#8255 身份验证失败。https://open.bigmodel.cn/api/paas/v4/

85.255**3 Posted at: 2 hours ago

身份验证失败。
https://open.bigmodel.cn/api/paas/v4/
{'model': 'glm-5.3', 'timeout': 300, 'temperature': 0.1, 'max_tokens': 16384}
{'thinking': {'type': 'enabled'}}:Traceback (most recent call last):
File "videotrans\translator\_openaicompat.py", line 90, in _item_task
File "videotrans\translator\_openaicompat.py", line 40, in _create_completion
File "openai\_utils\_utils.py", line 298, in wrapper
File "openai\resources\chat\completions\completions.py", line 1215, in create
File "openai\_base_client.py", line 1332, in post
File "openai\_base_client.py", line 1105, in request
openai.AuthenticationError: Error code: 401 - {'error': {'code': '1000', 'message': '身份验证失败。'}}

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
File "videotrans\util\TestSrtTrans.py", line 19, in run
File "videotrans\translator\_runner.py", line 71, in run
File "videotrans\translator\_base.py", line 82, in run
File "videotrans\translator\_base.py", line 165, in _run_srt
File "tenacity\__init__.py", line 338, in wrapped_f
File "tenacity\__init__.py", line 477, in call
File "tenacity\__init__.py", line 378, in iter
File "tenacity\__init__.py", line 400, in
File "concurrent\futures\_base.py", line 451, in result
File "concurrent\futures\_base.py", line 403, in __get_result
File "tenacity\__init__.py", line 480, in call
File "videotrans\translator\_openaicompat.py", line 101, in _item_task
videotrans.configure.excepts.StopTask: 身份验证失败。
https://open.bigmodel.cn/api/paas/v4/
{'model': 'glm-5.3', 'timeout': 300, 'temperature': 0.1, 'max_tokens': 16384}
{'thinking': {'type': 'enabled'}}


=
system:Windows-10-10.0.26300-SP0
version:v4.16
frozen:True
language:en_US
root_dir:C:/Users/rajamoiz/Desktop/dub software

1 Replies

#1 DeepSeek reply at 2 hours ago

This is not a software bug. The HTTP 401 error code 1000 "身份验证失败" returned by Zhipu AI (open.bigmodel.cn) indicates that the API Key itself was rejected: the key is missing, invalid, expired, revoked, or was pasted incorrectly into the wrong settings field. The model parameters (glm-5.3, max_tokens, thinking) and the request body are irrelevant here, because authentication fails before any inference runs.

Step-by-step resolution

  1. Re-copy the full key
    Log in to https://open.bigmodel.cn → API Keys. Zhipu keys typically have the form {id}.{secret}. Copy the complete string; it is very easy to miss the part after the dot, or to copy a stray space or newline. Then paste it again into the software.
  2. Confirm you are pasting into the correct field
    In the software, go to Menu → Translation Settings → 智谱AI (ZhipuAI) and paste the key there.
    Do not paste it into the OpenAI / OpenAI-compatible field, because that field calls a different endpoint and will also return 401.
  3. Check key status on the platform

    • Confirm that the key has not been deleted, disabled, or regenerated. If you generated a new key in the console, the old one is immediately invalidated and must be re-entered here.
    • Confirm that the account has an active resource package or remaining quota. An unfunded or suspended account can also fail authentication.
    • Confirm that the key belongs to the same account or organization that has access to the model you selected.
  4. Fix the model name
    glm-5.3 may not be an available model for your account. In the channel settings window, open the model dropdown and select an actually available model (for example, the glm-4 series listed there) instead of typing a name manually. Manually typed model names that do not exist for your account will cause failures.
  5. Do not use a proxy for this channel
    open.bigmodel.cn is a domestic Chinese API and is on the software's built-in no_proxy whitelist. If you filled a proxy in the proxy field on the main interface, clear it and retry. An invalid proxy address will make every request fail.
  6. Retry the test
    In the settings window, click Test (or Save and then re-run the translation test). The 401 should disappear once authentication succeeds.
Note: Thinking is enabled with max_tokens: 16384. This is fine, but once authentication is fixed, keep max_tokens sufficiently large; otherwise thinking mode will be truncated and you may get Could not parse response content.

If the error persists after confirming that the key is correct and active, the 401 would then have to come from the platform side (account restriction or region limitation). In that case, contact Zhipu platform support with your key ID, or switch the translation channel to DeepSeek.

请查阅相关文档:

Thinking...
Post Your Reply
If you have more than 50 messages, you will no longer receive an automatic reply. Please ask a new question!
Open source and free maintenance is not easy. If this project is helpful to you, please consider making a small donation to help the project continue to maintain and update.

Dondate via ko-fi.com

Related resource