Cracked AI Engineering

Qwen 2.5 7B Vision Instruct

InferenceOpen Weights

The Qwen 2.5 7B Vision Instruct AI model by Inference offers developers a powerful tool with a context window of 125,000 tokens and the ability to process up to 4,096 tokens in its output. With capabilities for text input, vision, and function calling, this model excels in multimodal tasks and complex reasoning. Open weights and affordable pricing at $0.2/M input and $0.2/M output tokens make it a cost-effective solution for AI development.

Key Specifications

Context Window

125K tokens

Max Output Tokens

4K tokens

Input Pricing

$0.20

per million tokens

Output Pricing

$0.20

per million tokens

Capabilities

  • Text Generation
  • Vision
  • Function Calling
  • File Attachments

Additional Details

Provider
Inference
Release Date
January 1, 2025
Supported Input Types
text, image

Compare with Similar Models