# Rate limits

> How throttling works, what a 429 means here, and how to build a client that does not trigger one.

_Source: https://aiprimetech.io/docs/api-reference/rate-limits/ · Home > Docs > API reference_

Limits keep shared upstream capacity fair. They apply per account, not per key, so adding keys does not raise your ceiling.


## What is limited

| Dimension | Behaviour |
|---|---|
| Concurrent requests | In-flight requests per account. The usual cause of a 429. |
| Requests per minute | Sustained call rate. |
| Tokens per minute | Combined input and output throughput. |

Unlimited plans apply fair-use limits rather than a credit balance — they remove the per-token charge, not the concurrency ceiling.


## Handling 429 properly

1. Back off exponentially with jitter — 1s, 2s, 4s, 8s, each plus or minus a random fraction.
2. Cap concurrency client-side with a semaphore instead of firing everything and retrying the rejects.
3. Queue batch work rather than parallelising it maximally; throughput is bounded by tokens per minute, not by how many sockets you open.
4. Treat `529` differently from `429` — that is upstream capacity, not you, and usually clears within seconds.

```python
import asyncio

sem = asyncio.Semaphore(8)      # ceiling on concurrency, tune to your plan

async def ask(client, body):
    async with sem:
        return await client.post("/v1/messages", json=body)
```

> Agentic tools such as Claude Code fan out aggressively by design. If you see 429s during heavy agent use, lower the tool's parallelism before raising your plan.


## Reducing pressure instead of retrying

- Route cheap work to `claude-haiku-4-5` — smaller models finish sooner and hold a slot for less time.
- Turn on [prompt caching](/docs/guides/prompt-caching/): cached prefixes cut input tokens and therefore token-per-minute pressure.
- Trim conversation history; see [Context management](/docs/guides/context-management/).
- Batch offline work into off-peak windows.

- [Errors](https://aiprimetech.io/docs/api-reference/errors/) — Status code reference
- [Cost control](https://aiprimetech.io/docs/guides/cost-control/) — Spend less per task
- [Plans](https://aiprimetech.io/docs/billing/plans/) — Flat-rate options


---
_ClaudeAPIKey.dev is an independently operated, Anthropic-compatible API gateway. Not affiliated with Anthropic._