# Adola

Adola lets developers ship supported open models through one OpenAI-compatible inference API.

Billing must be enabled before API use. The API supports streaming and exposes token usage and request cost. Each successfully metered request costs the greater of its token subtotal or the model’s displayed request minimum. There is no recurring subscription or monthly minimum spend.

## Key pages

- Product: https://adola.app/
- Trial: https://adola.app/try
- API docs: https://adola.app/docs
- OpenAPI: https://adola.app/openapi.json
- Pricing: https://adola.app/pricing
- Resources: https://adola.app/resources
- Privacy: https://adola.app/privacy
- Terms: https://adola.app/terms
- Signup: https://adola.app/signup

## API

- Models: GET https://api.adola.app/v1/models
- Public catalog: GET https://api.adola.app/v1/catalog
- Chat completions: POST https://api.adola.app/v1/chat/completions
- Current model IDs and prices are published by the public catalog.

Send standard chat messages and read the answer from `choices[0].message.content`.
Set `stream: true` for OpenAI-compatible server-sent events.
Successful responses include standard token usage, customer billing metadata, and metering status.