Microsoft Azure AI Foundry Llama 4 Maverick 17B 128E Instruct FP8 — status, pricing and lifecycle

Active

No. Llama 4 Maverick 17B 128E Instruct FP8 is active at Microsoft Azure AI Foundry and has no announced end date.

Llama-4-Maverick-17B-128E-Instruct-FP8 last verified

Lifecycle status

Microsoft Azure AI Foundry has not announced a deprecation or shutdown date for this model. That is a statement about what has been published, not a guarantee — providers typically announce a shutdown months ahead, and this page updates when they do.

Status
Active
Deprecation announced
not announced
Shutdown date
not announced

Pricing & context

Input
$0.25 / M tokens
Output
$1.00 / M tokens
Context window
1M tokens
Model maker
Meta

Sources

  • learn.microsoft.com https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule
  • prices.azure.com https://prices.azure.com/api/retail/prices?$filter=serviceName eq 'Foundry Models' and contains(meterName,'Llama 4 Maverick 17B Inp glbl')
  • azure.microsoft.com https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/meta/

Verified against the source on . Dataset snapshot . Providers can change a date without notice — the link above is always the final word.

Common questions

What does Llama 4 Maverick 17B 128E Instruct FP8 cost?
$0.25 per million input tokens and $1.00 per million output tokens, as last verified on 2026-07-18.
What is the context window of Llama 4 Maverick 17B 128E Instruct FP8?
1M tokens.
Is Llama 4 Maverick 17B 128E Instruct FP8 deprecated?
No. Llama 4 Maverick 17B 128E Instruct FP8 is active at Microsoft Azure AI Foundry and has no announced end date.

All Microsoft Azure AI Foundry models and their end dates →