SambaNova Cloud
llama-3.2-90b-vision-instruct model retirement
Stopped workingSubscribe to SambaNova CloudShare
Calls to the model llama-3.2-90b-vision-instruct on SambaNova Cloud stopped working on April 14, 2025.
What to use instead of llama-3.2-90b-vision-instruct
Move to gemma-4-31b-it. llama-4-maverick-17b-128e-instruct, named first, stopped working on 2026-06-09.
In SambaNova Cloud's words
Model ID: Llama-3.2-90B-Vision-Instruct; Removal date: 4/14/2025; Recommended replacement: Llama-4-Maverick-17B-128E-Instruct
Facts
- API
- SambaNova Cloud
api.sambanova.ai - Model
llama-3.2-90b-vision-instruct- Released
- September 25, 2024 (models.dev)
- Kind
- Model retirement
- Takes effect
- April 14, 2025
- Calls after that day
- Fail
- Source
- Deprecations page
- Last updated
- Verified
- , against SambaNova Cloud's own pages
Questions
When does llama-3.2-90b-vision-instruct shut down?
Calls to the model llama-3.2-90b-vision-instruct on SambaNova Cloud stopped working on April 14, 2025.
What happens to calls after April 14, 2025?
They have failed since April 14, 2025.
When was llama-3.2-90b-vision-instruct released?
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.
llama-3.2-90b-vision-instruct on other APIs 2
-
Azure AI Foundry
llama-3.2-90b-vision-instructModel retirement Stopped working -
DeepInfra
meta-llama/llama-3.2-90b-vision-instructModel retirement Stopped working
More from SambaNova Cloud 10
-
llama-3.1-swallow-70b-instruct-v0.3Model retirement Stopped working -
llama-3.1-tulu-3-405bModel retirement Stopped working -
llama-3.2-11b-vision-instructModel retirement Stopped working -
meta-llama-3.1-70b-instructModel retirement Stopped working -
qwen2.5-72b-instructModel retirement Stopped working -
qwen2.5-coder-32b-instructModel retirement Stopped working -
llama-4-scout-17b-16e-instructModel retirement Stopped working -
qwen2-audio-7b-instructModel retirement Stopped working -
meta-llama-3.1-405b-instructModel retirement Stopped working -
meta-llama-3.2-1b-instructModel 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.