{"uid":"cap__OAbOIbTsqPEUSv1LDjZ0","slug":"citiview-agent-market-deepseek-v4-pro-chat-completions-7d63d580","name":"Citiview Agent Market – DeepSeek V4 Pro Chat Completions","description":"OpenAI-compatible chat completions on DeepSeek V4 Pro, a top open frontier model with reasoning, tool calling and a 1M-token context. Set your OpenAI SDK base URL to https://agents.citiviewgroup.com/v1/deepseek-pro and pay per token with x402 instead of an API key: $2.64 per million input and $7.92 per million output tokens, minimum $0.002 a call, at most $0.2158. The 402 quotes your request's maximum; \"upto\" payers are charged only the tokens used. Same request/response shap","url":"https://agents.citiviewgroup.com/v1/deepseek-pro/chat/completions?utm_source=zero.xyz","method":"GET","headers":{},"bodySchema":{"type":"object","$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-pro","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":"0.018273","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":"$0.018273/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.018273","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.018273","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_LtBxhP3dqUVhodllCH_Dp","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.018273","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 Pro, a frontier reasoning model with tool calling and 1M-token context, billed per token via x402","exampleAgentPrompt":"Ask DeepSeek V4 Pro: 'Summarize the key differences between transformer and state space models in 3 bullet points' — keep the temperature at 0.7 and limit the response to 300 tokens.","exampleUseCases":[{"title":"Long document reasoning over 1M context","prompt":"I have a 600-page legal contract — send the full text to DeepSeek V4 Pro and ask it to identify every clause that limits liability, then summarize them. Use the 1M-token context window so nothing gets cut off."},{"title":"Agentic tool-calling workflow","prompt":"Use DeepSeek V4 Pro's tool-calling to run a multi-step research task: first search for the latest GDP figures for the G7 countries, then calculate which country grew fastest last year, and return a concise answer."},{"title":"Low-cost per-token LLM inference for a SaaS app","prompt":"I'm building a customer support bot and need to send user messages to a frontier model and get replies billed per token — use DeepSeek V4 Pro with a system message saying 'You are a helpful support agent for Acme Software' and a temperature of 0.3."}],"resultDescription":"Returns an OpenAI-compatible chat.completion JSON object containing the assistant's generated message, finish reason (e.g. 'stop'), token usage breakdown (prompt_tokens, completion_tokens, total_tokens), model identifier ('deepseek-v4-pro'), and a unique completion ID.","failureModes":["Insufficient x402 payment balance — payment rejected before completion","Prompt or output exceeds per-call maximum cost cap of $0.2158 — call refused","max_tokens set too low, causing truncated output with finish_reason='length'","Temperature or other parameter out of valid range — validation error","Network timeout for very long generations near the 1M-token limit","Model unavailable or overloaded — 503 or equivalent error"],"whenToPreferThis":"Choose this endpoint when you need OpenAI-SDK-compatible chat completions from a top open frontier model (DeepSeek V4 Pro) with genuine reasoning capabilities, tool calling, and a massive 1M-token context window, and you want to pay per token via x402 micropayments rather than a subscription API key. It is especially well-suited for agents that need to process very long documents, run multi-step reasoning chains, or invoke tools, and where cost predictability per call (capped at $0.2158, minimum $0.002) matters. Prefer this over OpenAI or Anthropic-native endpoints when you want an open-model alternative billed transparently per token without a monthly commitment.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-15T06:38:35.178Z","isFirstParty":false,"canonicalSlug":"citiview-agent-market-deepseek-v4-pro-chat-completions-7d63d580"}