/ Models

Language models

Qwen: 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...

Maker
Qwen
Context window
262K
Max output
262K
Input / 1M
$0.12
Output / 1M
$0.8
1M in + 1M out
$0.92

Everything else

Max output262K
Input / 1M$0.12
Output / 1M$0.8
Cache read / 1M$0.07
Cache write / 1M
1M in + 1M out$0.92
Takestext
Returnstext
Toolsyes
Reasoningno
Open weightsyes
Released2026-02-04
Knowledge cutoff
Retires
Catalog idqwen/qwen3-coder-next

Using it

In 00, this model is picked per agent — and per tier, so the model that answers your customers need not be the one that writes your code. Get 00.

← all models