Qwen3 Next 80B A3B Thinking
Alibaba · Released Sep 2025
An 80-billion-parameter dense language model from Alibaba with extended reasoning capabilities and a 131k-token context window.
- Strengths
- Balances model capacity with reasoning depth, suited for complex problem-solving tasks that benefit from step-by-step analysis.
- Best for
- Multi-step reasoning, research synthesis, and technical problem-solving where extended thinking provides value without requiring the scale of larger models.
- Limitations
- Smaller context window than Qwen3 Next 80B A3B Instruct (131k vs 262k tokens) and lower capacity than the 235B Thinking variant for handling very large or intricate documents.
Input / 1M
$0.15
Output / 1M
$1.20
Cached input / 1M
—
Context window
262K
Price history
Input (solid)Output (dashed)
Price change
- 30d
- in — out —
- 90d
- in increased 53.8% out increased 53.8%
- 1y
- in increased 53.8% out increased 53.8%
- Since launch
- in increased 53.8% out increased 53.8%
Snapshots
| Effective | Input | Output | Cached in | Note | Source |
|---|---|---|---|---|---|
| 29 Jul 2026 | $0.15 | $1.20 | — | Imported from OpenRouter | openrouter.ai |
| 11 Jun 2026 | $0.0975 | $0.78 | — | Imported from OpenRouter | openrouter.ai |