Gemini API Quota Exceeded: 429 RESOURCE_EXHAUSTED Error & Solutions

Python

import time
import random
import google.generativeai as genai
import os

genai.configure(api_key=os.environ["GOOGLE_API_KEY"])
model = genai.GenerativeModel("gemini-2.0-flash")

def call_with_backoff(prompt, max_retries=5):
    for attempt in range(max_retries):
        try:
            return model.generate_content(prompt)
        except Exception as e:
            if "429" in str(e) or "RESOURCE_EXHAUSTED" in str(e):
                if attempt == max_retries - 1:
                    raise
                # Exponential backoff: 1s, 2s, 4s, 8s, 16s + jitter
                wait = (2 ** attempt) + random.uniform(0, 1)
                print(f"Rate limited. Waiting {wait:.1f}s before retry {attempt + 1}/{max_retries}")
                time.sleep(wait)
            else:
                raise

response = call_with_backoff("Explain exponential backoff in one paragraph")

JavaScript / Node.js

import { GoogleGenerativeAI } from "@google/generative-ai";

const genAI = new GoogleGenerativeAI(process.env.GOOGLE_API_KEY);
const model = genAI.getGenerativeModel({ model: "gemini-2.0-flash" });

async function callWithBackoff(prompt, maxRetries = 5) {
  for (let attempt = 0; attempt < maxRetries; attempt++) {
    try {
      const result = await model.generateContent(prompt);
      return result.response.text();
    } catch (error) {
      const isQuota = error.message?.includes("429") ||
                      error.message?.includes("RESOURCE_EXHAUSTED");
      if (isQuota && attempt < maxRetries - 1) {
        const wait = (2 ** attempt + Math.random()) * 1000;
        console.log(`Rate limited. Retrying in ${(wait / 1000).toFixed(1)}s...`);
        await new Promise(resolve => setTimeout(resolve, wait));
      } else {
        throw error;
      }
    }
  }
}

const text = await callWithBackoff("What is exponential backoff?");
console.log(text);

cURL (check quota headers)

# Use -i to see response headers — Gemini returns Retry-After on 429
curl -i -X POST \
  "https://generativelanguage.googleapis.com/v1beta/models/gemini-2.0-flash:generateContent?key=YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "contents": [{"parts": [{"text": "Hello"}]}]
  }'

# Bash retry loop with backoff
MAX=5; WAIT=1
for i in $(seq 1 $MAX); do
  STATUS=$(curl -s -o /tmp/gemini_resp.json -w "%{http_code}" \
    -X POST "https://generativelanguage.googleapis.com/v1beta/models/gemini-2.0-flash:generateContent?key=$GOOGLE_API_KEY" \
    -H "Content-Type: application/json" \
    -d '{"contents":[{"parts":[{"text":"Hello"}]}]}')
  [ "$STATUS" = "200" ] && break
  echo "Attempt $i failed ($STATUS). Sleeping ${WAIT}s..."
  sleep $WAIT; WAIT=$((WAIT * 2))
done
cat /tmp/gemini_resp.json

Enable billing (removes most free tier limits)

1. Open console.cloud.google.com → Billing
2. Link a billing account to your project
3. On paid tier, gemini-2.0-flash automatically goes from 15 RPM to 2,000 RPM
4. You are charged per token — gemini-2.0-flash costs $0.075 / 1M input tokens

Request a quota increase

1. Go to console.cloud.google.com → APIs & Services → Generative Language API → Quotas & System Limits
2. Find the specific metric you need more of (e.g., GenerateContent requests per minute per project)
3. Click the pencil icon → enter the new limit → Submit Request
4. Quota increase requests require an active billing account and are typically approved within 2 business days