Qwen3 Next 80B A3B Instruct
AlibabaOpen weights262k context
Qwen3 Next 80B A3B Instruct is an open-weights model from Alibaba with a 262k-token context window. 1 provider lists it, at $0.15 per million input tokens and $1.20 per million output tokens (Amazon Bedrock).
- Maker
- Alibaba
- Licence
- Open weights
- Context window
- 262k
- Providers listed
- 1
- Lowest input, per 1M
- $0.15
- Lowest output, per 1M
- $1.20
Providers serving Qwen3 Next 80B A3B Instruct
Cheapest first, by the blended rate of three input tokens to one output token. Prices in US dollars per million tokens; each date links to the pricing page the price was read from.
| Provider | Input | Output | Price checked | Context | Tools | JSON mode | OpenAI-compatible | Model ID |
|---|---|---|---|---|---|---|---|---|
Amazon Bedrock | $0.15 | $1.20 | 25 Oct 2026 | 262k | Yes | Yes | No | qwen.qwen3-next-80b-a3b |
How each provider handles your prompts
For each provider's paid API, from its own pages, checked 26 Oct 2026. Where a promise lives matters: a signed agreement binds the provider, while a docs page can change without notice. Not legal advice.
| Provider | Trains on your prompts | Keeps prompts | Zero retention | Data processing agreement |
|---|---|---|---|---|
| Amazon Bedrock OpenAI models (flagged traffic) and Claude Fable 5/5.1 (all traffic, with possible AWS human review) keep data up to 30 days; the Responses API stores responses unless store=false. | No | not stored for most models; up to 30 days for abuse detection on models AWS lists | Yes, by default | Public |
Benchmark scores
Published scores only, each linked to its source. Compare every model in Bench rankings
| Benchmark | Score |
|---|---|
τ²-Bench Telecom Agentic tool use | 13.2%v |