Skip to content
AI Dev Toolkit.
Esc
  • AI Token CounterCount tokens for GPT, Claude, Gemini, DeepSeek, Qwen and more.Tool
  • LLM API Cost CalculatorEstimate per-request, daily and monthly API costs.Tool
  • AI Model ComparisonCompare prices, context windows and features across models.Tool
  • AI Model Pricing PagesSpecs, real costs and cheaper alternatives for popular models.Tool
  • Context Window CheckerSee whether your text fits each model's context window.Tool
  • Subscription vs API CalculatorFind out whether a chat plan or the API is cheaper for you.Tool
  • GPU / VRAM CalculatorCheck how much VRAM a local model needs and which GPUs fit.Tool
  • Claude Code Error DatabaseExact Claude Code error messages with tested fixes.Tool

Claude Code · Server and limits

API Error: Request rejected (429)

You hit the rate limit of the API key, Bedrock project or Google Cloud project Claude Code is using.

Message

The exact error

Claude Code
API Error: Request rejected (429) · this may be a temporary capacity issue. If it persists, check https://status.claude.com.

Also appears as:

A short-lived server throttle (not your plan limit)
API Error: Server is temporarily limiting requests (not your usage limit)

Meaning

What it means

A 429 means too many requests or tokens in a short time for the credential in use. On the Anthropic API, rate limits depend on your key’s usage tier. A common surprise is that Claude Code is using an ANTHROPIC_API_KEY from your environment, with its low limits, instead of your subscription.

Causes

Common causes

  • Your API key’s tier limits (requests or tokens per minute)
  • A stray ANTHROPIC_API_KEY in your environment taking priority over your subscription
  • Many parallel subagents or tool calls at once

Fix

How to fix it

  1. Check which credential is in use

    Run /status. If it shows an API key you didn’t intend, unset ANTHROPIC_API_KEY and run /login to use your subscription.

  2. Check or raise your limits

    See your limits in the provider console. For Anthropic keys, the rate limits reference explains how tiers rise with usage.

  3. Reduce concurrency

    Run fewer subagents in parallel, lower CLAUDE_CODE_MAX_TOOL_USE_CONCURRENCY, or use a smaller model for high-volume scripted runs.

Related

Related errors

Search all Claude Code errors