Cracked AI Engineering

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

Vercel AI GatewayOpen Weights

The Llama-4-Maverick-17B-128E-Instruct-FP8 AI model by Vercel AI Gateway offers developers a powerful tool with a context window of 128,000 tokens and output limit of 4,096 tokens. With capabilities in text input, vision, and function calling, this model stands out for its open weights and affordable pricing of $0/M input and $0/M output tokens. Utilize this model for advanced reasoning tasks and multimodal applications with a training data cutoff of 2024-08.

Key Specifications

Context Window

128K tokens

Max Output Tokens

4K tokens

Input Pricing

Free

per million tokens

Output Pricing

Free

per million tokens

Capabilities

  • Text Generation
  • Vision
  • Function Calling
  • File Attachments

Additional Details

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

Compare with Similar Models