Alibaba/ Qwen
Qwen3 Coder 480B A35B
alibaba/qwen/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...
Released
2025-07-23
Context window
262K
Max output
66K
Weights
Open weight
Modalities
Input
Text
Output
Text
Identity
- Version
- qwen3-coder
- Knowledge cutoff
- 2025-06-30
Resources
Providers
| Provider | Provider model ID | Protocol | Context | Max output | Input | Output | Capabilities | Notes | Pricing | Streaming |
|---|---|---|---|---|---|---|---|---|---|---|
| OpenRouter | qwen/qwen3-coder | openai_chat | 262K | 66K | Text | Text | Tool callStructuredTemperatureOpen weight | Hugging Face: Qwen/Qwen3-Coder-480B-A35B-Instruct | input $0.3/M · cache read $0.1/M output $1/M | Yes |
| NanoGPT | qwen/qwen3-coder | openai_chat | 262K | 66K | Text | Text | Tool callStructuredTemperatureOpen weight | - | input $0.13/M · cache read $0.065/M output $0.5/M | Yes |
| FastRouter | qwen/qwen3-coder | openai_chat | 262K | 66K | Text | Text | Tool callStructuredTemperatureOpen weight | - | input $0.3/M output $1.2/M | Yes |
| Kilo Gateway | qwen/qwen3-coder | openai_chat | 262K | 66K | Text | Text | Tool callStructuredTemperatureOpen weight | - | input $0.975/M output $4.875/M | Yes |
Capabilities
Tool callStructuredTemperatureOpen weight