Skip to contentBase Eleven
Sign inStart free
Reference

API reference

Every endpoint, field, header, status and example of the Base Eleven API, from the OpenAPI 3.1 document the gateway is tested against.

Base Eleven's models are fictional and its API returns simulated responses. Usage, credits and billing run for real, in test mode.

Base URL https://api.baseeleven.dev/v1. Send your key in x-api-key or as Authorization: Bearer <key>; the quickstart shows a first call. The try-it panel below sends real calls with your key, metered like any other.

Limits by model

The document states these as conditions on MessagesRequest, which not every viewer shows: max_tokens runs from 1 to the model’s maximum, and input tokens plus max_tokens may not exceed its context. The first entry of messages is always the user’s turn.

Limits by model, from the company spec
ModelAPI idHighest max_tokensContext tokens
Eleven Liteeleven-lite1,02432,000
Eleven Maxeleven-max4,096128,000

Endpoints