Skip to main content
ALAlibaba/ Qwen

Qwen3 Coder 480B A35B

alibaba/qwen3-coder

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...

Model information

Released
2025-07-23
Context window
262K
Max output
66K
Weights
Open

Modalities

Input
Text
Output
Text

Identity

Version
qwen3-coder
Knowledge cutoff
2025-06-30

Resources

Capabilities

Open weightStructuredTemperatureTool call

Providers

ProviderProvider model IDProtocolContextMax outputInputOutputCapabilitiesNotesPricingStreaming
OpenRouterqwen/qwen3-coderopenai_chat262K66K
Tool callStructuredTemperature
Hugging Face: Qwen/Qwen3-Coder-480B-A35B-Instruct
input $0.3/M · output $1/M
cache read $0.1/M
Yes
NanoGPTqwen/qwen3-coderopenai_chat262K66K
Tool callStructured
-
input $0.13/M · output $0.5/M
cache read $0.065/M
Yes
FastRouterqwen/qwen3-coderopenai_chat262K66K
Tool callTemperature
-
input $0.3/M · output $1.2/M
Yes
Kilo Gatewayqwen/qwen3-coderopenai_chat262K66K
Tool callStructuredTemperature
-
input $0.975/M · output $4.875/M
Yes
Alibabaqwen3-codercustom262K66K
---Yes

FAQ