Groq · Model retirement
meta-llama/llama-4-maverick-17b-128e-instruct
Stopped working
Calls to the model meta-llama/llama-4-maverick-17b-128e-instruct on Groq stopped working on March 9, 2026.
What to use instead of meta-llama/llama-4-maverick-17b-128e-instruct
Move to openai/gpt-oss-120b, recommended by Groq.
Facts
- API
- Groq
api.groq.com - Model
meta-llama/llama-4-maverick-17b-128e-instruct- Kind
- Model retirement
- Takes effect
- March 9, 2026
- Calls after that day
- Fail
- Source
- Deprecations page
- Last updated
meta-llama/llama-4-maverick-17b-128e-instruct on other APIs
- NVIDIA Deprecated, no date
More from Groq
- meta-llama/llama-guard-4-12b Stopped working
- moonshotai/kimi-k2-instruct-0905 Stopped working
- playai-tts Stopped working
- playai-tts-arabic Stopped working
- meta-llama/llama-4-scout-17b-16e-instruct Stopped working
- qwen/qwen3-32b Stopped working