Skip to main content
For errors, Anannas returns a JSON response with the following shape: 
type ErrorResponse = {
  error: {
    code: number;
    message: string;
    metadata?: Record<string, unknown>;
  };
};
The HTTP Response will have the same status code as error.code, forming a request error if:
  • Your original request is invalid
  • Your API key/account is out of credits
Otherwise, the returned HTTP response status will be200 and any error that occurs while the LLM is producing output will be emitted in the response body or as an SSE data event. Example code for printing errors in JavaScript: 
const request = await fetch('https://api.anannas.ai/v1/chat/completions', {
  method: "POST",
  headers: {
    "Authorization": `Bearer ${process.env.ANANNAS_API_KEY}`,
    "Content-Type": "application/json"
  },
  body: JSON.stringify({
    model: "openai/gpt-4o",
    messages: [{ role: "user", content: "Hello world" }]
  })
});

console.log(request.status); // Will be an error code unless the model started processing
const response = await request.json();
console.error(response.error?.code);
console.error(response.error?.message);

​
Error Codes

  • 400: Bad Request (invalid or missing params, CORS)
  • 401: Invalid credentials (expired/disabled/invalid API key)
  • 402: Your account or API key has insufficient credits
  • 403: Your chosen model requires moderation and your input was flagged
  • 408: Your request timed out
  • 429: You are being rate limited
  • 502: The model provider is down or returned an invalid response
  • 503: No available model provider meets your routing requirements

​
Moderation Errors

If your input was flagged, the error.metadata will contain information about the issue: 
type ModerationErrorMetadata = {
  reasons: string[];
  flagged_input: string;
  provider_name: string;
  model_slug: string;
};

​
Provider Errors

If the model provider encounters an error, the error.metadata will contain information about the issue: 
type ProviderErrorMetadata = {
  provider_name: string;
  raw: unknown;
};

​
Anannas-Specific Error Examples

  1. Invalid Model
{
  "model": "invalid/model-name",
  "messages": [
    { "role": "user", "content": "Test" }
  ]
}
  1. Invalid API Key
{
  "error": {
    "code": 401,
    "message": "Invalid API key"
  }
}
  1. Missing Auth
{
  "model": "openai/gpt-3.5-turbo",
  "messages": [
    { "role": "user", "content": "Test" }
  ]
}

​
When No Content is Generated

Occasionally, the model may not generate any content. This typically occurs when:
  • The model is warming up from a cold start
  • The system is scaling up to handle more requests
If persistent, consider retrying or using a different provider. Note that prompt processing costs may still apply.
Was this page helpful?