Okapi Okapi

Groq · Model retirement

llama-3.3-70b-versatile

Stopped working

Calls to the model llama-3.3-70b-versatile on Groq stopped working on August 16, 2026.

What to use instead of llama-3.3-70b-versatile

Move to openai/gpt-oss-120b. qwen/qwen3.6-27b, also named, stopped working on 2026-09-14.

Facts

API
Groq api.groq.com
Model
llama-3.3-70b-versatile
Kind
Model retirement
Takes effect
August 16, 2026
Calls after that day
Fail
Who it affects
free and developer tiers
Source
Deprecations page
Last updated

More from Groq

Know before your API calls break.

Okapi finds the calls a breaking change hits in your code and opens the pull request that fixes them.

Add to GitHub