{"uid":"cap_ueEKhZNOit6zvnEgKsLaH","slug":"citiview-agent-market-meta-llama-3-3-70b-chat-completions-6e9f8959","name":"Citiview Agent Market – Meta Llama 3.3 70B Chat Completions","description":"Citiview Agent Market: 211 pay-per-call tools for AI agents. Cited answers, deep research, agent memory, file hosting, webhooks, schedules, sanctions and link safety checks, OpenAI-compatible LLMs on 11 models, web search, scraping, PDF, OCR, speech, Solana and EVM token risk, DeFi, prediction odds, SEC data. Pay per call in USDC with x402. No key, no signup.","url":"https://agents.citiviewgroup.com/v1/large/chat/completions?utm_source=zero.xyz","method":"GET","headers":{},"bodySchema":{"type":"object","$schema":"https://json-schema.org/draft/2020-12/schema","required":["input"],"properties":{"input":{"type":"object","required":["type","method"],"properties":{"type":{"type":"string","const":"http"},"method":{"enum":["GET"],"type":"string"},"queryParams":{"type":"object","required":["prompt"],"properties":{"prompt":{"type":"string","description":"User message"},"system":{"type":"string","description":"Optional system message"},"max_tokens":{"type":"integer"},"temperature":{"type":"number"}}}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object"}}}}},"responseSchema":{"type":"json","example":{"id":"chatcmpl-...","model":"llama-3.3-70b","usage":{"total_tokens":18,"prompt_tokens":14,"completion_tokens":4},"object":"chat.completion","choices":[{"index":0,"message":{"role":"assistant","content":"Bonjour !"},"finish_reason":"stop"}]}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.008939","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":"$0.008939/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.008939","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.008939","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_5QocQDTYDmIOGOpia-EDw","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.008939","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"OpenAI-compatible chat completions endpoint powered by Meta Llama 3.3 70B, supporting tool calling and streaming, accessible via HTTP GET or POST with x402 micropayment pricing.","exampleAgentPrompt":"Ask Llama 3.3 70B: 'What are the pros and cons of using Rust over Go for a high-concurrency web server?' — use up to 512 output tokens and a temperature of 0.7.","exampleUseCases":[{"title":"Agentic reasoning with tool calls","prompt":"I need you to reason through this multi-step task using Llama 3.3 70B and call the appropriate tools: first check today's weather in Berlin, then draft a short travel advisory based on the forecast. Use tool calling and keep your response under 1024 tokens."},{"title":"General knowledge Q&A for a chatbot","prompt":"Send this user question to the Llama 3.3 70B model with a system prompt that says 'You are a helpful customer support agent for a SaaS company' and get back an answer: 'How do I reset my two-factor authentication?'"},{"title":"Creative writing with temperature control","prompt":"Generate a short, imaginative story opening (about 300 words) using Llama 3.3 70B — set temperature to 0.9 and use the prompt 'A lighthouse keeper discovers a message in a bottle written in a language that shouldn't exist.'"}],"resultDescription":"Returns an OpenAI-compatible chat completion object containing the generated message content, finish reason (e.g. 'stop' or 'tool_calls'), tool call objects if triggered, and token usage statistics (prompt tokens, completion tokens, total tokens). Up to 2048 output tokens per response.","failureModes":["Payment not included or rejected — 402 Payment Required with x402 challenge","Prompt exceeds model context window — truncation or 400 error","max_tokens set above 2048 — capped or error response","Invalid or missing prompt parameter — 400 Bad Request","Model temporarily unavailable — 503 Service Unavailable","Malformed tool definition — tool calling may silently fail or return error"],"whenToPreferThis":"Choose this endpoint when you need a capable, general-purpose 70B-scale LLM with tool calling support and want to pay per request via x402 micropayment rather than managing an API key subscription. Ideal for agents that need strong reasoning, instruction following, or multi-step tool use without committing to OpenAI or Anthropic pricing. Prefer the sibling Qwen 2.5 Coder endpoint for code-heavy tasks, or the Qwen3 30B MoE endpoint for thinking/reasoning-heavy workflows.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-14T06:48:36.331Z","isFirstParty":false,"canonicalSlug":"citiview-agent-market-meta-llama-3-3-70b-chat-completions-6e9f8959"}