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

# Error Handling

> Understand ARouter error responses and how to handle them in your application.

## Error Format

All errors follow a consistent JSON format:

```json theme={null}
{
  "error": {
    "message": "Human-readable error description",
    "type": "error_type"
  }
}
```

## Error Types

| HTTP Status | Error Type                             | Description                                                   |
| ----------- | -------------------------------------- | ------------------------------------------------------------- |
| `400`       | `invalid_request_error`                | Malformed request body or missing required fields             |
| `401`       | `authentication_error`                 | Missing, invalid, or expired API key                          |
| `402`       | `payment_required`                     | Insufficient credits — top up your account                    |
| `403`       | `permission_error` / `forbidden_error` | Key doesn't have access to the requested provider or resource |
| `413`       | `invalid_request_error`                | Request body too large (max 10 MB)                            |
| `429`       | `rate_limit_error`                     | Rate limit exceeded (RPM or daily cap)                        |
| `502`       | `server_error`                         | Upstream provider request failed                              |
| `503`       | `server_error`                         | No available providers for the requested model                |

## Common Errors and Solutions

### 401 — Invalid API Key

```json theme={null}
{
  "error": {
    "message": "invalid api key",
    "type": "authentication_error"
  }
}
```

**Fix:** Check that your API key is correct and hasn't been revoked.

### 403 — Provider Not Allowed

```json theme={null}
{
  "error": {
    "message": "provider 'anthropic' is not allowed for this API key",
    "type": "forbidden_error"
  }
}
```

**Fix:** Your API key has an `allowed_providers` restriction. Use a different key
or update the allowed providers via the management API.

### 429 — Rate Limited

```json theme={null}
{
  "error": {
    "message": "rate limit exceeded",
    "type": "rate_limit_error"
  }
}
```

**Fix:** Implement exponential backoff. Consider raising your key's rate limit.

### 502 — Upstream Failed

```json theme={null}
{
  "error": {
    "message": "upstream request failed",
    "type": "server_error"
  }
}
```

**Fix:** The LLM provider returned an error or is unreachable. ARouter automatically
handles key failover, but the provider itself may be experiencing issues. Retry or switch
to a different provider.

## Handling Errors in Code

<Tabs>
  <Tab title="Python (OpenAI)">
    ```python theme={null}
    from openai import OpenAI, APIStatusError, APIConnectionError

    client = OpenAI(
        base_url="https://api.arouter.ai/v1",
        api_key="lr_live_xxxx",
    )

    try:
        response = client.chat.completions.create(
            model="openai/gpt-5.4",
            messages=[{"role": "user", "content": "Hello!"}],
        )
    except APIStatusError as e:
        if e.status_code == 401:
            print("Invalid API key")
        elif e.status_code == 402:
            print("Insufficient credits — top up your account")
        elif e.status_code == 429:
            print("Rate limited, backing off...")
        elif e.status_code in (502, 503):
            print("Provider error, retrying...")
        else:
            print(f"API error {e.status_code}: {e.message}")
    except APIConnectionError:
        print("Network error — check your connection")
    ```
  </Tab>

  <Tab title="Node.js (OpenAI)">
    ```typescript theme={null}
    import OpenAI from "openai";

    const client = new OpenAI({
      baseURL: "https://api.arouter.ai/v1",
      apiKey: "lr_live_xxxx",
    });

    try {
      const response = await client.chat.completions.create({
        model: "openai/gpt-5.4",
        messages: [{ role: "user", content: "Hello!" }],
      });
    } catch (error) {
      if (error instanceof OpenAI.APIError) {
        switch (error.status) {
          case 401: console.error("Invalid API key"); break;
          case 402: console.error("Insufficient credits"); break;
          case 429: console.error("Rate limited"); break;
          case 502:
          case 503: console.error("Provider error"); break;
          default:  console.error(`Error ${error.status}: ${error.message}`);
        }
      }
    }
    ```
  </Tab>

  <Tab title="Go">
    ```go theme={null}
    resp, err := client.ChatCompletion(ctx, req)
    if err != nil {
        var apiErr *arouter.APIError
        if errors.As(err, &apiErr) {
            switch apiErr.StatusCode {
            case 401:
                log.Fatal("Invalid API key")
            case 429:
                log.Println("Rate limited, backing off...")
                time.Sleep(time.Second)
            case 502:
                log.Println("Provider error, retrying...")
            }
        } else {
            log.Fatal("Network error:", err)
        }
    }
    ```
  </Tab>
</Tabs>

## Retry Strategy

For production applications, we recommend:

1. **Retry on 429 and 502** with exponential backoff
2. **Do not retry on 400, 401, 403** — these are permanent errors
3. **Set a max retry count** (e.g., 3 attempts)
4. **Consider multi-model routing** — if one model cannot serve the request, send an ordered candidate list via `models` and `route`

```python theme={null}
import time
from openai import OpenAI, APIStatusError

def call_with_retry(client, request, max_retries=3):
    for attempt in range(max_retries):
        try:
            return client.chat.completions.create(**request)
        except APIStatusError as e:
            if e.status_code in (429, 502, 503) and attempt < max_retries - 1:
                time.sleep(2 ** attempt)
                continue
            raise
```

## Handling Errors During Streaming

When streaming (`stream: true`), errors behave differently depending on when they occur:

* **Before any tokens are sent** — ARouter returns a standard HTTP error response with a non-200 status code. Handle this the same as non-streaming errors.
* **After tokens have been sent** — The HTTP status is already 200 OK. The error is delivered as an SSE event in the stream body.

Mid-stream errors look like:

```json theme={null}
{
  "id": "chatcmpl-xxx",
  "object": "chat.completion.chunk",
  "error": {
    "code": "server_error",
    "message": "Provider disconnected unexpectedly"
  },
  "choices": [
    { "index": 0, "delta": { "content": "" }, "finish_reason": "error" }
  ]
}
```

Check the `finish_reason` on each chunk. If it's `"error"`, the stream has terminated abnormally.

```typescript theme={null}
for await (const chunk of stream) {
  // Check for mid-stream error
  if ("error" in chunk) {
    console.error(`Stream error: ${(chunk as any).error.message}`);
    break;
  }
  if (chunk.choices[0]?.finish_reason === "error") {
    console.error("Stream terminated due to an error");
    break;
  }
  const content = chunk.choices[0]?.delta?.content;
  if (content) process.stdout.write(content);
}
```

See the [Streaming Guide](/en/guides/streaming) for complete error handling examples.