When is meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8 shut down?
meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8 shut down on 2026-03-31 per Together AI's deprecation page (checked 2026-11-12). No official replacement is published on that page. Price, context window, and max output were left blank because the official pages we checked did not publish them.
retired
Add this badge to your README
The image shows the model id and the status from this page. The link opens this page.
The inference table lists this id as removed from serverless inference. Supported by on-demand dedicated endpoints: Yes. Models marked "Yes" can be deployed as on-demand dedicated endpoints, either under the listed ID or as the underlying base model of a serving variant (for example, a deprecated -FP8 or -Turbo ID).
The inference table lists this id as removed from serverless inference. Supported by on-demand dedicated endpoints: Yes. Models marked "Yes" can be deployed as on-demand dedicated endpoints, either under the listed ID or as the underlying base model of a serving variant (for example, a deprecated -FP8 or -Turbo ID).
When is meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8 shut down?
meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8 shut down on 2026-03-31 per Together AI's deprecation page (checked 2026-11-12). No official replacement is published on that page. Price, context window, and max output were left blank because the official pages we checked did not publish them.
What replaces meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8?
No official replacement is published on that page.
Is meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8 deprecated?
meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8 status is retired.
Sources
Together AI deprecations, checked 2026-11-12. 2026-03-31 | `meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8` | Yes