claude-ratelimit-requests-limit: 1000
claude-ratelimit-requests-remaining: 998
claude-ratelimit-requests-reset: 2025-01-01T00:01:00Z
claude-ratelimit-tokens-limit: 80000
claude-ratelimit-tokens-remaining: 79500
claude-ratelimit-tokens-reset: 2025-01-01T00:01:00Z
retry-after: 5

import Anthropic from '@claude-ai/sdk';

const client = new Anthropic({
  maxRetries: 3, // default: 2. Set to 0 to disable.
});

async function callWithBackoff(params: Anthropic.MessageCreateParams, maxRetries = 5) {
  for (let attempt = 0; attempt < maxRetries; attempt++) {
    try {
      return await client.messages.create(params);
    } catch (err) {
      if (err instanceof Anthropic.RateLimitError) {
        const retryAfter = Number(err.headers?.['retry-after'] || 2 ** attempt);
        const jitter = Math.random() * 1000;
        console.log(`Rate limited. Retry in ${retryAfter}s (attempt ${attempt + 1})`);
        await new Promise(r => setTimeout(r, retryAfter * 1000 + jitter));
      } else {
        throw err;
      }
    }
  }
  throw new Error('Exceeded max retries');
}

// Count before sending — avoid burning RPM on requests that'll fail
const count = await client.messages.countTokens({
  model: 'claude-sonnet-4-20250514',
  messages,
  system: systemPrompt,
});
console.log(`This request will use ${count.input_tokens} input tokens`);

import anthropic
import time

client = anthropic.Anthropic(max_retries=5)

# Or manual handling:
try:
    message = client.messages.create(...)
except anthropic.RateLimitError as e:
    retry_after = float(e.response.headers.get("retry-after", 5))
    time.sleep(retry_after)