Together AI
thinkingmachines/inkling model retirement
Stopped workingSubscribe to Together AIShare
On November 6, 2026, Together AI retired model thinkingmachines/inkling. Requests targeting this model fail as of that date.
What to use instead of thinkingmachines/inkling
Update your requests to use meta-models/Muse-Spark-Open-816B-A42B, which is the replacement recommended by Together AI.
In Together AI's words
Removal date: 2026-11-06; Model: thinkingmachines/Inkling; Recommended replacement: meta-models/Muse-Spark-Open-816B-A42B; Supported by on-demand dedicated endpoints: Yes
Facts
- API
- Together AI
api.together.xyz - Model
thinkingmachines/inkling- Released
- July 15, 2026 (models.dev)
- Kind
- Model retirement
- Takes effect
- November 6, 2026
- Calls after that day
- Fail
- Source
- Deprecations page
- Last updated
- Verified
- , against Together AI's own pages
Questions
When does thinkingmachines/inkling shut down?
Calls to the model thinkingmachines/inkling on Together AI stopped working on November 6, 2026.
What happens to calls after November 6, 2026?
They have failed since November 6, 2026.
When was thinkingmachines/inkling released?
thinkingmachines/inkling was released on July 15, 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.
thinkingmachines/inkling on other APIs 4
-
DeepInfra
thinkingmachines/inklingModel retirement Stopped working -
No date
Fireworks AI
accounts/fireworks/models/inklingModel retirement Deprecated, no date -
No date
api.venice.ai
InklingModel retirement Deprecated, no date -
No date
DeepInfra
thinkingmachines/inklingModel retirement Deprecated, no date
More from Together AI 10
-
google/gemma-4-31b-itModel retirement Stopped working -
deepseek-ai/deepseek-v4-flash-0731Model retirement Stopped working -
meta-llama/llama-3.3-70b-instruct-turboModel retirement Stopped working -
qwen/qwen3.8-2.4t-a95bModel retirement Stopped working -
deepseek-r1Model retirement Redirected -
deepseek-v3Model retirement Redirected -
deepseek-v3-0324Model retirement Redirected -
kimi-k2Model retirement Redirected -
minimaxai/minimax-m3Model retirement Stopped working -
mistralai/mistral-7b-instruct-v0.3Model retirement Redirected
You fixed this one by hand.
Okapi opens the pull request with the fix before the next breaking change reaches your code.