QQwen · Released Sep 11, 2025
Qwen3 Next 80B A3B Instruct
Qwen3-Next-80B-A3B-Instruct is an instruction-tuned chat model in the Qwen3-Next series optimized for fast, stable responses without “thinking” traces. It targets complex tasks across reasoning, code generation, knowledge QA, and…
- Released
- Sep 11 2025
- Context window
- 262K 16K out
- Input / 1M tokens
- $0.09 from $0.072
- Output / 1M tokens
- $1.10 from $0.57
Where to run it
22 providers compared
Cheapest: Alibaba (China) at $0.14 / $0.57 per 1M input / output tokens — 71% less than the priciest option.
| Provider | Input | Output | Cache read | Context | Max output | Uptime | vs. best |
|---|---|---|---|---|---|---|---|
| Alibaba (China) | $0.14 | $0.57 | — | 131K | 33K | — | Cheapest |
| Qiniu | $0.14 | $0.58 | — | 131K | 33K | — | +1% |
| DeepInfraFP8 | $0.072 | $0.88 | — | 262K | 236K | — | +9% |
| DeepInfraFP8 | $0.09 | $1.10 | — | 262K | 16K | 96.5%24h | +36% |
| Kilo Gateway | $0.09 | $1.10 | — | 262K | 16K | — | +36% |
| ParasailFP8 | $0.10 | $1.10 | $0.07 | 262K | 236K | 100%24h | +39% |
| NanoGPT | $0.10 | $1.10 | $0.07 | 262K | 33K | — | +39% |
| Merge Gateway | $0.10 | $1.10 | $0.05 | 131K | 33K | — | +39% |
| IO.NET | $0.12 | $1.26 | $0.059 | 262K | 4K | — | +61% |
| Googleglobal | $0.15 | $1.20 | — | 262K | 236K | 98.2%24h | +64% |
| Vercel AI Gateway | $0.15 | $1.20 | — | 262K | 262K | — | +64% |
| Amazon Bedrock | $0.15 | $1.20 | — | 262K | 262K | — | +64% |
| Neon | $0.15 | $1.20 | — | 131K | 10K | — | +64% |
| Eden AI | $0.15 | $1.20 | $0.015 | 262K | 33K | — | +64% |
| Hugging Face | $0.25 | $1.00 | — | 262K | 33K | — | +74% |
| Helicone | $0.14 | $1.40 | — | 262K | 16K | — | +81% |
| LLM Gateway | $0.15 | $1.50 | — | 131K | 33K | — | +94% |
| Jalapeno Cloud | $0.15 | $1.50 | — | 129K | 33K | — | +94% |
| Jiekou.AI | $0.15 | $1.50 | — | 66K | 66K | — | +94% |
| DevPass (LLM Gateway) | $0.15 | $1.50 | — | 131K | 33K | — | +94% |
| DeepInfrapriority · FP8 | $0.14 | $1.65 | — | 262K | 236K | 88.5%24h | +104% |
| AI/ML API | $0.21 | $1.65 | — | 129K | 16K | — | +125% |
| Venice AI | $0.35 | $1.90 | — | 256K | 16K | — | +193% |
| Alibaba | $0.50 | $2.00 | — | 131K | 33K | — | +248% |
Value
Price vs. performance
Qwen3 Next 80B A3B Instruct Other Qwen Other labs Value frontier · Fiction.LiveBench vs. input price per 1M tokens (log scale) · Drag to pan, pinch or Ctrl + scroll to zoom, double-click to zoom in.
Benchmarks
1 benchmark score
| Benchmark | Score | Rank | Leader |
|---|---|---|---|
| Fiction.LiveBenchWriting & content · Understanding long creative writing (16k tokens) | 55.6% | #16of 24 | GPT-597.2% |
Specs
Details
- Model ID
qwen/qwen3-next-80b-a3b-instruct- Developer
- Qwen
- Release date
- Sep 11, 2025 ·
- Context window
- 262,144 tokens
- Max output
- 16,384 tokens
- API price
- $0.09 / $1.10 per 1M input / output tokens
- Providers
- 22
- Input types
- text
- Reasoning
- No
- 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.