3-70b-chat-completions-2eddece7"}