DeepInfra
stepfun-ai/step-5-preview model retirement
Stopped working
DeepInfra will retire the model stepfun-ai/step-5-preview on October 29, 2026. After this date, calls using model stepfun-ai/step-5-preview will fail.
What to use instead of stepfun-ai/step-5-preview
Move to zai-org/GLM-5.3-Flash, which is recommended by DeepInfra.
Facts
- API
- DeepInfra
api.deepinfra.com - Model
stepfun-ai/step-5-preview- Kind
- Model retirement
- Takes effect
- October 29, 2026
- Calls after that day
- Fail
- Source
- Model list
- Last updated
- Verified
- , against DeepInfra's own pages
Questions
When does stepfun-ai/step-5-preview shut down?
Calls to the model stepfun-ai/step-5-preview on DeepInfra stopped working on October 29, 2026.
What happens to calls after October 29, 2026?
They have failed since October 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 DeepInfra 10
-
ibm-granite/granite-4.2-30bModel retirement Stopped working -
openai/gpt-oss-120b-turboModel retirement Stopped working -
thinkingmachines/inklingModel retirement Stopped working -
black-forest-labs/flux-1-redux-devModel retirement Stopped working -
bria/fiboModel retirement Stopped working -
bria/fibo-1.5Model retirement Stopped working -
gryphe/mythomax-l2-13bModel retirement Stopped working -
nousresearch/hermes-3-llama-3.1-405bModel retirement Stops workingin 4 days -
nousresearch/hermes-3-llama-3.1-70bModel retirement Stops workingin 4 days -
meta-llama/meta-llama-3.1-70b-instruct-turboModel retirement Stops workingin 5 days
You fixed this one by hand.
Okapi opens the pull request with the fix before the next breaking change reaches your code.