Qwen3.8 Flash-Next
Qwen3.8 Flash-Next is the open-weight basis of the hosted Qwen3.8-Flash (Qwen Community License 1.0, August 2026) and, in the developers' words, an experimental preview of the architecture that will underpin Qwen4: a mixture-of-experts model with 125B parameters and 6B active per token, using block-sparse attention. It is tuned for low-latency, long-context agentic work and takes text, images and video — coding assistance, document and codebase analysis, desktop interaction. 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: qwen3.8-flash-next
from openai import OpenAI client = OpenAI( api_key="hb-...", base_url="https://api.heabsy.com/v1",) r = client.chat.completions.create( model="qwen3.8-flash-next", 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": "qwen3.8-flash-next", "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: "qwen3.8-flash-next", 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
- August 2026
- Licence
- Qwen Community License 1.0
- Architecture
- mixture of experts · 125B parameters, 6B active per token
- Input
- text, images, video
- Reasoning
- switchable per request
- 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
Qwen Community License 1.0. An MIT-style grant with two conditions: products above 100 million monthly active users or US$20 million monthly revenue must display the model name, and a business offering the model as a service or as an AI work assistant needs a separate licence from Qwen. Internal use that exposes nothing to third parties is exempt.
A summary of the licence, not legal advice.
Technical details
- Context window
- 256K tokens
- Max output
- 16,384 tokens
- Throughput limit
- 200K tok/min
- Tokenizer
- Qwen
- Streaming
- yes
- Open weights
- Qwen/Qwen3.8-Flash-Next
- max_tokens
- 1 … 16384
- 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 Qwen3.8 Flash-Next 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 Qwen3.8 Flash-Next 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 Qwen3.8 Flash-Next context window?
256K tokens, with up to 16,384 tokens of output.
›What does Qwen3.8 Flash-Next cost?
$0.15 per million input tokens and $0.47 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 Qwen3.8 Flash-Next?
Yes, 200K tokens per minute. Higher limits are a question of volume, not of principle.
›Which languages does Qwen3.8 Flash-Next 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 Qwen3.8 Flash-Next released?
Qwen Community License 1.0. An MIT-style grant with two conditions: products above 100 million monthly active users or US$20 million monthly revenue must display the model name, and a business offering the model as a service or as an AI work assistant needs a separate licence from Qwen. Internal use that exposes nothing to third parties is exempt.
›Can reasoning be switched off in Qwen3.8 Flash-Next?
Yes. Per the developer, thinking can be switched on or off for each request.
Compare with similar models
| Model | Developer | Parameters | Context | Licence | Input / 1M |
|---|---|---|---|---|---|
| Qwen3.8 Flash-Next | Qwen (Alibaba) | 125B / 6B | 256K | Qwen Community License 1.0 | $0.15 |
| 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 |
| Qwen3.6 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