xtekky/gpt4free · error · ResponseStatusError

Response {response.status_code}: Bad Gateway

Error message

Response {response.status_code}: Bad Gateway

What it means

Sync variant: upstream HTTP 502 Bad Gateway becomes ResponseStatusError. The provider's gateway could not reach its backend; unrelated to your request payload.

Source

Thrown at g4f/requests/raise_for_status.py:114

    is_html = False
    if message is None:
        is_html = response.headers.get("content-type", "").startswith(
            "text/html"
        ) or response.text.startswith("<!DOCTYPE")
        message = response.text
    if message is None or is_html:
        if response.status_code == 520:
            message = "Unknown error (Cloudflare)"
    if response.status_code in (429, 402):
        raise RateLimitError(f"Response {response.status_code}: {message}")
    if response.status_code == 401:
        raise MissingAuthError(f"Response {response.status_code}: {message}")
    if response.status_code == 403 and is_cloudflare(response.text):
        raise CloudflareError(f"Response {response.status_code}: Cloudflare detected")
    elif response.status_code == 403 and is_openai(response.text):
        raise MissingAuthError(f"Response {response.status_code}: OpenAI Bot detected")
    elif response.status_code == 502:
        raise ResponseStatusError(f"Response {response.status_code}: Bad Gateway")
    elif response.status_code == 504:
        raise RateLimitError(f"Response {response.status_code}: Gateway Timeout ")
    elif response.status_code == 400 and "API key not valid" in message:
        raise MissingAuthError(f"Response {response.status_code}: Invalid API key")
    else:
        raise ResponseStatusError(
            f"Response {response.status_code}: {'HTML content' if is_html else message}"
        )

View on GitHub (pinned to 973504e177)

Solutions

1. Retry after a short delay.
2. Fail over to another provider.
3. Check provider status pages for incidents.
4. Wrap calls with a bounded retry loop for 5xx.

from g4f.errors import ResponseStatusError, CloudflareError, RateLimitError
def is_bad_gateway(err: BaseException) -> bool:
    return isinstance(err, ResponseStatusError) and not isinstance(err, (CloudflareError, RateLimitError)) and 'Bad Gateway' in str(err)

from g4f.errors import ResponseStatusError
import time
for attempt in range(3):
    try:
        resp = g4f.ChatCompletion.create(model, messages)
        break
    except ResponseStatusError as e:
        if 'Bad Gateway' not in str(e):
            raise
        time.sleep(2 ** attempt)

When it happens

Trigger: Synchronous g4f provider calls during backend outages or proxy failures that return 502.

Common situations: Provider maintenance windows; overloaded free providers; transient proxy errors.

Understand the failure class

• HTTP status errors: handling 4xx and 5xx responses — how to handle 4xx and 5xx responses properly.

Related errors

• Response {response.status}: Bad Gateway
• LMArena Beta encountered an error: hasArenaError
• Install "websocket-client" package: pip install websocket-cl
• Response {response.status_code}: {message}
• Response {response.status_code}: Cloudflare detected

AI-assisted analysis of xtekky/gpt4free@973504e177 (2026-08-14). Data as JSON: /api/errors/a4f70a1773ac83f6. Report an issue: GitHub.