{"uid":"cap_N7tFxqTLQ7cTykVuxp9SQ","slug":"x402engine-cohere-command-a-llm-via-http-402-micropayment-03256271","name":"x402engine — Cohere Command-A LLM via HTTP 402 Micropayment","description":"125 production APIs behind HTTP 402 micropayments. 87 LLMs, Kling V3 and Hailuo video generation, image generation, code execution, travel search, web scraping, TTS, and transaction simulation. Pay with USDC on Base, USDm on MegaETH, or USDC on Solana.","url":"https://x402engine.app/api/llm/command-a?utm_source=zero.xyz","method":"POST","headers":{},"bodySchema":{"type":"object","$schema":"https://json-schema.org/draft/2020-12/schema","required":["input"],"properties":{"input":{"type":"object","required":["type","bodyType","body","method"],"properties":{"body":{"type":"object","required":["messages"],"properties":{"seed":{"type":"integer","description":"Model-supported seed; see /docs/llm-capabilities.md."},"stop":{"oneOf":[{"type":"string"},{"type":"array","items":{"type":"string"},"maxItems":4}],"description":"Model-supported stop; see /docs/llm-capabilities.md."},"top_k":{"type":"integer","description":"Model-supported top_k; see /docs/llm-capabilities.md."},"top_p":{"type":"number","description":"Model-supported top_p; see /docs/llm-capabilities.md."},"stream":{"type":"boolean","description":"Return live OpenAI-compatible SSE after payment settlement."},"messages":{"type":"array","items":{"type":"object","anyOf":[{"required":["content"]},{"required":["tool_calls"]}],"required":["role"],"properties":{"name":{"type":"string"},"role":{"enum":["system","developer","user","assistant","tool"],"type":"string"},"content":{"oneOf":[{"type":"string"},{"type":"null"},{"type":"array","items":{"type":"object","required":["type"],"properties":{"type":{"enum":["text"],"type":"string"}},"additionalProperties":true},"maxItems":100,"minItems":1}]},"refusal":{"type":["string","null"]},"reasoning":{"type":"string"},"tool_calls":{"type":"array","items":{"type":"object"}},"annotations":{"type":"array","items":{"type":"object"}},"tool_call_id":{"type":"string"},"cache_control":{"type":"object"},"reasoning_details":{"type":"array","items":{"type":"object"}}},"additionalProperties":false},"maxItems":100,"minItems":1,"description":"Text or model-supported multimodal messages; assistant tool calls may have null content"},"max_tokens":{"type":"integer","example":1024,"description":"Total output budget, including reasoning. Use this or max_completion_tokens."},"temperature":{"type":"number","description":"Model-supported temperature; see /docs/llm-capabilities.md."},"stream_options":{"type":"object","description":"Optional include_usage boolean; usage is always requested upstream."},"response_format":{"type":"object","description":"Model-supported response_format; see /docs/llm-capabilities.md."},"presence_penalty":{"type":"number","description":"Model-supported presence_penalty; see /docs/llm-capabilities.md."},"frequency_penalty":{"type":"number","description":"Model-supported frequency_penalty; see /docs/llm-capabilities.md."},"max_completion_tokens":{"type":"integer","description":"Alias for total output budget; bounded by model maxOutputTokens."}},"additionalProperties":false},"type":{"type":"string","const":"http"},"method":{"enum":["POST"],"type":"string"},"bodyType":{"enum":["json","form-data","text"],"type":"string"}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object","required":["choices","content"],"properties":{"model":{"type":"string"},"usage":{"type":"object","description":"Provider token and usage accounting, when returned."},"choices":{"type":"array","items":{"type":"object","properties":{"index":{"type":"integer"},"message":{"type":"object","properties":{"role":{"type":"string"},"content":{"type":["string","null"]},"tool_calls":{"type":"array","items":{"type":"object"}}}},"finish_reason":{"type":["string","null"]}}}},"content":{"type":"string","description":"Convenience copy of the first assistant message's text."}}}}}}},"responseSchema":{"type":"json","example":{"model":"cohere/command-a","choices":[{"index":0,"message":{"role":"assistant","content":"Hello!"},"finish_reason":"stop"}],"content":"Hello!"}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.018586","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":"$0.018586/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.018586","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.018586","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_JQRpKkZtGN__bevvtsPwJ","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.018586","costPer":"request","priority":0,"asset":null,"unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Runs a chat completion request through Cohere's Command-A model, paid per-call via USDC micropayment on Base, MegaETH, or Solana.","exampleAgentPrompt":"Using the Command-A model, send this conversation: system prompt 'You are a concise business analyst' and user message 'Summarize the key risks of entering the EV market in 2025 in 3 bullet points', with max 512 tokens and temperature 0.3.","exampleUseCases":[{"title":"Agentic task reasoning with Command-A","prompt":"Send this to Cohere Command-A: system says 'You are an expert software architect' and the user asks 'Design a microservices architecture for a ride-sharing app — list services, their responsibilities, and communication patterns.' Use up to 1024 tokens and keep temperature at 0.5."},{"title":"Streaming customer support response","prompt":"Use Command-A to generate a streaming response for this support scenario: system is 'You are a friendly customer support agent for a SaaS billing product' and the user says 'My invoice is wrong — I was charged twice for March.' Stream the reply back and cap it at 300 tokens."},{"title":"Tool-calling with pay-per-use LLM","prompt":"Call Command-A with a tool-use message: system prompt is 'You are a travel planning assistant', user message is 'Find me flights from New York to Tokyo next month', and include a search_flights tool definition. Use temperature 0 and max 512 tokens."}],"resultDescription":"Returns an OpenAI-compatible JSON object containing the model name ('cohere/command-a'), a choices array with the assistant message (role, content, finish_reason), and a top-level content string. If streaming is enabled, returns SSE chunks in OpenAI-compatible format.","failureModes":["Payment not settled — 402 response if USDC/USDm balance is insufficient","Invalid messages array — 400 if messages is empty or missing required role field","Exceeded max_tokens budget — response truncated or error if token limit is invalid","Unsupported parameter for Command-A — top_k, seed, or stop may be ignored or rejected if not supported per /docs/llm-capabilities.md","Model unavailable — 503 if Command-A inference endpoint is down","Stream timeout — SSE connection dropped if network or server latency is too high"],"whenToPreferThis":"Choose this endpoint when you need Cohere's Command-A specifically — known for strong enterprise document grounding, tool use, and RAG-style tasks — and want to avoid committing to a Cohere subscription or API key. Ideal for agents that need pay-per-call billing in USDC with no monthly overhead. Prefer over generic OpenAI-compatible endpoints when Command-A's enterprise reasoning or multilingual strengths are a better fit than GPT or Claude alternatives also available on x402engine.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-12T18:30:25.153Z","isFirstParty":false,"canonicalSlug":"x402engine-cohere-command-a-llm-via-http-402-micropayment-03256271"}