Novita AI
deepseek/deepseek-v4-flash model retirement
Stopped workingSubscribe to Novita AIShare
Novita AI retired model deepseek/deepseek-v4-flash on October 9, 2026. Calls requesting this model fail since that date. The change affects any requests still directed to the retired model identifier.
What to use instead of deepseek/deepseek-v4-flash
Update your calls to use the recommended replacement model, deepseek/deepseek-v4.1-flash.
In Novita AI's words
Model ID: deepseek/deepseek-v4-flash; Retirement time: Oct 9, 2026, 16:00 UTC; Replacement model: deepseek/deepseek-v4.1-flash
Facts
- API
- Novita AI
api.novita.ai - Model
deepseek/deepseek-v4-flash- Released
- April 24, 2026 (models.dev)
- Kind
- Model retirement
- Takes effect
- October 9, 2026
- Calls after that day
- Fail
- Source
- Model notices
- Last updated
- Verified
- , against Novita AI's own pages
Questions
When does deepseek/deepseek-v4-flash shut down?
Calls to the model deepseek/deepseek-v4-flash on Novita AI stopped working on October 9, 2026.
What happens to calls after October 9, 2026?
They have failed since October 9, 2026.
When was deepseek/deepseek-v4-flash released?
deepseek/deepseek-v4-flash was released on April 24, 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.
deepseek/deepseek-v4-flash on other APIs 5
-
Nebius
deepseek-ai/deepseek-v4-flashModel retirement Stopped working -
Azure AI Foundry
deepseek-v4-flashModel retirement Stops workingin 471 days -
No date
OpenCode
deepseek-v4-flashModel retirement Deprecated, no date -
No date
Alibaba Model Studio
deepseek-v4-flashModel retirement Deprecated, no date -
No date
Tinfoil
deepseek-v4-flashModel retirement Deprecated, no date
More from Novita AI 10
-
baidu/ernie-4.5-vl-424b-a47bModel retirement Stopped working -
deepseek/deepseek-v4-flash-vision-expModel retirement Stopped working -
minimax/minimax-m2Model retirement Stopped working -
minimax/minimax-m2.1Model retirement Stopped working -
minimax/minimax-m2.5-highspeedModel retirement Stopped working -
mistralai/mistral-nemoModel retirement Stopped working -
openai/gpt-oss-20bModel retirement Stopped working -
qwen/qwen-2.5-72b-instructModel retirement Stopped working -
qwen/qwen3-235b-a22b-fp8Model retirement Stopped working -
qwen/qwen3-235b-a22b-instruct-2507Model 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.