Limits and usage

Your tenant has request, concurrency, document, and monthly input-token limits. GET /v1/usage shows the limits assigned to you and your current usage. The example uses BREADBOWL_API_URL and BREADBOWL_API_KEY from the quickstart.

curl --fail-with-body \
  "$BREADBOWL_API_URL/v1/usage" \
  -H "Authorization: Bearer $BREADBOWL_API_KEY"

Unless onboarding assigned different values, the alpha defaults are:

Limit	Default
Requests per minute	60
Concurrent requests	2
Input tokens per UTC month	50,000,000
Stored documents	100,000

Request size limits are:

Input	Maximum
JSON body	5 MiB
Documents per upload or score request	50
Text per document	100 KiB
Query text	8 KiB
`top_k` / `candidate_k`	100 / 500

Token values in the usage response are decimal strings. Use BigInt or another arbitrary-precision integer type if you calculate with them. On HTTP 429, inspect error.code and honor Retry-After. Reduce concurrency for concurrency_limit_exceeded; stop retrying when monthly usage is exhausted.

Get started

Guides

Help