Private LLM chat completion (x402 or API-key paid)

OpenAI-compatible chat completion — pass an OpenAI-style {model, messages, max_tokens} body, receive the standard {choices, usage} response. Price is per call: ceil(total message chars / 3.5) estimated input tokens × the model's input rate + max_tokens × its output rate, marked up — set max_tokens tight for tighter billing. Anonymous — no account; metering keeps token counts only.

post/v1/agent/chat

Request

  • Base URL: https://livepairai.com (the document declares no server; this is the origin it was published from)
  • URL: https://livepairai.com/v1/agent/chat
  • Auth: one of:
    • API key in header x-api-key
    • HTTP bearer
    • none

Request body

modelstring

Text model id — see textModels in GET /v1/agent/models (default: deepseek/deepseek-v4-flash)

max_tokensnumber

Output token cap — billed at this amount; set it tight to pay less

temperaturenumber
reasoning_effort'low' | 'medium' | 'high'

OpenAI-style reasoning effort — passed through to reasoning-capable models

payerstring

Your payer wallet — applies your volume-tier discount (5% at $100+, 10% at $500+, 15% at $2000+ lifetime paid). Must equal the wallet that signs the payment.

Response

OpenAI chat completion — {choices:[{message:{role,content}}], usage:{prompt_tokens,completion_tokens}}

choicesobject[]
usageobject

Changes

No recorded changes to this operation across all 1 revision of this API.