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

# payload_too_large

> HTTP 413 — request body or token count exceeds the configured cap.

|                 |                              |
| --------------- | ---------------------------- |
| **HTTP status** | `413 Payload Too Large`      |
| **Code**        | `payload_too_large`          |
| **Retry?**      | No — send a smaller payload. |

## When this happens

Two distinct triggers share this error code:

* **Raw byte cap.** The request body exceeds the API's configured
  `MAX_REQUEST_SIZE` (10 MB by default).
* **Per-analyzer token cap.** The hero `POST /api/v1/analyze/` rejects
  prompts that exceed the per-analyzer token limits (e.g. 100,000
  tokens for the safety / prompt-injection / vector analyzers,
  1,000,000 for YARA / SDP / URL).

The response detail tells you which.

## Example response

```json theme={null}
{
  "detail": "Request body exceeds 10 MB.",
  "code": "payload_too_large",
  "request_id": "5b3f6c7e-7d24-4d40-9b12-3a59c01c6e91",
  "doc_url": "https://docs.lasscyber.com/errors/payload_too_large"
}
```

For an analyzer-level cap:

```json theme={null}
{
  "detail": "Prompt exceeds 100,000 token limit for safety_moderation_analyzer.",
  "code": "payload_too_large",
  "request_id": "...",
  "doc_url": "https://docs.lasscyber.com/errors/payload_too_large"
}
```

## How to fix

* **For prompt analysis**: trim the prompt or split it into chunks
  yourself before sending to Agnes. The classifier already chunks at
  400 tokens internally for prompt-injection; the cap is on the
  *input* you submit.
* **For uploads / threat-intel ingestion**: split the payload across
  multiple requests.

## Per-analyzer token caps

| Analyzer                     | Max input tokens |
| ---------------------------- | ---------------- |
| Prompt Injection & Jailbreak | 100,000          |
| Safety & Responsible AI      | 100,000          |
| Sensitive Data               | 1,000,000        |
| Natural Language             | 100,000          |
| URL Risk                     | 1,000,000        |
| YARA                         | 1,000,000        |
| Semantic Threat Intelligence | 100,000          |

The combined analyzer enforces the *most restrictive* limit across the
analyzers in your policy.

## SDK behaviour

| SDK        | Exception                                                    |
| ---------- | ------------------------------------------------------------ |
| Python     | `agnes.ValidationError` (with `code == "payload_too_large"`) |
| TypeScript | `ValidationError` (with `code === "payload_too_large"`)      |

SDKs do not retry 413s.

## Related

* [Combined analyzer](/concepts/combined-analyzer) — token limits and
  chunking.