Alibaba Cloud (Qwen): Qwen3.8 2.4T-A95B

Overview

Large open-source Qwen3.8 model served on Model Studio, with thinking and non-thinking modes.

Provider

ACAlibaba Cloud (Qwen)

Modality

Text

Input

text

Output

text

Weights

Open weights

Supported parameters

tools, response_format, reasoning, temperature, top_p, top_k, web_searchProvider's model page, checked October 8, 2026.

Distillable

Conditional (licence terms)Qwen3.8-Max License: products with more than 100 million monthly users or US$20 million monthly revenue must show the model name, and model-as-a-service businesses above US$50 million a year need a separate licence.Licence or terms, checked October 8, 2026.

Tags

open-weights, reasoning

Docs

Provider documentation

Data policy

Prompts go to

Alibaba Cloud Model Studio (prices shown are for the Singapore / International deployment)

Retention

Alibaba Cloud states it never uses your data for model training, Model Studio stores data generated from model calls as required by law (no period stated)

Zero data retention

Not stated by the provider

Region

Singapore (International) for these prices, other regions such as China (Beijing), Hong Kong, Frankfurt, Virginia and Tokyo have separate price lists

Policy

Alibaba Cloud (Qwen) data policy

Summarised from the provider's published terms. The provider's own policy is what applies.

Where you can run it

How Qwen3.8 2.4T-A95B can be deployed, bought and reached through Safeguard.

Deployment

Private cloudOn-premAir-gapped

Procurement

Not published yet

Inference regions

Not published yet

On-prem and air-gapped deployments run wherever you install them.

Pricing

Notes

International (Singapore), 0 to 1M input tokens, both modes.

Source

Alibaba Cloud (Qwen) pricing , last verified October 8, 2026

No markup on model usage: you pay the provider's list price.

API

OpenAI-compatible. Your API key and access to this model are set up for your workspace when you choose Use with Safeguard.

from openai import OpenAI

client = OpenAI(
    base_url="https://api.safeguard.sh/gpt/v1",
    api_key="SAFEGUARD_API_KEY",
)

response = client.chat.completions.create(
    model="qwen/qwen3.8-2.4t-a95b",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Base URL https://api.safeguard.sh/gpt/v1, model qwen/qwen3.8-2.4t-a95b.