Llama 4 Maverick 17B 128E Instruct FP8 API
About
Integrate multimodal vision capabilities using Llama 4 Maverick 17B 128E Instruct FP8, designed to process both text and images seamlessly. This model delivers cost-effective pricing at $0.25/1M input and $1.00/1M output tokens, native tool calling support, open weights architecture. Access Llama 4 Maverick 17B 128E Instruct FP8 via the Azure Cognitive Services API with up to 16K output tokens.
Capabilities
Input Modalities
textimage
Output Modalities
text
Reasoning
No
Limits
Context Window
1.0M
Tokens
Input Limit
1.0M
Tokens
Max Output
16K
Tokens
Pricing
Standard (per 1M tokens)
Input
$0.25
Output
$1.00
Frequently Asked Questions
Llama 4 Maverick 17B 128E Instruct FP8 by Azure Cognitive Services costs $0.25 per 1M input tokens and $1.00 per 1M output tokens.
Model Details
ID
llama-4-maverick-17b-128e-instruct-fp8
Provider
Azure Cognitive ServicesFamily
llama
Release Date
Apr 5, 2025
Knowledge Cutoff
Aug 1, 2024
API Integration
NPM Package
@ai-sdk/azure
Environment Variables
AZURE_COGNITIVE_SERVICES_RESOURCE_NAME
AZURE_COGNITIVE_SERVICES_API_KEY