Skip to main content
ALAlibaba/ Qwen

Qwen3 Coder Next

alibaba/qwen3-coder-next

Qwen3-Coder-Next is an open-weight causal language model optimized for coding agents and local development workflows. It uses a sparse MoE design with 80B total parameters and only 3B activated per...

Model information

Released
2026-02-04
Context window
262K
Max output
262K
Model parameters
80B
Weights
Open

Modalities

Input
Text
Output
Text

Identity

Version
qwen3-coder-next
License
Apache-2.0

Resources

Capabilities

Open weightStructuredTemperatureTool call

Providers

ProviderProvider model IDProtocolContextMax outputInputOutputCapabilitiesNotesPricingStreaming
OpenRouterqwen/qwen3-coder-nextopenai_chat262K262K
Tool callStructuredTemperature
Hugging Face: Qwen/Qwen3-Coder-Next
input $0.12/M · output $0.8/M
cache read $0.07/M
Yes
NanoGPTqwen/qwen3-coder-nextopenai_chat262K262K
Tool callStructured
-
input $0.2/M · output $1.5/M
cache read $0.1/M
Yes
Kilo Gatewayqwen/qwen3-coder-nextopenai_chat262K262K
Tool callStructuredTemperature
-
input $0.3/M · output $1.5/M
Yes
NovitaAIqwen/qwen3-coder-nextopenai_chat262K262K
Tool callStructuredTemperature
-
input $0.2/M · output $1.5/M
Yes
Jiekou.AIqwen/qwen3-coder-nextopenai_chat262K262K
Tool callStructuredTemperature
-
input $0.2/M · output $1.5/M
Yes
Alibabaqwen3-coder-nextcustom262K262K
---Yes

FAQ