Qwen3 Next 80B A3B Instruct
Qwen3 Next 80B A3B Instruct (Apache 2.0, September 2025) is the Qwen team's efficiency experiment: 80B parameters with only 3B active per token, thanks to a hybrid of linear and gated attention. It answers directly — there is no thinking mode and it never emits reasoning traces — and its advantage shows on very long inputs. The developers report results on par with their much larger 235B instruct model on a number of benchmarks. It is fulfilled through global providers under our European contract, and requests go only to backends that do not retain prompts or completions.
model id: qwen3-next-80b-a3b-instruct
from openai import OpenAI client = OpenAI( api_key="hb-...", base_url="https://api.heabsy.com/v1",) r = client.chat.completions.create( model="qwen3-next-80b-a3b-instruct", messages=[{"role": "user", "content": "Hello"}],)print(r.choices[0].message.content)
curl https://api.heabsy.com/v1/chat/completions \ -H "Authorization: Bearer $HEABSY_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "qwen3-next-80b-a3b-instruct", "messages": [{"role": "user", "content": "Hello"}] }'
import OpenAI from "openai"; const client = new OpenAI({ apiKey: process.env.HEABSY_API_KEY, baseURL: "https://api.heabsy.com/v1",}); const r = await client.chat.completions.create({ model: "qwen3-next-80b-a3b-instruct", messages: [{ role: "user", content: "Hello" }],});console.log(r.choices[0].message.content);
Price list, updated 12 September 2026. No minimum spend, no subscription.
About the model
- Developer
- Qwen (Alibaba)
- Released
- September 2025
- Licence
- Apache-2.0
- Architecture
- mixture of experts · 80B parameters, 3B active per token
- Input
- text
- Reasoning
- no reasoning mode
- Languages named by the developer
- none named on the model card
Source: the developer's model card, as of 17 September 2026.
Licence: what it means for your company
Apache-2.0. A permissive open-source licence: you may use, modify and sell products built on the model, including commercially; when you redistribute the weights, the licence and copyright notices go with them.
A summary of the licence, not legal advice.
Technical details
- Context window
- 256K tokens
- Max output
- 65,536 tokens
- Throughput limit
- 200K tok/min
- Tokenizer
- Other
- Streaming
- yes
- Open weights
- Qwen/Qwen3-Next-80B-A3B-Instruct
- max_tokens
- 1 … 65536
- temperature
- 0 … 2
- top_p
- 0 … 1
- frequency_penalty
- -2 … 2
- presence_penalty
- -2 … 2
- stop
- array
- seed
- integer
This model is fulfilled through global providers under our European contract: one DPA with an EU company, one invoice for every model in the catalog, no US counterparty on your paperwork. Compute may run outside the EEA — if you need strict EEA-only processing, use our own-hardware model.
Questions about this model
›Where is Qwen3 Next 80B A3B Instruct computed?
Outside the EEA, through a global provider under our European contract. You get one DPA with an EU company and one invoice, but the compute itself does not run in the EEA — we state that instead of hiding it.
›Does Qwen3 Next 80B A3B Instruct store prompts and completions?
No. This model runs with zero data retention: request content is not written to durable storage and nothing is used for training.
›How large is the Qwen3 Next 80B A3B Instruct context window?
256K tokens, with up to 65,536 tokens of output.
›What does Qwen3 Next 80B A3B Instruct cost?
$0.14 per million input tokens and $1.70 per million output tokens. No minimum spend and no subscription; the same price list covers the API and the invoice.
›Is there a throughput limit on Qwen3 Next 80B A3B Instruct?
Yes, 200K tokens per minute. Higher limits are a question of volume, not of principle.
›Which languages does Qwen3 Next 80B A3B Instruct support?
The developer's model card names no languages. Test the model on your own material before relying on it in a particular language.
›Under which licence is Qwen3 Next 80B A3B Instruct released?
Apache-2.0. A permissive open-source licence: you may use, modify and sell products built on the model, including commercially; when you redistribute the weights, the licence and copyright notices go with them.
›Can reasoning be switched off in Qwen3 Next 80B A3B Instruct?
Qwen3 Next 80B A3B Instruct has no reasoning mode — it answers directly, which keeps latency and output tokens low.
Compare with similar models
| Model | Developer | Parameters | Context | Licence | Input / 1M |
|---|---|---|---|---|---|
| Qwen3 Next 80B A3B Instruct | Qwen (Alibaba) | 80B / 3B | 256K | Apache-2.0 | $0.14 |
| Qwen3 Coder Next | Qwen (Alibaba) | 80B / 3B | 256K | Apache-2.0 | $0.18 |
| Qwen3.8 Flash-Next | Qwen (Alibaba) | 125B / 6B | 256K | Qwen Community License 1.0 | $0.15 |
| Qwen3.6 35B A3B | Qwen (Alibaba) | 35B / 3B | 256K | Apache-2.0 | $0.15 |
30 more models behind the same key and the same invoice.
Browse the catalog