UnioAPI Documentation
Platform Guides

Rate Limits

The three request-level limits, how they are counted, and handling 429.

Three limits

The platform enforces three per-user limits at the request entry:

LimitMeaning
RPMRequests per minute
RPDRequests per day
ConcurrencyRequests in flight at the same time

Exact quotas are shown in the console.

How counting works

  • Per user account, not per API key: all keys under one account share the same RPM, RPD, and concurrency quota — creating more keys does not multiply it.
  • No TPM cap: the platform does not limit token throughput; upstream capacity shortages are handled internally by routing and failover, not charged against your quota.
  • Internal failover retries do not consume extra entry quota.

Handling 429

There are two sources of 429 with different handling:

SourceSignatureAction
RPM / RPD / concurrency limitRegular rate limitingRetry with exponential backoff; persistent 429 means you exceed the quota
Balance temporarily frozenComes with Retry-After: 1Book balance is positive; retry shortly — see Billing & Usage

Retry guidance: honor the Retry-After header; otherwise back off exponentially starting at 1 second, and cap concurrency for batch jobs.

Auxiliary endpoints such as GET /v1/models incur no call billing but share request admission with other /v1 endpoints — aggressive polling may also get 429.

On this page