onomeoonomeoBeta
Feedback

qwen3.5-397b-a17b

By Qwen

Reads images: a question can carry pictures.

Model name for the APIqwen3.5-397b-a17b

qwen3.5-397b-a17b is paused.It is switched off for now and cannot be called. The figures on this page are the latest this site has for it, and it returns to the model list once it is back on.

Uptime, last 3 days
75%
32 calls counted
Price per reply
Free
Limited by number of calls

Your chats and training

The provider does not say.

Nothing in that company’s published terms says whether prompts are used for training. Treat it as if they might be.

Which company answers for a model is not published here, so this says what the policy is, not whose it is. Checked against their terms on Sep 28, 2026.

Model facts

Context length
256K tokens
Longest reply
64K tokens
Calls tools
Yes
Knowledge cutoff
Jan 2025
Released
1 Feb 2026
Open weights
Yes

Context, reply length, tool calling, knowledge cutoff, release date and open weights come from the models.dev open dataset, read once a day.

Use in chatAPI docs

This model has been failing often lately. You can use instead:autodeepseek-v4-pro

Call it through the API

Any OpenAI-compatible client works: use the address in the sample and this model name.

import requests

response = requests.post(
    "https://onomeo.com/v1/chat/completions",
    headers={"Authorization": "Bearer YOUR_API_KEY"},
    json={"model": "qwen3.5-397b-a17b", "messages": [
        {"role": "user", "content": "Hello!"}
    ]}
)
print(response.json())

More from Qwen

  1. qwen3.8-flash-nextFree66% up, last 3 days
  2. qwen3.8-27bFree64% up, last 3 days
  3. qwen3.8-max—No record yet

Other free models

  1. muse-glimmer-30bFree100% up, last 3 days
  2. ministral-14b-latestFree100% up, last 3 days
  3. minimax-m2.7Free64% up, last 3 days
  4. hy4-previewFree97% up, last 3 days
  5. gpt-oss-20bFree99% up, last 3 days
  6. glm-5.3-flashFree79% up, last 3 days

qwen3.5-397b-a17b against other models

Figures come from real calls made through this site. Models are served by third-party providers and may slow down or be withdrawn; this page follows those changes.