Together AI
meta-llama/llama-4-maverick-17b-128e-instruct-fp8 model retirement
Stopped workingSubscribe to Together AIShare
Calls to the model meta-llama/llama-4-maverick-17b-128e-instruct-fp8 on Together AI stopped working on March 31, 2026.
In Together AI's words
Removal date: 2026-03-31; Model: meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8; Supported by on-demand dedicated endpoints: Yes
Facts
- API
- Together AI
api.together.xyz - Model
meta-llama/llama-4-maverick-17b-128e-instruct-fp8- Released
- April 5, 2025 (models.dev)
- Kind
- Model retirement
- Takes effect
- March 31, 2026
- Calls after that day
- Fail
- Source
- Deprecations page
- Last updated
- Verified
- , against Together AI's own pages
Questions
When does meta-llama/llama-4-maverick-17b-128e-instruct-fp8 shut down?
Calls to the model meta-llama/llama-4-maverick-17b-128e-instruct-fp8 on Together AI stopped working on March 31, 2026.
What happens to calls after March 31, 2026?
They have failed since March 31, 2026.
When was meta-llama/llama-4-maverick-17b-128e-instruct-fp8 released?
meta-llama/llama-4-maverick-17b-128e-instruct-fp8 was released on April 5, 2025, 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.
meta-llama/llama-4-maverick-17b-128e-instruct-fp8 on other APIs 3
-
DeepInfra
meta-llama/llama-4-maverick-17b-128e-instruct-fp8Model retirement Stopped working -
Azure AI Foundry
llama-4-maverick-17b-128e-instruct-fp8Model retirement Stops workingin 13 days -
No date
DeepInfra
meta-llama/llama-4-maverick-17b-128e-instruct-fp8Model retirement Deprecated, no date
More from Together AI 10
-
meta-llama/llama-3.2-3b-instruct-turboModel retirement Stopped working -
meta-llama/meta-llama-3.1-8b-instruct-turboModel retirement Stopped working -
mistralai/mistral-small-24b-instruct-2501Model retirement Stopped working -
qwen/qwen3-next-80b-a3b-instructModel retirement Stopped working -
zai-org/glm-4.5-air-fp8Model retirement Stopped working -
zai-org/glm-4.7Model retirement Stopped working -
servicenow-ai/apriel-1.5-15b-thinkerModel retirement Stopped working -
servicenow-ai/apriel-1.6-15b-thinkerModel retirement Stopped working -
mistralai/mixtral-8x7b-instruct-v0.1Model retirement Stopped working -
qwen/qwen3-vl-8b-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.