Llama 4 Maverick 17B 128E Instruct FP8 by GitHub Models — Specs, Pricing & Capabilities | whichllm

Model ID meta/llama-4-maverick-17b-128e-instruct-fp8

Provider GitHub Models

Family llama

Status -

Knowledge Cutoff 2024-12

Release Date 2025-01-31

Input Modalities text, image

Output Modalities text

Context Window 128000

Input Limit -

Output Limit 8192

Tool Calling Yes

Reasoning Yes

Structured Output -

Temperature Control Yes

Open Weights Yes

Input Cost / 1M tokens -

Output Cost / 1M tokens -

Reasoning Cost / 1M tokens -

Cache Read Cost / 1M tokens -

Cache Write Cost / 1M tokens -