xtekky/gpt4free · error · RateLimitError

The Qwen provider reached the request limit after 5 attempts

Error message

The Qwen provider reached the request limit after 5 attempts.

What it means

Raised as RateLimitError when Qwen's internal retry loop (5 attempts, 2s sleeps, midtoken invalidation each time) still encounters rate-limit failures — every attempt was a 429 ClientResponseError or a RuntimeError containing 'RateLimited'. The provider gives up rather than loop forever; only ~10s of backoff has elapsed, so the underlying limit is still in force.

Source

Thrown at g4f/Provider/Qwen.py:727

                            yield Usage.from_dict(usage)
                        return

                except (aiohttp.ClientResponseError, RuntimeError) as e:
                    is_rate_limit = (
                        isinstance(e, aiohttp.ClientResponseError) and e.status == 429
                    ) or ("RateLimited" in str(e))
                    if is_rate_limit:
                        debug.log(
                            f"[Qwen] WARNING: Rate limit detected (attempt {attempt + 1}/5). Invalidating current midtoken."
                        )
                        cls._midtoken = None
                        cls._midtoken_uses = 0
                        conversation = None
                        await asyncio.sleep(2)
                        continue
                    else:
                        raise e
            raise RateLimitError(
                "The Qwen provider reached the request limit after 5 attempts."
            )
        raise RateLimitError("The Qwen provider reached the limit Cloudflare.")

View on GitHub (pinned to 973504e177)

Solutions

1. Wait minutes-to-hours before retrying (quota windows), not seconds — the 5x2s internal backoff is far too short for hard limits.
2. Change egress IP / rotate proxy so the IP-based component resets.
3. Reduce request frequency and concurrency to stay under the free tier.
4. Update g4f; retry cadence and identity handling are tuned upstream.

Example fix

# before
for i in range(100):
    r = await Qwen.create_async_generator(model, msgs[i])

# after
from g4f.errors import RateLimitError
for i in range(100):
    while True:
        try:
            r = await Qwen.create_async_generator(model, msgs[i])
            break
        except RateLimitError:
            await asyncio.sleep(600)  # wait out the quota window

def is_qwen_rate_limit(exc: Exception) -> bool:
    from g4f.errors import RateLimitError
    return isinstance(exc, RateLimitError) and 'request limit after 5 attempts' in str(exc)

from g4f.errors import RateLimitError
try:
    r = await Qwen.create_async_generator(model, msgs)
except RateLimitError as e:
    if 'after 5 attempts' in str(e):
        await asyncio.sleep(600)  # quota window, not 2s
        r = await Qwen.create_async_generator(model, msgs)
    else:
        raise

When it happens

Trigger: Sustained 429s from chat.qwen.ai: free-tier hourly/daily quota exhausted, IP-based throttling, or bursts of requests from one cookie identity across all 5 attempts.

Common situations: Bots hammering Qwen anonymously; quota already spent before this call; shared/datacenter IP throttled; retrying immediately after this error without waiting, re-entering the same loop.

Related errors

• {data['code']}:{data['details']}
• Response: {resp_json}
• {error["code"]}: {error["details"]}
• The Qwen provider reached the limit Cloudflare.
• {chunk_text}

AI-assisted analysis of xtekky/gpt4free@973504e177 (2026-08-14). Data as JSON: /api/errors/6c393b84c1d6ba04. Report an issue: GitHub.