All Models

Qwen 3 Coder 480B

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 Jan 15, 2025
Input Modalities text
Output Modalities text
Tarsk Use coding

Benchmarks

18
Intelligence Index
39.3
Math Index

Available Providers (3)

Provider Model ID Input Cost Output Cost Context Max Output Docs
NanoGPT qwen/qwen3-coder $0.13/MTok $0.50/MTok 262K 65.5K
IO.NET Intel/Qwen3-Coder-480B-A35B-Instruct-int4-mixed-ar $0.22/MTok $0.95/MTok 106K 4.1K
Synthetic hf:Qwen/Qwen3-Coder-480B-A35B-Instruct $2/MTok $2/MTok 256K 32K

Capabilities

Reasoning
Tool Calling
Attachments
Open Weights
Structured Output