Chroma Rate Limits
Chroma Cloud is serverless and meters Write / Storage / Query / Network rather than capping requests per second. Public documentation does not publish a numeric per-second or per-minute API rate-limit policy; tenants that exceed configured spend or per-database scaling envelopes are paused rather than throttled. The open-source Chroma server (self-hosted) has no built-in rate limiter — limits are bounded by the underlying host.
Chroma Rate Limits is the machine-readable rate-limit profile for Chroma on the APIs.io network, conforming to the API Commons Rate Limits specification.
It captures 2 rate-limit definitions, measuring varies.
The profile also includes 3 backoff/retry policies defined and response codes documented for throttled, serverError, and serviceUnavailable.
Tagged areas include AI, Vector Database, Retrieval, Serverless, and Rate Limiting.
Limits
Policies
Sources
Work with this as data
Every rate limit here is available over the APIs.io API and to AI agents over MCP.