All Models

Qwen3 Coder 480B A35B

qwen Tool Calling Open Weights Structured Output

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...

Providers 3
Released Jul 22, 2025
Input Modalities text
Output Modalities text
Tarsk Use coding

Benchmarks

18.2
Intelligence Index
39.3
Math Index

Available Providers (3)

Provider Model ID Input Cost Output Cost Context Max Output Docs
OpenRouter qwen/qwen3-coder $0.30/MTok $1/MTok 262.1K 65.5K
Kilo Gateway qwen/qwen3-coder $0.97/MTok $4.88/MTok 262.1K 65.5K
Weights & Biases Qwen/Qwen3-Coder-480B-A35B-Instruct $1/MTok $1.50/MTok 262.1K 262.1K

Capabilities

Reasoning
Tool Calling
Attachments
Open Weights
Structured Output