Catalog
Qwenrouted

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)
Context
256K tokens
Serving
Global providers · EU contract
Tool calling
Reasoning
Structured output
Vision
Input
$0.15/ 1M
Cached input
$0.02/ 1M
Output
$0.47/ 1M

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
Supported parameters
max_tokens
1 … 16384
temperature
0 … 2
top_p
0 … 1
frequency_penalty
-2 … 2
presence_penalty
-2 … 2
stop
array
seed
integer
Bought for you, billed by us

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

ModelDeveloperParametersContextLicenceInput / 1M
Qwen3.8 Flash-NextQwen (Alibaba)125B / 6B256KQwen Community License 1.0$0.15
Qwen3 Next 80B A3B InstructQwen (Alibaba)80B / 3B256KApache-2.0$0.14
Qwen3 Coder NextQwen (Alibaba)80B / 3B256KApache-2.0$0.18
Qwen3.6 35B A3BQwen (Alibaba)35B / 3B256KApache-2.0$0.15

30 more models behind the same key and the same invoice.

Browse the catalog