DeepInfra · Model retirement
meta-llama/llama-4-maverick-17b-128e-instruct-fp8
Stopped working
Calls to the model meta-llama/llama-4-maverick-17b-128e-instruct-fp8 on DeepInfra stopped working on October 1, 2026.
What to use instead of meta-llama/llama-4-maverick-17b-128e-instruct-fp8
Move to google/gemma-4-31B-it-turbo, recommended by DeepInfra.
Facts
- API
- DeepInfra
api.deepinfra.com - Model
meta-llama/llama-4-maverick-17b-128e-instruct-fp8- Kind
- Model retirement
- Takes effect
- October 1, 2026
- Calls after that day
- Fail
- Source
- Lifecycle page
- Last updated
meta-llama/llama-4-maverick-17b-128e-instruct-fp8 on other APIs
- Together AI Stopped working
- DeepInfra Deprecated, no date
More from DeepInfra
- google/gemma-4-e4b-it Stopped working
- meta-llama/llama-3.2-90b-vision-instruct Stopped working
- meta-llama/llama-4-maverick-17b-128e-instruct-turbo Stopped working
- qwen/qvq-72b-preview Stopped working
- qwen/qwen3.5-122b-a10b Stopped working
- stepfun-ai/step-3.5-flash Stopped working