Use this guide to help you diagnose and resolve common issues that arise when you call the Gemini API. If you encounter API key issues, ensure you have set up your API key correctly per the API key setup guide.
Error codes
The following table lists common error codes you may encounter, along with explanations for their causes and troubleshooting steps:
HTTP Code | Status | Description | Solution |
400 | INVALID_ARGUMENT | The request body is malformed. | Check the API reference for request format, examples, and supported versions. Using features from a newer API version with an older endpoint can cause errors. |
403 | PERMISSION_DENIED | Your API key doesn't have the required permissions. | Check that your API key is set and has the right access. |
404 | NOT_FOUND | The requested resource wasn't found. | Check if all parameters in your request are valid for your API version. |
429 | RESOURCE_EXHAUSTED | You've exceeded the rate limit. | Ensure you're within the model's rate limit. Request a quota increase if needed. |
500 | INTERNAL | An unexpected error occurred on Google's side. | 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. |
503 | UNAVAILABLE | The service may be temporarily overloaded or down. | 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. |
Check your API calls for model parameter errors
Ensure your model parameters are within the following values:
Model parameter | Values (range) |
Candidate count | 1-8 (integer) |
Temperature | 0.0-1.0 |
Max output tokens |
Use
get_model (Python)
to determine the maximum number of tokens for the model you are using.
|
TopP | 0.0-1.0 |
In addition to checking parameter values, make sure you're using the correct
API version (e.g., /v1
or /v1beta
) and
model that supports the features you need. For example, if a feature is in Beta
release, it will only be available in the /v1beta
API version.
Check if you have the right model
Ensure you are using a supported model. Use list_models
(Python) to get all models
available for use.
Safety issues
If you see a prompt was blocked because of a safety setting in your API call, review the prompt with respect to the filters you set in the API call.
If you see BlockedReason.OTHER
, the query or response may violate the terms
of service or be otherwise unsupported.
Improve model output
For higher quality model outputs, explore writing more structured prompts. The introduction to prompt design page introduces some basic concepts, strategies, and best practices to get you started.
If you have hundreds of examples of good input/output pairs, you can also consider model tuning.
Understand token limits
Use the ModelService
API to get additional
metadata about the models, including input and
output token limits.
To get the tokens used by your prompt, use
countMessageTokens
for chat models and
countTextTokens
for
text models.
Known issues
- Mobile support for Google AI Studio: While you can open the website on mobile, it has not been optimized for small screens.
- The API supports only English. Submitting prompts in different languages can produce unexpected or even blocked responses. See available languages for updates.
File a bug
File an issue in Github to ask questions or submit feature requests or bugs.