DeepInfra
qwen/qwen3-max-thinking model retirement
Stopped workingSubscribe to DeepInfraShare
DeepInfra retired model qwen/qwen3-max-thinking on October 10, 2026. Calls targeting this model fail since that date. The change affects any integrations configured to use this specific model identifier on api.deepinfra.com.
What to use instead of qwen/qwen3-max-thinking
Move to Qwen/Qwen3.8-Max, which is recommended by DeepInfra.
Facts
- API
- DeepInfra
api.deepinfra.com - Model
qwen/qwen3-max-thinking- Released
- January 23, 2026 (models.dev)
- Kind
- Model retirement
- Takes effect
- October 10, 2026
- Calls after that day
- Fail
- Source
- Model list
- Last updated
- Verified
- , against DeepInfra's own pages
Questions
When does qwen/qwen3-max-thinking shut down?
Calls to the model qwen/qwen3-max-thinking on DeepInfra stopped working on October 10, 2026.
What happens to calls after October 10, 2026?
They have failed since October 10, 2026.
When was qwen/qwen3-max-thinking released?
qwen/qwen3-max-thinking was released on January 23, 2026, according to models.dev.
How do I find the calls this hits in my code?
Okapi reads your repository, finds the calls this change hits and opens a pull request with the fix. It never commits to your branches: every change comes as a pull request you review.
More from DeepInfra 10
-
black-forest-labs/flux.1-kontext-devModel retirement Stopped working -
deepseek-ai/janus-pro-1bModel retirement Stopped working -
deepseek-ai/janus-pro-7bModel retirement Stopped working -
nvidia/nemotron-3-nano-30b-a3bModel retirement Stopped working -
nvidia/nvidia-nemotron-nano-9b-v2Model retirement Stopped working -
qwen/qwen-image-editModel retirement Stopped working -
tencent/hy3Model retirement Stopped working -
inclusionai/ling-3.0-flash-finModel retirement Stopped working -
qwen/qwen3-maxModel retirement Stopped working -
qwen/qwen3.8-2.4t-a95bModel retirement Stopped working
You fixed this one by hand.
Okapi opens the pull request with the fix before the next breaking change reaches your code.