Qwen3 235B A22B Thinking 2507
Review Qwen3 235B A22B Thinking 2507 on key metrics including price, context length, throughput, and model features.
AuthorQwen
Context Length262.1k
Supports Tools
Qwen3-235B-A22B-Thinking-2507 is a high-performance, open-weight Mixture-of-Experts (MoE) language model optimized for complex reasoning tasks. Activates 22B of its 235B parameters per forward pass and natively supports up to 262,144 tokens of context. This "thinking-only" variant enhances structured logical reasoning, mathematics, science, and long-form generation, and is instruction-tuned for step-by-step reasoning, tool use, agentic workflows, and multilingual tasks.
Activity
Last 14 daysPrompt
84KCompletion
102KTotal
186KStartup
Startup
Latency (p50)-
Throughput (p50)30.7 tok/s
Pricing
Input$0.07/M tokens
Output$0.30/M tokens
Features
Input Modalitiestext
Output Modalitiestext
Supported EndpointsChat Completions
Vision
Supports Tools