Anthropic Common Errors

Overview

Quick reference for all Claude API error types with exact HTTP codes, error bodies, and fixes. The API returns errors as JSON: {"type": "error", "error": {"type": "...", "message": "..."}}.

Error Reference

400 — invalidrequesterror

{"type": "error", "error": {"type": "invalid_request_error", "message": "messages: roles must alternate between \"user\" and \"assistant\""}}

Common causes and fixes:

401 — authentication_error

# Verify your key is set and valid
echo $ANTHROPIC_API_KEY | head -c 15  # Should show: sk-ant-api03-...

# Test directly with curl
curl -s https://api.anthropic.com/v1/messages \
  -H "x-api-key: $ANTHROPIC_API_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -H "content-type: application/json" \
  -d '{"model":"claude-sonnet-4-20250514","max_tokens":16,"messages":[{"role":"user","content":"hi"}]}'

403 — permission_error

API key lacks required permissions. Generate a new key at console.anthropic.com.

404 — notfounderror

Invalid endpoint or model. Check you're using https://api.anthropic.com/v1/messages and a valid model ID.

429 — ratelimiterror

{"type": "error", "error": {"type": "rate_limit_error", "message": "Number of request tokens has exceeded your per-minute rate limit"}}

Check headers for details:

• retry-after — seconds to wait
• anthropic-ratelimit-requests-limit — RPM cap
• anthropic-ratelimit-tokens-limit — TPM cap
• anthropic-ratelimit-tokens-remaining — tokens left this window

Fix: The SDK handles 429 with automatic retry (configurable via maxRetries). For manual handling, see anth-rate-limits.

529 — overloaded_error

API is temporarily overloaded. Retry after 30-60 seconds. Not counted against rate limits.

500 — api_error

Internal server error. Retry with exponential backoff. If persistent, check status.anthropic.com.

Quick Diagnostic Script

# 1. Check API status
curl -s https://status.anthropic.com/api/v2/status.json | python3 -c "import sys,json; d=json.load(sys.stdin); print(d['status']['description'])"

# 2. Verify key format
echo $ANTHROPIC_API_KEY | grep -qE '^sk-ant-api03-' && echo "Key format OK" || echo "Key format WRONG"

# 3. Test minimal request
curl -s -w "\nHTTP %{http_code}" https://api.anthropic.com/v1/messages \
  -H "x-api-key: $ANTHROPIC_API_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -H "content-type: application/json" \
  -d '{"model":"claude-sonnet-4-20250514","max_tokens":8,"messages":[{"role":"user","content":"1+1="}]}'

SDK Error Handling

import anthropic

try:
    message = client.messages.create(...)
except anthropic.AuthenticationError as e:
    print(f"Auth failed: {e.status_code}")
except anthropic.RateLimitError as e:
    print(f"Rate limited. Retry after: {e.response.headers.get('retry-after')}s")
except anthropic.BadRequestError as e:
    print(f"Invalid request: {e.message}")
except anthropic.APIStatusError as e:
    print(f"API error {e.status_code}: {e.message}")
except anthropic.APIConnectionError:
    print("Network error — check connectivity")

Resources

• Error Types Reference
• Rate Limits
• API Status

Next Steps

For comprehensive debugging, see anth-debug-bundle.