Cracked AI Engineering

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

SyntheticOpen Weights

The Llama-4-Maverick-17B-128E-Instruct-FP8 AI model by Synthetic offers developers a powerful tool with a massive context window of 524,000 tokens and the ability to handle text input, vision, and function calling. With open weights and competitive pricing at $0.22/M input and $0.88/M output tokens, this model is ideal for tasks requiring advanced reasoning and multimodal capabilities. Don't miss out on this cutting-edge AI model with a training data cutoff of 2024-08.

Key Specifications

Context Window

524K tokens

Max Output Tokens

4K tokens

Input Pricing

$0.22

per million tokens

Output Pricing

$0.88

per million tokens

Capabilities

  • Text Generation
  • Vision
  • Function Calling
  • File Attachments

Additional Details

Provider
Synthetic
Release Date
April 5, 2025
Supported Input Types
text, image

Compare with Similar Models