# Gemini API Error Codes

{% embed url="<https://ai.google.dev/gemini-api/docs/troubleshooting>" %}

<table><thead><tr><th width="130.06669108072919" valign="top">Error Codes</th><th width="275.199951171875" valign="top"></th><th valign="top"></th></tr></thead><tbody><tr><td valign="top"><strong>400</strong></td><td valign="top"><strong>INVALID_ARGUMENT</strong><br>The request body is malformed.</td><td valign="top">Check the <a href="https://ai.google.dev/api">API reference</a> for request format, examples, and supported versions. Using features from a newer API version with an older endpoint can cause errors.</td></tr><tr><td valign="top"><strong>400</strong></td><td valign="top"><strong>FAILED_PRECONDITION</strong><br>Gemini API free tier is not available in your country. Please enable billing on your project in Google AI Studio.</td><td valign="top">To use the Gemini API, you will need to setup a paid plan using <a href="https://aistudio.google.com/app/apikey">Google AI Studio</a>.</td></tr><tr><td valign="top"><strong>403</strong></td><td valign="top"><strong>PERMISSION_DENIED</strong><br>Your API key doesn't have the required permissions.</td><td valign="top">Check that your API key is set and has the right access. And make sure to go through proper authentication to use tuned models.</td></tr><tr><td valign="top"><strong>404</strong></td><td valign="top"><strong>NOT_FOUND</strong><br>The requested resource wasn't found.</td><td valign="top">Check if all <a href="https://ai.google.dev/docs/troubleshooting#check-api">parameters in your request are valid</a> for your API version.</td></tr><tr><td valign="top"><strong>429</strong></td><td valign="top"><strong>RESOURCE_EXHAUSTED</strong><br>You've exceeded the rate limit.</td><td valign="top">Verify that you're within the model's <a href="https://ai.google.dev/gemini-api/docs/rate-limits">rate limit</a>. <a href="https://ai.google.dev/gemini-api/docs/rate-limits#request-rate-limit-increase">Request a quota increase</a> if needed.</td></tr><tr><td valign="top"><strong>500</strong></td><td valign="top"><strong>INTERNAL</strong><br>An unexpected error occurred on Google's side.</td><td valign="top">Reduce your input context or temporarily switch to another model (e.g. from Gemini 1.5 Pro to Gemini 1.5 Flash) and see if it works. Or wait a bit and retry your request. If the issue persists after retrying, please report it using the Send feedback button in Google AI Studio.</td></tr><tr><td valign="top"><strong>503</strong></td><td valign="top"><strong>UNAVAILABLE</strong><br>The service may be temporarily overloaded or down.</td><td valign="top">Temporarily switch to another model (e.g. from Gemini 1.5 Pro to Gemini 1.5 Flash) and see if it works. Or wait a bit and retry your request. If the issue persists after retrying, please report it using the Send feedback button in Google AI Studio.</td></tr><tr><td valign="top"><strong>504</strong></td><td valign="top"><strong>DEADLINE_EXCEEDED</strong><br>The service is unable to finish processing within the deadline.</td><td valign="top">Set a larger 'timeout' in your client request to avoid this error.</td></tr></tbody></table>


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.vntranslator.com/help/troubleshooting/machine-translation-mt/gemini-api-error-codes.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.