Command Palette
Search for a command to run

Qwen3 Coder Next

by Qwen

Specifications

Input
Output
Context window
256K tokens
Released
Feb 2026

Performance

Speed
118 t/s
TTFT
283 ms
Latency
Intelligence

Pricing

Input
€0.22
per 1M tokens
Output
€1.12
per 1M tokens

About this model

Qwen3-Coder-Next is an open-weight coding model optimized for agents and local development, delivering high performance, long-context reasoning, and efficient IDE integration with minimal active parameters.

Technical specifications

Capabilities
Input modalities
Output modalities
Reasoning
No

Knowledge horizon

Released Feb 2026
Today
Since release 3 mo

See also

Add Model to Comparison
Search for a model to add
Command Palette
Search for a command to run