{"uid":"cap_spuIVlEu4Ok7y9Pph5MLh","slug":"agentrxi-deepseek-chat-completion-0abe53f8","name":"AgentRXI DeepSeek Chat Completion","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://agentrxi.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 $0.0740. The 402 quotes your request's maximum; \"upto\" payers are charged only the tokens used. Same request/response shape as OpenAI (to","url":"https://agentrxi.com/v1/deepseek/chat/completions?utm_source=zero.xyz","method":"GET","headers":{},"bodySchema":{"type":"object","$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_Sjkad_rQVHRJd22VzEXww","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":"Pay-per-call LLM chat completion using DeepSeek V4 Flash, billed in USDC per call via x402, with no API key or signup required.","exampleAgentPrompt":"Ask DeepSeek V4 Flash to summarize this paragraph for me in three bullet points: 'The Amazon rainforest is the world's largest tropical rainforest, covering over 5.5 million square kilometres...' — keep the response under 200 tokens.","exampleUseCases":[{"title":"Quick translation for agent pipeline","prompt":"Translate this sentence into French using DeepSeek Flash, keep it under 50 tokens: 'The payment was processed successfully.'"},{"title":"Structured data extraction from text","prompt":"Use DeepSeek to extract the company name, date, and total amount from this invoice text and return JSON: 'Acme Corp, Invoice #1042, Due March 15 2025, Total: $4,200.'"},{"title":"On-the-fly code explanation","prompt":"Have DeepSeek V4 Flash explain what this Python function does in plain English, max 150 tokens: 'def fib(n): return n if n <= 1 else fib(n-1)+fib(n-2)'"}],"resultDescription":"Returns an OpenAI-compatible chat completion JSON object containing the assistant's reply text, finish reason (e.g. 'stop'), model name ('deepseek-v4-flash'), and token usage breakdown (prompt, completion, total tokens).","failureModes":["Missing required 'prompt' query parameter returns a 400 error","Insufficient USDC balance or failed x402 payment returns a 402 Payment Required","Exceeding max_tokens limit may truncate the response with finish_reason 'length'","Invalid temperature value (outside 0–2) may cause a 422 validation error","Model unavailability or upstream DeepSeek outage returns a 503 or 500 error"],"whenToPreferThis":"Choose this endpoint when you need fast, cheap LLM inference from DeepSeek V4 Flash without committing to a subscription or API key — ideal for agent pipelines that want micropayment-per-call billing in USDC via x402. Prefer this over Llama 3.3 70B on AgentRXI when speed and cost matter more than reasoning depth, and over OpenAI-based endpoints when you want to avoid API key management entirely.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-15T06:39:22.902Z","isFirstParty":false,"canonicalSlug":"agentrxi-deepseek-chat-completion-0abe53f8"}