DeepInfra
meta-llama/llama-3.2-90b-vision-instruct model retirement
Stopped workingSubscribe to DeepInfraShare
DeepInfra retired the model meta-llama/llama-3.2-90b-vision-instruct on October 1, 2026. Calls specifying this model fail since that day. Any integrations relying on this specific model identifier are affected and no longer receive responses.
What to use instead of meta-llama/llama-3.2-90b-vision-instruct
Move to google/gemma-4-31B-it-turbo, which is recommended by DeepInfra.
Facts
- API
- DeepInfra
api.deepinfra.com - Model
meta-llama/llama-3.2-90b-vision-instruct- Released
- September 25, 2024 (models.dev)
- Kind
- Model retirement
- Takes effect
- October 1, 2026
- Calls after that day
- Fail
- Source
- Model list
- Last updated
- Verified
- , against DeepInfra's own pages
Questions
When does meta-llama/llama-3.2-90b-vision-instruct shut down?
Calls to the model meta-llama/llama-3.2-90b-vision-instruct on DeepInfra stopped working on October 1, 2026.
What happens to calls after October 1, 2026?
They have failed since October 1, 2026.
When was meta-llama/llama-3.2-90b-vision-instruct released?
meta-llama/llama-3.2-90b-vision-instruct was released on September 25, 2024, 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.
meta-llama/llama-3.2-90b-vision-instruct on other APIs 2
-
SambaNova Cloud
llama-3.2-90b-vision-instructModel retirement Stopped working -
Azure AI Foundry
llama-3.2-90b-vision-instructModel retirement Stopped working
More from DeepInfra 10
-
google/gemma-4-e4b-itModel retirement Stopped working -
meta-llama/llama-4-maverick-17b-128e-instruct-fp8Model retirement Stopped working -
meta-llama/llama-4-maverick-17b-128e-instruct-turboModel retirement Stopped working -
qwen/qvq-72b-previewModel retirement Stopped working -
qwen/qwen3.5-122b-a10bModel retirement Stopped working -
stepfun-ai/step-3.5-flashModel retirement Stopped working -
stepfun-ai/step-3.7-flashModel retirement Stopped working -
zai-org/glm-5.1Model retirement Stopped working -
nvidia/cosmos3-nanoModel retirement Stopped working -
nvidia/cosmos3-superModel 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.