Back to all models
qwen
qwenQwen: 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...
qwen/qwen3-coder
Context Size
1,048.576K
Input Price
33,000 pts/M
Output Price
270,000 pts/M
Architecture
Text
Supported Parameters
frequency_penaltylogit_biasmax_tokensmin_ppresence_penaltyrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_p
Details
TokenizerQwen3
Max Completion65,536 tokens
Provider Context262.144K tokens
ModeratedNo
CreatedJul 23, 2025