qwen

Qwen: Qwen3 Coder 30B A3B Instruct

Qwen3-Coder-30B-A3B-Instruct is a 30.5B parameter Mixture-of-Experts (MoE) model with 128 experts (8 active per forward pass), designed for advanced code generation, repository-scale understanding, and agentic tool use. Built on the...

Input Cost
$0.07
per 1M tokens
Output Cost
$0.27
per 1M tokens
Context Window
160,000
tokens
Compare vs GPT-4o
Developer ID: qwen/qwen3-coder-30b-a3b-instruct

Related Models

qwen
$0.06/1M

Qwen: Qwen3 14B

Qwen3-14B is a dense 14.8B parameter causal language model from the Qwen3 series, designed...

📝 40,960 ctx Compare →
qwen
$0.20/1M

Qwen: Qwen2.5 VL 32B Instruct

Qwen2.5-VL-32B is a multimodal vision-language model fine-tuned through reinforcement lear...

📝 128,000 ctx Compare →
qwen
$0.20/1M

Qwen: Qwen3 VL 235B A22B Instruct

Qwen3-VL-235B-A22B Instruct is an open-weight multimodal model that unifies strong text ge...

📝 262,144 ctx Compare →