Should I retry Anthropic 504 timeout_error?

Yes, with exponential backoff and jitter. Stream the response for long outputs; the SDK can collect the stream into a final message for you.

AI API errors / Anthropic (Claude)

Anthropic (Claude) · HTTP 504 · checked Oct 24, 2026

Anthropic 504 timeout_error: what it means and how to fix it

Retry: yes, with backoff

504 timeout_error

What it meansThe request took too long while processing. Long non-streaming requests with a large max_tokens are the usual cause.

How to fix it

Stream the response for long outputs; the SDK can collect the stream into a final message for you.
Use the Message Batches API for very long jobs.
Enable TCP keep-alive if you call the API directly.

Is it down right now?

Check our live status page or the official one.

Retry it properly

import anthropic

# The SDK retries 429, 5xx and connection errors with exponential backoff and honors retry-after.
client = anthropic.Anthropic(max_retries=6)

try:
    msg = client.messages.create(model="claude-sonnet-5-5", max_tokens=1024,
                                 messages=[{"role": "user", "content": "Hello"}])
except anthropic.RateLimitError as e:      # 429 after all retries
    print("still rate limited", e.response.headers.get("retry-after"))
except anthropic.APIStatusError as e:      # 529 overloaded, 500, 504...
    print(e.status_code, e.response.headers.get("request-id"))

The official SDKs already retry connection errors, 429 and 5xx twice with exponential backoff and honor retry-after; raise max_retries for batch jobs.

Same kind of error at other providers

Other Anthropic (Claude) errors

Source

Anthropic (Claude) error documentation: platform.claude.com/docs/en/api/errors (checked Oct 24, 2026)

Paying too much per call while you are here? Compare AI model prices or estimate your bill.

Up next

Paste any errorEvery AI API error, retry or fixAnthropic, OpenAI and Gemini in one finder.Read it next →

Also worth your time

Did this answer your question?