Back to all models

Llama 4 Maverick 17B (DeepInfra)

Meta Llama 4 Maverick 17B (128E Instruct FP8) served on DeepInfra. Fast and cheap for classification, extraction, and short summaries.

deepinfra-llama-4-maverick
STABLEGet Started
1,048,576 context
Starting at $0.20/M input tokens
Starting at $0.60/M output tokens
Streaming
Vision
Tools
JSON Output

Select Provider

All Providers for Llama 4 Maverick 17B (DeepInfra)

LLM Gateway routes requests to the best providers that are able to handle your prompt size and parameters.

DeepInfra
Context: 1.0M
Input
$0.2
/M tokens
Cached
$0.04
/M tokens
Output
$0.6
/M tokens
Get Started