Qwen3-Coder-Next
Weights availableOpen-weight Qwen model with a 256K-token context window and tool calling. Released February 3, 2026. Weights on Hugging Face.
Access details: Qwen open weights (Hugging Face)
The Hugging Face repository. Download the weights and run them yourself or with a host.
Qwen/Qwen3-Coder-NextAlso on the Qwen API as qwen3-coder-next
Updated Oct 1, 2026
Capabilities & limits
- Context window
- 256K
- Maximum output
- Not published
- Image input
- Unsupported
- Tool calling
- Supported
- Structured output
- Not published
Hosted price
USD / 1M tokens- Input
- $0.12
- Output
- $0.80
What OpenRouter charges for qwen/qwen3-coder-next. Other hosts set their own prices.
Free to download. Running the weights costs whatever your hardware or host charges.
Price history
Oct 1, 2026
Input Not applicable per million tokens
Oct 1, 2026
Output Not applicable per million tokens
Technical details
- Parameters
- 80B
- Active parameters
- 3B
- Architecture
- Causal Language Models
- Training / knowledge cutoff
- Not published
- Input modalities
- Text
- Output modalities
- Text
License
Apache-2.0
From Qwen
Official announcement ↗How they describe it
For local use, applications such as Ollama, LMStudio, MLX-LM, llama.cpp, and KTransformers have also supported Qwen3.
Release & lifecycle
- Published
- Feb 3, 2026
- available
- As of Oct 1, 2026