{"uid":"cap_u_WGb4VuUmHo7GsH5NSgM","slug":"citiview-deepseek-v4-flash-chat-completions-1498a64e","name":"Citiview DeepSeek V4 Flash Chat Completions","description":"OpenAI-compatible chat completions on DeepSeek V4 Flash, fast and inexpensive frontier model with tool calling and a 1M-token context. Set your OpenAI SDK base URL to https://agents.citiviewgroup.com/v1/deepseek and pay per token with x402 instead of an API key: $0.88 per million input and $2.64 per million output tokens, minimum $0.002 a call, at most $0.0740. The 402 quotes your request's maximum; \"upto\" payers are charged only the tokens used. Same request/response shape a","url":"https://agents.citiviewgroup.com/v1/deepseek/chat/completions?utm_source=zero.xyz","method":"GET","headers":{},"bodySchema":{"type":"object","$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":"deepseek-v4-flash","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":"0.007425","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":"$0.007425/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.007425","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.007425","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_bJEnpVjdS3taU5Jbjh3YH","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.007425","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 powered by DeepSeek V4 Flash with 1M-token context, tool calling, and pay-per-token x402 micropayments","exampleAgentPrompt":"Ask DeepSeek V4 Flash to explain the key differences between transformer and state-space models in plain English — keep it under 300 tokens and use a neutral tone.","exampleUseCases":[{"title":"Long-document summarization with LLM","prompt":"I have a 200,000-word legal contract I need summarized. Use the DeepSeek model to read the whole thing and give me a 500-word executive summary highlighting risks and obligations."},{"title":"Agentic reasoning with tool calling","prompt":"I'm building an agent that needs to decide which data source to query next. Send my reasoning prompt to DeepSeek V4 Flash with tool-calling enabled so it can pick the right action from my provided tool list."},{"title":"Cheap high-volume text classification","prompt":"I need to classify 10,000 customer support messages as billing, technical, or general — can you run each one through DeepSeek V4 Flash? I want to minimize cost per call since it's pay-per-token."}],"resultDescription":"Returns an OpenAI-compatible JSON object with a choices array containing the assistant's message content, finish reason, model name, completion ID, and a usage object showing prompt_tokens, completion_tokens, and total_tokens consumed.","failureModes":["Insufficient x402 payment balance returns 402 Payment Required","Prompt exceeds 1M token context window returns a context-length error","Invalid or missing prompt parameter returns 400 Bad Request","Model temporarily unavailable returns 503","Malformed request body returns validation error"],"whenToPreferThis":"Choose this endpoint when you need OpenAI-compatible chat completions without account signup, want to pay per call via x402 micropayments (charged only for tokens actually used), need a 1M-token context window for very long documents, or want inexpensive frontier-model inference at $0.88/M input tokens — significantly cheaper than comparable OpenAI or Anthropic endpoints.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-15T06:30:21.867Z","isFirstParty":false,"canonicalSlug":"citiview-deepseek-v4-flash-chat-completions-1498a64e"}