QQwen · Released Sep 11, 2025
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…
- Released
- Sep 11 2025
- Context window
- 262K 236K out
- Input / 1M tokens
- $0.15 from $0.14
- Output / 1M tokens
- $1.20 from $0.65
Where to run it
11 providers compared
Cheapest: NanoGPT at $0.15 / $0.65 per 1M input / output tokens — 85% less than the priciest option.
| Provider | Input | Output | Cache read | Context | Max output | Uptime | vs. best |
|---|---|---|---|---|---|---|---|
| NanoGPTno tool calling | $0.15 | $0.65 | $0.075 | 256K | 33K | — | Cheapest |
| Googleglobal | $0.15 | $1.20 | — | 262K | 236K | 0%24h | +50% |
| Kilo Gateway | $0.15 | $1.20 | — | 262K | 236K | — | +50% |
| Vercel AI Gateway | $0.15 | $1.20 | — | 262K | 262K | — | +50% |
| Merge Gatewayno tool calling | $0.15 | $1.20 | — | 131K | 33K | — | +50% |
| Alibaba (China) | $0.14 | $1.43 | — | 131K | 33K | — | +70% |
| Qiniu | $0.14 | $1.45 | — | 131K | 33K | — | +71% |
| Jalapeno Cloud | $0.15 | $1.50 | — | 262K | 33K | — | +77% |
| Jiekou.AI | $0.15 | $1.50 | — | 66K | 66K | — | +77% |
| Hugging Face | $0.30 | $2.00 | — | 262K | 33K | — | +164% |
| Alibaba | $0.50 | $6.00 | — | 131K | 33K | — | +582% |
Benchmarks
Benchmark scores
No benchmark scores yet — Epoch AI hasn't evaluated Qwen3 Next 80B A3B Thinking. Scores appear here automatically once it does.
Specs
Details
- Model ID
qwen/qwen3-next-80b-a3b-thinking- Developer
- Qwen
- Release date
- Sep 11, 2025 ·
- Context window
- 262,144 tokens
- Max output
- 235,929 tokens
- API price
- $0.15 / $1.20 per 1M input / output tokens
- Providers
- 11
- Input types
- text
- Reasoning
- Yes
- Tool calling
- Yes
- Open weights
- Yes
- Free tier
- No
Release date and prices from OpenRouter's catalog; providers from OpenRouter and models.dev. Buying directly from a provider can cost a little differently. Speed, latency and uptime are measured on OpenRouter only; uptime is the share of OpenRouter requests each provider served over the last day. Benchmark scores are the best result per benchmark from Epoch AI, licensed CC BY 4.0. Rank counts every model tracked here with a score.