> ## Documentation Index
> Fetch the complete documentation index at: https://manifest.build/llm-gateway/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# M203: Concurrency limit exceeded

> M203 is returned when a workspace has more than 10 requests in flight.

## What you saw

```text theme={"theme":{"light":"github-light","dark":"github-dark"}}
[🦚 Manifest M203] Too many concurrent requests. Give it a moment.
See https://manifest.build/llm-gateway/docs/errors/M203
```

## Why it happened

The gateway caps in-flight requests at 10 per workspace, shared by all its harnesses. Streaming completions hold a slot until the stream ends, so an agent that fires off parallel streams can hit this fast.

## How to fix it

1. Let in-flight requests finish, then retry. Most SDKs handle this automatically with backoff on `429`.
2. Reduce parallelism on the client side. Most agents only need one or two concurrent calls.
3. The 10 concurrent-request cap is a fixed guardrail. No env var or setting changes it, self-hosted included. Reduce parallelism as in step 2.

## Related

* [M201: Per-user rate limit](/llm-gateway/docs/llm-gateway/docs/errors/M201)
* [M202: Per-IP rate limit](/llm-gateway/docs/llm-gateway/docs/errors/M202)
* [M200: Usage limit exceeded](/llm-gateway/docs/llm-gateway/docs/errors/M200)
* [Self-hosted setup](/llm-gateway/docs/llm-gateway/docs/self-hosted)
* [All error codes](/llm-gateway/docs/llm-gateway/docs/errors)