qwen

Qwen: Qwen3 Coder 480B A35B

Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team. It is optimized for agentic coding tasks such as function calling, tool use, and long-context reasoning over repositories. The model features 480 billion total parameters, with 35 billion active per forward pass (8 out of 160 experts). Pricing for the Alibaba endpoints varies by context length. Once a request is greater than 128k input tokens, the higher pricing is used.

Input Cost
$0.22
per 1M tokens
Output Cost
$1.00
per 1M tokens
Context Window
262,144
tokens
Compare vs GPT-4o
Developer ID: qwen/qwen3-coder

Related Models

qwen
$0.05/1M

Qwen: Qwen3 30B A3B Thinking 2507

Qwen3-30B-A3B-Thinking-2507 is a 30B parameter Mixture-of-Experts reasoning model optimize...

📝 32,768 ctx Compare →
qwen
$0.20/1M

Qwen: Qwen2.5-VL 7B Instruct

Qwen2.5 VL 7B is a multimodal LLM from the Qwen Team with the following key enhancements: ...

📝 32,768 ctx Compare →
qwen
$0.08/1M

Qwen: Qwen3 30B A3B

Qwen3, the latest generation in the Qwen large language model series, features both dense ...

📝 40,960 ctx Compare →