meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8

by DeepInfra — Price updated 2026-04-04

Pricing ($/1M tokens)
Input $0.15
Output $0.60
Specifications
Context Window 1,048,576
Max Output 1,048,576
Input text
Output text
About This Model

meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8 is a budget-friendly language model from DeepInfra.

It supports a context window of 1.0M tokens with up to 1.0M output tokens.

With input pricing at $0.15/1M tokens, it sits in the mid-range of available models.