Models / Alibaba / Qwen3-Next 80B-A3B (Thinking)
Alibaba · qwen
Qwen3-Next 80B-A3B (Thinking)
Efficient Qwen thinking model for local reasoning, math, and coding agents
$0.50 in · $6.00 out
per 1M tokens · first-party price. Reference price from Alibaba, the lab's own listing.
Provider input prices run from $0.14 to $0.50 per 1M tokens. Output prices run from $0.65 to $6.00.
- Context
- 131,072
- Max output
- 32,768
- Cache read
- —
- Cache write
- —
- Reasoning
- Yes
- Tool calls
- Yes
- Structured output
- Unknown
- Vision
- No
- Open weights
- Yes
- License
- —
- Released
- Sep 1, 2025
- Updated in source
- Sep 1, 2025
- Knowledge
- 2025-04
- Providers
- 10
Providers
| Provider | Input | Output | Cache read | Cache write | Status |
|---|---|---|---|---|---|
| Alibaba | $0.14 | $1.43 | — | — | — |
| DevPass | $0.15 | $1.20 | — | — | — |
| Jalapeno Cloud | $0.15 | $1.50 | — | — | — |
| Kilo Gateway | $0.15 | $1.20 | — | — | — |
| LLM Gateway | $0.15 | $1.20 | — | — | — |
| Merge Gateway | $0.15 | $1.20 | — | — | — |
| NanoGPT | $0.15 | $0.65 | $0.075 | — | — |
| OpenRouter | $0.15 | $1.20 | — | — | — |
| Vercel AI Gateway | $0.15 | $1.20 | — | — | — |
| Alibabareference | $0.50 | $6.00 | — | — | — |
Jobs this model qualifies for
- Coding agents — clears the bar
- Cheapest summarization — clears the bar