Chroma · Rate Limits

Chroma Db Rate Limits

Chroma does not publish fixed numeric request-rate limits for its v2 REST API. On self-hosted (open-source) deployments, throughput is bounded only by your own hardware, and the server advertises operational limits - notably a maximum batch size - via the GET /api/v2/pre-flight-checks endpoint that clients read before writing. On Chroma Cloud, capacity is governed by usage-based metering (data written, stored, queried, and network egress) and per-plan limits such as the number of databases and team members, rather than by a documented per-minute request cap.

Chroma Db 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 5 rate-limit definitions, measuring requests, operations, records, bytes, and databases.

The profile also includes 2 backoff/retry policies defined and response codes documented for throttled.

Tagged areas include Vector Database, Embeddings, Vector Search, Rate Limiting, and Quotas.

5 Limits Throttle: 429
Vector DatabaseEmbeddingsVector SearchRate LimitingQuotas

Limits

REST API Requests account
requests
not published
No fixed numeric request-rate limit is documented for the v2 REST API.
Self-Hosted Throughput deployment
operations
hardware-bound
Constrained by your own infrastructure, not by Chroma.
Write Batch Size request
records
server max_batch_size
The maximum records per add/upsert/update call is advertised via GET /api/v2/pre-flight-checks.
Cloud Usage Metering account
bytes
per plan / usage-based
Chroma Cloud meters data written, stored, queried, and network egress; capacity scales with spend.
Cloud Database Count account
databases
per plan (Starter ~10, Team ~100, Enterprise unlimited)
Plan-level limit on number of databases rather than a request rate.

Policies

Batch Sizing
Clients should chunk writes to stay within the server's advertised max_batch_size from pre-flight-checks.
Backoff Strategy
Clients should implement exponential backoff with jitter and honor Retry-After on 429 responses.

Sources

Work with this as data

Every rate limit here is available over the APIs.io API and to AI agents over MCP.

MCP server

One button, every client — Claude, Cursor, VS Code and the rest.

https://apis.io/mcp

Tools for rate limits

4 MCP tools reach this
  • find_rate_limitsBrowse and filter every rate limit in the catalog.
  • apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.
  • resolveTurn a domain, URL or GitHub org into the provider it belongs to.
  • find_cohortsEvery scored population of providers in the catalog.
All 92 tools

Call it yourself

curl for this page
This rate limit
curl "https://apis.io/api/v1/rate-limits/chroma-db-rate-limits"
All rate limits
curl "https://apis.io/api/v1/rate-limits?limit=25"

Discovery needs no key. Ratings and market analysis are Pro.

Get an API key

Free tier, no email required.

A second provider on the same verified email joins the account you already have.