OpusGate

Rate limits & restrictions

There are no artificial token quotas, daily caps or model gating — you pay for the tokens you use. The limits that do exist protect the gateway, and normal coding-agent traffic never hits them.

LimitValueWhen exceeded
Requests per minute600 / min per client429 — back off and retry
Request body size25 MB413 — trim attachments / context
Gateway timeout180 s per request504 upstream_timeout — use streaming
Token limitsnone of our ownonly the model's native context window applies

Streaming and long generations

The 180-second timeout applies to how long the connection can sit without completing. With "stream": true tokens flow as they're generated, so even very long outputs finish fine. Every tool documented in the setup guides streams by default — the timeout mostly bites hand-written non-streaming scripts with large max_tokens.

Concurrency

There is no artificial concurrency cap on the OpusGate side; parallel requests are bounded only by upstream model throughput. If you hit sustained upstream 429s at high parallelism, add exponential backoff — or contact support to discuss your workload.

What we deliberately don't limit
Requests per day, tokens per month, model access per plan — none of that exists here. A $2 balance and a $200 balance get the same models and the same throughput.

Error bodies for 429 / 504 and friends are on the error codes page.

← PreviousError codesNext →API keys