qwen

Qwen: Qwen3 30B A3B Thinking 2507

Qwen3-30B-A3B-Thinking-2507 is a 30B parameter Mixture-of-Experts reasoning model optimized for complex tasks requiring extended multi-step thinking. The model is designed specifically for β€œthinking mode,” where internal reasoning traces are separated...

Input Cost
$0.08
per 1M tokens
Output Cost
$0.40
per 1M tokens
Context Window
131,072
tokens
Compare vs GPT-4o
Developer ID: qwen/qwen3-30b-a3b-thinking-2507

Related Models

qwen
$0.26/1M

Qwen: Qwen-Plus

Qwen-Plus, based on the Qwen2.5 foundation model, is a 131K context model with a balanced ...

πŸ“ 1,000,000 ctx Compare →
qwen
$0.78/1M

Qwen: Qwen3 Max

Qwen3-Max is an updated release built on the Qwen3 series, offering major improvements in ...

πŸ“ 262,144 ctx Compare →
qwen
Free/1M

Qwen: Qwen3 Coder 480B A35B (free)

Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model develop...

πŸ“ 262,000 ctx Compare →