Groq
llama-guard-3-8b model retirement
Stopped workingSubscribe to GroqShare
Calls to the model llama-guard-3-8b on Groq stopped working on June 6, 2025.
The error you get
What Groq answers a call to llama-guard-3-8b once the model is gone, as recorded from real responses:
{"error":{"message":"The model `llama-guard-3-8b` does not exist or you do not have access to it.","type":"invalid_request_error","code":"model_not_found"}}What to use instead of llama-guard-3-8b
Move to openai/gpt-oss-safeguard-20b. meta-llama/llama-guard-4-12b, named first, stopped working on 2026-03-05.
In Groq's words
Deprecated Model: llama-guard-3-8b; Shutdown Date: 06/06/25; Recommended Replacement Model ID: meta-llama/llama-guard-4-12b
Facts
- API
- Groq
api.groq.com - Model
llama-guard-3-8b- Released
- July 23, 2024 (models.dev)
- Kind
- Model retirement
- Takes effect
- June 6, 2025
- Calls after that day
- Fail
- Source
- Deprecations page
- Last updated
- Verified
- , against Groq's own pages
Questions
When does llama-guard-3-8b shut down?
Calls to the model llama-guard-3-8b on Groq stopped working on June 6, 2025.
What happens to calls after June 6, 2025?
They have failed since June 6, 2025.
What error does llama-guard-3-8b return once it is shut down?
Groq answers HTTP 404: "The model `llama-guard-3-8b` does not exist or you do not have access to it.". Send another model to fix it.
When was llama-guard-3-8b released?
llama-guard-3-8b was released on July 23, 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-guard-3-8b on other APIs 1
-
DeepInfra
meta-llama/llama-guard-3-8bModel retirement Stopped working
More from Groq 10
-
deepseek-r1-distill-qwen-32bModel retirement Stopped working -
llama-3.2-11b-vision-previewModel retirement Stopped working -
llama-3.2-1b-previewModel retirement Stopped working -
llama-3.2-3b-previewModel retirement Stopped working -
llama-3.2-90b-vision-previewModel retirement Stopped working -
llama-3.3-70b-specdecModel retirement Stopped working -
qwen-2.5-32bModel retirement Stopped working -
qwen-2.5-coder-32bModel retirement Stopped working -
qwen-qwq-32bModel retirement Stopped working -
mistral-saba-24bModel 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.