Cracked AI Engineering

Qwen3 235B A22B Thinking 2507

submodelOpen Weights

The Qwen3 235B A22B Thinking 2507 AI model by submodel offers developers a powerful tool for advanced reasoning and function calling with a vast context window of 262,144 tokens. With the ability to process text input and provide output up to 131,072 tokens, this model is ideal for complex language tasks and multimodal applications. Open weights availability and competitive pricing at $0.2/M input and $0.6/M output tokens make it a cost-effective choice for AI development projects.

Key Specifications

Context Window

262K tokens

Max Output Tokens

131K tokens

Input Pricing

$0.20

per million tokens

Output Pricing

$0.60

per million tokens

Capabilities

  • Text Generation
  • Function Calling
  • Advanced Reasoning

Additional Details

Provider
submodel
Release Date
August 23, 2025
Advanced Reasoning
Supported
Supported Input Types
text

Compare with Similar Models