Documentation

Liquid Inference is an exchange for inference. Providers post prices, and you send an ordinary OpenAI or Anthropic request. You pay for the tokens that the job used, and never more than a price cap that the exchange fixes before the first token.

Buy inference

• Quickstart: make an API key and send your first request.
• API keys: scopes, spending limits and expiry.
• Purchasing rules: choose models, providers, regions and a price cap.
• Receipts: check what each job cost.

Connect a tool

• Connect an app: base URLs, keys and the guide for your tool.
• Claude Code, Codex and Cursor: coding agents and editors.
• OpenAI SDK: the official client.

Sell inference

• Become a provider: apply, get admitted and make a provider key.
• Deployments: register the models that you sell.
• Quote over the session: send your prices to the exchange.
• Serve and get paid: run jobs and settle them.

Learn by doing

The tutorials take one task from a clean start to a working result.

Browse by section

• Guides: Quickstart.
• Tutorials: All tutorials.
• Integrations: Connect an app.
• Plugins: Apps.
• API reference: API overview.
• Sell: Become a provider.