{"uid":"cap_PAHICLSjRUbNkiVn-ntV8","slug":"aispace-chat-completions-venice-ai-ec2dcdb3","name":"AiSpace Chat Completions (Venice.ai)","description":"OpenAI-compatible chat on 100+ Venice models via x402 USDC (Base). Model from GET /api/v1/models?type=text; personas via /characters. Thinking models: empty content + reasoning_content is success; use venice_parameters.disable_thinking for plain text.","url":"https://x402.aispace.bot/api/v1/chat/completions","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"model":{"type":"string","example":"gemini-3-6-flash","description":"Venice text model id. List available ids at GET /api/v1/models?type=text (e.g. gemini-3-6-flash, zai-org-glm-5)."},"stream":{"type":"boolean","description":"If true, stream tokens via SSE. Default false."},"messages":{"type":"array","items":{"type":"object"},"description":"OpenAI chat messages: array of {role:'system'|'user'|'assistant', content:string}. On multi-turn tool use with reasoning models, round-trip assistant.reasoning_details verbatim."},"max_tokens":{"type":"integer","description":"Optional. Buyer-chosen completion cap — this gateway does not set a default. Omit unless you want to bound output. On thinking models a small value can exhaust on reasoning_content and leave content empty (finish_reason=length)."},"venice_parameters":{"type":"object","properties":{"disable_thinking":{"type":"boolean","description":"Skip chain-of-thought on reasoning models; forces a normal content reply."},"strip_thinking_response":{"type":"boolean","description":"Run thinking server-side but hide it from the client."}}},"venice_parameters.disable_thinking":{"type":"string","description":"Set true to skip chain-of-thought on reasoning models (forces a normal content reply)."},"choices[].message.reasoning_content":{"type":"string","description":"On thinking models, chain-of-thought text. content may be empty if max_tokens is spent on thinking first (finish_reason=length). Check this field as well as content."},"choices[].message.reasoning_details":{"type":"string","description":"Structured thought signatures (Claude Opus / GPT-5.4 Pro etc). Pass back unchanged on the next turn."},"venice_parameters.strip_thinking_response":{"type":"string","description":"If true, hide thinking from the client while still running it server-side."}}},"responseSchema":{"type":"json","example":{"id":"gcp-1788177689318","cost":{"usd":0,"diem":0},"model":"gemini-3-6-flash","usage":{"total_tokens":1780,"prompt_tokens":1780,"completion_tokens":0},"object":"chat.completion","choices":[{"index":0,"message":{"role":"assistant","content":"","reasoning_content":null},"finish_reason":"length"}],"created":1788177689,"venice_parameters":{"enable_e2ee":true,"enable_x_search":false,"disable_thinking":false,"enable_web_search":"off","enable_web_scraping":false,"enable_web_citations":false,"web_search_citations":[],"strip_thinking_response":false,"include_venice_system_prompt":true,"include_search_results_in_stream":false,"return_search_results_as_documents":false}}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.01","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":"$0.01/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.01","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.01","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_4ZTIFx1cJnIRUnQKcIG7P","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.01","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Sends a chat completion request to AiSpace's privacy-focused AI chat API powered by Venice.ai, returning an AI-generated response.","exampleAgentPrompt":"Using AiSpace's Venice-powered privacy AI, send these messages to the qwen3-5-9b model and get a completion: system message 'You are a helpful assistant' and user message 'Explain quantum entanglement in simple terms.'","exampleUseCases":[{"title":"Private AI research assistant","prompt":"I need to ask a sensitive question about my medical symptoms without it being stored anywhere — use AiSpace's privacy AI with the qwen3-5-9b model to answer: 'What are common causes of persistent lower back pain in adults over 40?'"},{"title":"Code generation with privacy","prompt":"Use AiSpace's Venice-powered AI to help me write a Python function that parses a CSV file and returns rows where a column value exceeds a threshold — use qwen3-5-9b and keep it private."},{"title":"Creative writing collaboration","prompt":"I want to brainstorm plot ideas for a sci-fi short story using AiSpace's AI — send the qwen3-5-9b model a message asking for 5 unique story premises set on a generation starship."}],"resultDescription":"Returns a JSON object confirming success (ok: true) along with the AI-generated chat completion text from the selected model. The response follows a standard OpenAI-compatible chat completions format.","failureModes":["Payment not processed — x402 payment of $0.001 USDC required before response","Missing required 'messages' query parameter returns validation error","Missing required 'model' parameter results in bad request","Invalid model name returns error or fallback behavior","Streaming flag set to true may require SSE handling","Schema quirk: parameters appear in queryParams rather than request body, which may cause integration confusion","Venice.ai backend downtime causes 503 or timeout"],"whenToPreferThis":"Choose this endpoint when privacy is a primary concern and you need AI chat completions without server-side data retention, powered by Venice.ai's uncensored models. Prefer it over mainstream OpenAI or Anthropic APIs when you want a pay-per-call micropayment model (via x402/USDC) and compatibility with Venice's model lineup including Qwen variants.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-15T00:42:39.649Z","isFirstParty":false}