Skip to main content
The Liquid API is an OpenAI-compatible inference API plus native endpoints for decision models and large batch uploads. Every endpoint lives under one host:

​
Authentication

Every request needs an API key, sent as a bearer token: Authorization: Bearer $LIQUID_API_KEY. Create a key on the API keys page of Liquid Console; it is shown once. See the Quickstart. To send a request from a reference page, paste your key into its playground. Model ids in the examples appear as $MODEL_ID (and $DECISION_MODEL_ID for decision models). Replace them with a model id from the Models page or GET /openai/v1/models.

​
Rate limits

Inference requests count toward a limit for your organization and model. See Rate limits.

​
Download

The full reference as an OpenAPI document, for importing into Postman, Insomnia, and code generators.