Together AI
deepseek-ai/deepseek-r1-distill-llama-70b-131k model retirement
Stopped workingSubscribe to Together AIShare
On July 29, 2026, Together AI retired the model deepseek-ai/deepseek-r1-distill-llama-70b-131k. Calls targeting this model fail since that date.
What to use instead of deepseek-ai/deepseek-r1-distill-llama-70b-131k
Move to meta-llama/Llama-3.3-70B-Instruct-Reference, recommended by Together AI.
In Together AI's words
Removal date: 2026-07-29; Model: deepseek-ai/DeepSeek-R1-Distill-Llama-70B-131k; Suggested replacement: meta-llama/Llama-3.3-70B-Instruct-Reference
Facts
- API
- Together AI
api.together.xyz - Model
deepseek-ai/deepseek-r1-distill-llama-70b-131k- Kind
- Model retirement
- Takes effect
- July 29, 2026
- Calls after that day
- Fail
- Source
- Deprecations page
- Last updated
- Verified
- , against Together AI's own pages
Questions
When does deepseek-ai/deepseek-r1-distill-llama-70b-131k shut down?
Calls to the model deepseek-ai/deepseek-r1-distill-llama-70b-131k on Together AI stopped working on July 29, 2026.
What happens to calls after July 29, 2026?
They have failed since July 29, 2026.
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 Together AI 10
-
deepseek-ai/deepseek-r1-0528Model retirement Stopped working -
deepseek-ai/deepseek-r1-distill-llama-70b-32kModel retirement Stopped working -
deepseek-ai/deepseek-v3Model retirement Stopped working -
deepseek-ai/deepseek-v3-0324Model retirement Stopped working -
deepseek-ai/deepseek-v3-baseModel retirement Stopped working -
deepseek-ai/deepseek-v3.1-baseModel retirement Stopped working -
google/gemma-3-12b-itModel retirement Stopped working -
google/gemma-3-12b-it-vlmModel retirement Stopped working -
google/gemma-3-12b-ptModel retirement Stopped working -
google/gemma-3-1b-itModel 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.