{"uid":"cap_LalgWOTF8gV2AsHqPhgmc","slug":"deepseek-via-locus-x402-1af7e227","name":"DeepSeek via Locus x402","description":"Frontier AI models — DeepSeek-V3 for fast chat and code, DeepSeek-R1 for deep chain-of-thought reasoning. OpenAI-compatible API format. Among the most capable and cost-efficient models available.","url":"https://deepseek.x402.paywithlocus.com/deepseek/chat?utm_source=zero.xyz","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"stop":{"type":"string"},"model":{"type":"string"},"top_p":{"type":"number"},"stream":{"type":"boolean"},"messages":{"type":"array","items":{"type":"object","required":["role"],"properties":{"name":{"type":"string"},"role":{"type":"string"},"content":{"anyOf":[{"type":"string"},{"type":"array","items":{"type":"object","required":["type"],"properties":{"text":{"type":"string"},"type":{"type":"string"},"image_url":{"type":"object","required":["url"],"properties":{"url":{"type":"string"}},"additionalProperties":true}},"additionalProperties":true}},{"type":"null"}]},"tool_calls":{"type":"array","items":{"type":"object","additionalProperties":true}},"tool_call_id":{"type":"string"}},"additionalProperties":true}},"max_tokens":{"type":"number"},"temperature":{"type":"number"}}},"responseSchema":{"type":"json","example":{"data":{},"payment":{"scheme":"exact","settledUsdc":"0.001000","authorizedMaxUsdc":"0.001000"},"request":{"id":"00000000-0000-4000-8000-000000000000","statusUrl":"/requests/00000000-0000-4000-8000-000000000000"},"success":true}},"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_G4uKNoQxGBHrYu4jNPgsV","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":"Calls DeepSeek frontier AI models (V3 for fast chat/code, R1 for deep reasoning) via an OpenAI-compatible, pay-per-call x402 API","exampleAgentPrompt":"Use DeepSeek R1 with deep chain-of-thought reasoning to figure out the most efficient algorithm for finding all prime numbers up to 1 million — give me up to 2000 tokens in the response.","exampleUseCases":[{"title":"Code debugging with fast AI","prompt":"I have a Python function that's supposed to merge two sorted lists but it's returning incorrect results — can you use DeepSeek V3 to find the bug and rewrite it correctly? Keep the answer under 1000 tokens."},{"title":"Step-by-step math reasoning","prompt":"Use DeepSeek R1 to solve this probability problem step by step: if I flip a fair coin 10 times, what's the probability of getting at least 7 heads? Show all reasoning, up to 1500 tokens."},{"title":"Automated text summarization pipeline","prompt":"Summarize this 3-paragraph legal clause into plain English using DeepSeek V3 — I need a concise answer, so cap it at 500 tokens and keep the temperature low at 0.2 for consistency."}],"resultDescription":"A JSON response containing a chat completion object nested under 'data', with the AI-generated text in the standard OpenAI-compatible format, plus a 'payment' object confirming 0.001 USDC was settled, a 'request' object with a UUID and status URL for tracking, and a 'success' boolean.","failureModes":["Insufficient USDC balance or x402 payment authorization failure — payment rejected before inference runs","max_tokens not provided — required to bound metered authorization, request will be rejected","Streaming requested (stream:true) — not supported via public x402, will fail or be silently ignored","Invalid model name specified — only deepseek-v4-flash and deepseek-v4-pro are valid metered options","Messages array malformed or empty — model returns error without valid conversation input","Rate limits or upstream DeepSeek API downtime causing 5xx errors"],"whenToPreferThis":"Choose this endpoint when you need a capable, cost-efficient frontier LLM accessible via a simple pay-per-call micropayment (no subscription or API key management) — especially when you want DeepSeek's specific strengths: fast chat and code generation with V3, or deep multi-step chain-of-thought reasoning with R1. Prefer it over OpenAI or Anthropic endpoints when cost efficiency matters most or when DeepSeek's reasoning style is specifically desired. Ideal for agents that need to dynamically pay per inference using x402/USDC without pre-provisioning API credentials.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-11T00:39:41.452Z","isFirstParty":false,"canonicalSlug":"deepseek-via-locus-x402-1af7e227"}