Llama-4-Maverick-17B-128E-Instruct-FP8 | Sulat AI Models

Loading models

AI models by Sulat.com

Find AI models and the companies that serve them.

Use this site to learn more about AI models, compare their details, and see which providers or companies make them available.

Llama-4-Maverick-17B-128E-Instruct-FP8 | Sulat AI Models

Model details

Llama-4-Maverick-17B-128E-Instruct-FP8

Find out what this model does, when it was released, and which provider serves it.

Synthetichf:meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8llama

Open provider page Provider docs

Quick Info

Provider: Synthetic
Model key: hf:meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
Release date: Apr 5, 2025
Last updated: Apr 5, 2025
Knowledge: 2024-08
Input modalities: text, image
Output modalities: text
Capabilities: Tool calling, Attachments, Open weights, Temp controls
Cost summary: In $0.22 · Out $0.88
Limit summary: 524,000 token context window

Cost

Input token cost: $0.22
Output token cost: $0.88

Limits

Output tokens: 4,096 tokens
Context window: 524,000 tokens