qwen
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...
Quality Score
90/100
composite of price, context, capability
Input Price
$0.10
per 1M tokens
Output Price
$0.78
per 1M tokens
Context Window
131,072
tokens
- Model ID
- qwen/qwen3-next-80b-a3b-thinking
- Vendor
- qwen
- Tokenizer
- Qwen3
- Input Modalities
- text
- Output Modalities
- text
- Max Output
- 32,768 tokens
- Tool Calling
- ✓ supported
- Structured Output
- ✓ supported
- Reasoning Mode
- ✓ supported
- Vision
- text only
- Audio
- no
- Moderated
- no
Similar models
qwen
Qwen: Qwen3 VL 32B Instruct
$0.10 in / $0.42 out
131,072 ctx
91
qwen
Qwen: Qwen3 VL 8B Instruct
$0.08 in / $0.50 out
131,072 ctx
91
qwen
Qwen: Qwen3 VL 30B A3B Instruct
$0.13 in / $0.52 out
131,072 ctx
91
qwen
Qwen: Qwen3 30B A3B Thinking 2507
$0.08 in / $0.40 out
131,072 ctx
91
qwen
Qwen: Qwen3 235B A22B Thinking 2507
$0.15 in / $1.50 out
131,072 ctx
90
qwen
Qwen: Qwen3 235B A22B
$0.46 in / $1.82 out
131,072 ctx
90