/ Models

Language models

Qwen: Qwen3 Next 80B A3B Thinking

Qwen3-Next-80B-A3B-Thinking is a reasoning-first chat model in the Qwen3-Next line that outputs structured “thinking” traces by default. It’s designed for hard multi-step problems; math proofs, code synthesis/debugging, logic, and agentic...

Maker
Qwen
Context window
262K
Max output
33K
Input / 1M
$0.15
Output / 1M
$1.20
1M in + 1M out
$1.35

Everything else

Max output33K
Input / 1M$0.15
Output / 1M$1.20
Cache read / 1M
Cache write / 1M
1M in + 1M out$1.35
Takestext
Returnstext
Toolsyes
Reasoningalways on
Open weightsyes
Released2025-09-11
Knowledge cutoff2025-09-30
Retires
Catalog idqwen/qwen3-next-80b-a3b-thinking

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