Llama 4 Maverick 17B

meta

A multimodal model from the Llama 4 collection with MoE architecture for text and image tasks. Designed for multimodal experiences with vision capabilities.

Try Now

Capabilities

Tool Use

Image Input

PDF Input

Example Use Cases

Multimodal text and image tasks

Vision-enabled workflows

Llama 4 multimodal

Technical Specifications

Context Window

131,072 tokens

Max Output

8,192 tokens

Cache Miss Cost

$0.15 per 1M tokens

Non-Reasoning Cost

$0.60 per 1M tokens

Web Search Cost

$15 per 1K calls

Code Execution Cost

$0.19 per 1K calls

⚠️ Legacy

Made legacy on

Reason

Poor tool calling capabilities and hallucinates web searches

Recommended Replacement

MiniMax M2.1