Together AI
qwen/qwen3-next-80b-a3b-thinking model retirement
Stopped workingSubscribe to Together AIShare
Calls to the model qwen/qwen3-next-80b-a3b-thinking on Together AI stopped working on February 25, 2026.
What to use instead of qwen/qwen3-next-80b-a3b-thinking
Move to Qwen/Qwen3.5-122B-A10B, recommended by Together AI.
In Together AI's words
Removal date: 2026-02-25; Model: Qwen/Qwen3-Next-80B-A3B-Thinking; Supported by on-demand dedicated endpoints: No
Facts
- API
- Together AI
api.together.xyz - Model
qwen/qwen3-next-80b-a3b-thinking- Released
- September 2025 (models.dev)
- Kind
- Model retirement
- Takes effect
- February 25, 2026
- Calls after that day
- Fail
- Source
- Deprecations page
- Last updated
- Verified
- , against Together AI's own pages
Questions
When does qwen/qwen3-next-80b-a3b-thinking shut down?
Calls to the model qwen/qwen3-next-80b-a3b-thinking on Together AI stopped working on February 25, 2026.
What happens to calls after February 25, 2026?
They have failed since February 25, 2026.
When was qwen/qwen3-next-80b-a3b-thinking released?
qwen/qwen3-next-80b-a3b-thinking was released on September 2025, 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.
qwen/qwen3-next-80b-a3b-thinking on other APIs 3
-
Novita AI
qwen/qwen3-next-80b-a3b-thinkingModel retirement Stopped working -
Nebius
qwen/qwen3-next-80b-a3b-thinkingModel retirement Stopped working -
No date
Alibaba Model Studio
qwen3-next-80b-a3b-thinkingModel retirement Deprecated, no date
More from Together AI 10
-
alibaba-nlp/gte-modernbert-baseModel retirement Stopped working -
baai/bge-base-en-v1.5-vllmModel retirement Stopped working -
black-forest-labs/flux.1-devModel retirement Stopped working -
black-forest-labs/flux.1-dev-loraModel retirement Stopped working -
black-forest-labs/flux.1-kontext-devModel retirement Stopped working -
marin-community/marin-8b-instructModel retirement Stopped working -
meta-llama/llama-3.2-3b-instruct-turbo-classifierModel retirement Stopped working -
meta-llama/llama-guard-3-11b-vision-turboModel retirement Stopped working -
meta-llama/llamaguard-2-8bModel retirement Stopped working -
meta-llama/meta-llama-3.1-70b-instruct-turboModel 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.