LMllm.market
API documentation

OpenAI-compatible API

The public API supports active catalog discovery, Chat Completions, and Responses. Use https://llm.market/v1 as your base URL.

Supported endpoints

GET/v1/modelsList active model IDs
POST/v1/chat/completionsRequires chat:completions scope
POST/v1/responsesRequires responses scope

Quick start

Create an API key in the dashboard, then use a model ID returned by /v1/models.

Example
curl https://llm.market/v1/chat/completions \
  -H "Authorization: Bearer sk-YOUR_LLM_MARKET_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"MODEL_FROM_V1_MODELS","messages":[{"role":"user","content":"Say hello!"}],"max_tokens":100}'

Billing and streaming

A request is authorized against subscription quota or available PAYG balance before it is forwarded. Streaming requests include stream_options.include_usage upstream so final token usage can be settled. If the upstream does not return usage, llm.market releases the reservation instead of inventing a charge.

API keys

Create a key in the dashboard and call https://llm.market/v1. Interactive chat UI is not part of the product surface.