xtekky/gpt4free · error · RateLimitError

{data['code']}:{data['details']}

Error message

{data['code']}:{data['details']}

What it means

Raised as RateLimitError during Qwen's file registration step: the POST that registers filename/size/type returned success=false with code and details fields (raise_for_status passed, so HTTP was 2xx but the API refused). The embedded 'code:details' string names the upstream reason — commonly quota, file-type, or rate limits.

Source

Thrown at g4f/Provider/Qwen.py:334

            file_name = file_name or f"file-{len(data_bytes)}{extension}"
            file_size = len(data_bytes)

            # Get File Url
            async with session.post(
                f"{cls.url}/api/v2/files/getstsToken",
                json={
                    "filename": file_name,
                    "filesize": file_size,
                    "filetype": file_type,
                },
                headers=headers,
            ) as r:
                await raise_for_status(r, "Create file failed")
                res_data = await r.json()
                data = res_data.get("data")

                if res_data["success"] is False:
                    raise RateLimitError(f"{data['code']}:{data['details']}")
                file_url = data.get("file_url")
                file_id = data.get("file_id")

            # Put File into Url
            str_date = datetime.datetime.now(datetime.timezone.utc).strftime(
                "%Y%m%dT%H%M%SZ"
            )
            headers_put = get_oss_headers("PUT", str_date, data, file_type)
            async with session.put(
                file_url.split("?")[0], data=data_bytes, headers=headers_put
            ) as response:
                await raise_for_status(response)

            file_class: Literal["default", "vision", "video", "audio", "document"]
            _type: Literal["file", "image", "video", "audio"]
            show_type: Literal["file", "image", "video", "audio"]
            if "image" in file_type:
                _type = "image"

View on GitHub (pinned to 973504e177)

Solutions

1. Read the embedded code:details — 'rate limit' means wait/retry; quota means clean up uploaded files on chat.qwen.ai or wait for reset.
2. Reduce number/size of attachments per request.
3. Retry after a delay; the outer loop invalidates state but file quota errors need time.
4. Update g4f for current Qwen API behavior.

Example fix

# before
resp = await Qwen.create_async_generator(model, msgs, media=[('big.png', png_bytes), ('big2.png', png2_bytes)])

# after - one attachment, retry on RateLimitError
for attempt in range(3):
    try:
        resp = await Qwen.create_async_generator(model, msgs, media=[('big.png', png_bytes)])
        break
    except RateLimitError:
        await asyncio.sleep(60)

from pathlib import Path

def qwen_file_ok(name: str, size: int) -> bool:
    return Path(name).suffix.lower() in {'.png','.jpg','.jpeg','.pdf','.txt','.md'} and size <= 20*1024*1024

from g4f.errors import RateLimitError
try:
    resp = await Qwen.create_async_generator(model, msgs, media=media)
except RateLimitError as e:
    if 'file' in str(e).lower() or ':' in str(e):
        await asyncio.sleep(120)
        resp = await Qwen.create_async_generator(model, msgs, media=media)
    else:
        raise

When it happens

Trigger: Calling Qwen with media attachments when chat.qwen.ai's create-file API rejects the registration: free-tier file quota exhausted, too many uploads in a short window, unsupported file type, or invalid/expired cookies making the API refuse instead of 401.

Common situations: Repeated runs uploading the same files (quota accumulates); anonymous cookie jar (generate_cookies) flagged; large batches of media; g4f's OSS upload flow out of sync with API changes.

Related errors

• The Qwen provider reached the request limit after 5 attempts
• Failed to upload file: {res_json}
• Upload failed: {result}
• Response: {resp_json}
• {error["code"]}: {error["details"]}

AI-assisted analysis of xtekky/gpt4free@973504e177 (2026-08-14). Data as JSON: /api/errors/832939dd2ef360a4. Report an issue: GitHub.