When you work with the Gemini API and wait for a well-formed response, a pop-up suddenly appears with the error message ‘429 RESOURCE_EXHAUSTED’. Frustrating, right? It simply means your project exceeded a rate limit or quota applied by the Gemini API.<\/p>\n
Don’t worry, we have got you covered. In this blog, we will learn what the error means, why it occurred, how to mitigate it quickly, and how to prevent it from happening again.<\/p>\n
Gemini API Error 429 means your app has exceeded the allowed rate limit or quota (like requests per minute or tokens per minute). To fix it, slow down your requests, reduce input size, and use exponential backoff.<\/p>\n
| Error Code<\/span><\/b><\/td>\n | Meaning<\/span><\/b><\/td>\n | Common Cause<\/span><\/b><\/td>\n<\/tr>\n| 400\u00a0<\/span><\/b>\u00a0(INVALID_ARGUMENT)<\/span><\/b><\/td>\n | The request body is malformed.<\/span><\/td>\n | There is a\u00a0typo,\u00a0or\u00a0a\u00a0required\u00a0field\u00a0is missing\u00a0in\u00a0your\u00a0request.<\/span><\/td>\n<\/tr>\n | 403\u00a0<\/span><\/b>(PERMISSION_DENIED)<\/span><\/b><\/td>\n | Your API key\u00a0doesn’t\u00a0have\u00a0the required\u00a0permissions.<\/span><\/td>\n | You are using the wrong API key; you are\u00a0attempting\u00a0to use a tuned model without\u00a0proper authentication.<\/span><\/td>\n<\/tr>\n | 404\u00a0<\/span><\/b>\u00a0(NOT_FOUND)<\/span><\/b><\/td>\n | The requested resource was\u00a0not\u00a0found.<\/span><\/td>\n | An image, audio, or video file referenced in your request was not found.<\/span><\/td>\n<\/tr>\n | 429\u00a0(RESOURCE_EXHAUSTED)<\/span><\/b><\/td>\n | You\u00a0have\u00a0exceeded the rate limit.<\/span><\/td>\n | You are sending too many requests per minute with the\u00a0free-tier\u00a0Gemini API.<\/span><\/td>\n<\/tr>\n | 500\u00a0<\/span><\/b>(INTERNAL)<\/span><\/b><\/td>\n | Internal server error due to\u00a0a\u00a0long\u00a0input context or an unexpected processing\u00a0issue<\/span><\/td>\n | Your input context is too long.<\/span><\/td>\n<\/tr>\n | 503\u00a0<\/span><\/b>\u00a0(UNAVAILABLE)<\/span><\/b><\/td>\n | The service may be temporarily\u00a0unavailable due to overload\u00a0or\u00a0downtime.<\/span><\/td>\n | The service is\u00a0currently experiencing a\u00a0capacity\u00a0issue.<\/span><\/td>\n<\/tr>\n | 504\u00a0<\/span><\/b>\u00a0(DEADLINE_EXCEEDED)<\/span><\/b><\/td>\n | The service is unable to finish processing within the deadline.<\/span><\/td>\n | Your prompt (or context) is too large to be processed\u00a0within the given\u00a0time.<\/span><\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n | Gemini API Error 429: Causes & Fixes<\/h2>\n |
| Error Code<\/span><\/b><\/td>\n | Cause\u00a0<\/span><\/b><\/td>\n | Fix\u00a0<\/span><\/b><\/td>\n<\/tr>\n| 400 INVALID_ARGUMENT<\/span><\/b><\/td>\n | Malformed request payload<\/span><\/td>\n | Fix JSON,\u00a0required\u00a0fields, and\u00a0API version<\/span><\/td>\n<\/tr>\n | 400 FAILED_PRECONDITION<\/span><\/b><\/td>\n | Free tier unavailable +\u00a0billing\u00a0disabled<\/span><\/td>\n | Enable billing<\/span><\/td>\n<\/tr>\n | 403 PERMISSION_DENIED<\/span><\/b><\/td>\n | Incorrect API key or missing permissions<\/span><\/td>\n | Correct authentication<\/span><\/td>\n<\/tr>\n | 404 NOT_FOUND<\/span><\/b><\/td>\n | Resource not found or invalid parameters<\/span><\/td>\n | Correct endpoint\/model name<\/span><\/td>\n<\/tr>\n | 429 RESOURCE_EXHAUSTED<\/span><\/b><\/td>\n | Rate limit exceeded<\/span><\/td>\n | Throttle, backoff, request quota increase<\/span><\/td>\n<\/tr>\n | 500 INTERNAL<\/span><\/b><\/td>\n | Context too long or unexpected issue<\/span><\/td>\n | Reduce context; retry; switch model<\/span><\/td>\n<\/tr>\n | 503 UNAVAILABLE<\/span><\/b><\/td>\n | Temporary capacity issue<\/span><\/td>\n | Retry; switch model<\/span><\/td>\n<\/tr>\n | 504 DEADLINE_EXCEEDED<\/span><\/b><\/td>\n | Prompt too large<\/span><\/td>\n | Increase timeout or reduce prompt size<\/span><\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n | 1. Error 400 – Bad Request (INVALID_ARGUMENT)<\/h3>\n2. Error 400 – FAILED_PRECONDITION<\/h3>\n3. Error 403 – Forbidden (PERMISSION_DENIED)<\/h3>\n4. Error 404 – Resource Not Found (NOT_FOUND)<\/h3>\n5. Error 500 – Internal Server Error<\/h3>\n6. Error 503 – Service Unavailable<\/h3>\n7. Error 504 – Deadline Exceeded<\/h3>\nHow to Prevent Gemini API Errors<\/h2>\nHere’s how you can prevent most of the errors from occurring altogether:<\/p>\n 1. Monitor your tokens and request usage<\/h4>\n2. Add rate limits on the client side<\/h4>\n3. Estimate tokens ahead of time<\/h4>\n4. Structure prompts are clean and succinct<\/h4>\n5. Set appropriate timeouts<\/h4>\n6. Use Google’s official client SDKs<\/h4>\n7. Split workloads into multiple projects<\/h4>\nConclusion<\/h2>\nGemini API errors can be frustrating, but the good news is that they are predictable, and you can also fix these. As you are aware, Google enforces strict token and request limits, so the solution is designing your application with token budgeting, batching, rate limiting, and retries in mind.<\/p>\n By learning what each error indicates and working within Google’s recommended practices, you can create a Gemini-powered application that is more stable, scalable, and production-ready.<\/p>\n Frequently Asked Questions<\/h2>\n |
Ans.<\/strong> Use Google’s official SDKs (e.g., python-genai, js-genai), which include built-in retry and error handling mechanisms.<\/p>\n Ans.<\/strong> Throttle requests, reduce token usage, set exponential backoff with jitter, or request an increase in quota.<\/p>\n Ans.<\/strong> The JSON payload is malformed, or required fields are missing.<\/p>\n Ans.<\/strong> You are using an invalid API Key or missing authentication (note: 401 isn’t common, but could still occur based on configuration).<\/p>\nQ 2. How do I fix Gemini API Error 429?<\/h4>\n
Q 3. What causes Gemini API Error 400 (Bad Request)?<\/h4>\n
Q 4. Why am I getting Gemini API Error 401 (Unauthorized)?<\/h4>\n
Q 5. What is Gemini API Error 403 (Forbidden)?<\/h4>\n