Llama-4-Maverick-17B-128E-Instruct-FP8 by Vercel AI Gateway — Specs, Pricing & Capabilities | whichllm

Model ID meta/llama-4-maverick

Provider Vercel AI Gateway

Family llama

Status -

Knowledge Cutoff 2024-08

Release Date 2025-04-05

Input Modalities text, image

Output Modalities text

Context Window 128000

Input Limit -

Output Limit 4096

Tool Calling Yes

Reasoning No

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 -