Langdock · Rate Limits

Langdock Rate Limits

Name: Langdock Rate Limits
Creator: Langdock
Keywords: Rate Limiting, Artificial Intelligence

Langdock enforces default per-model rate limits on the public API expressed as both a request-rate and a token-rate. Workspaces that bring their own model keys (BYOK) can have admins configure custom per-model limits in Settings.

Langdock Rate Limits is the machine-readable rate-limit profile for Langdock on the APIs.io network, conforming to the API Commons Rate Limits specification.

It captures 2 rate-limit definitions, measuring requests_per_minute and tokens_per_minute.

The profile also includes response codes documented for throttled.

Tagged areas include Rate Limiting and Artificial Intelligence.

2 Limits Throttle: 429

Rate LimitingArtificial Intelligence

Limits

Requests per minute (default, per model) workspace

requests_per_minute · minute

500

Tokens per minute (default, per model) workspace

tokens_per_minute · minute

60000

Sources

https://docs.langdock.com/en/developer/overview/api-introduction