Back to models
Qwen·Qwen 3 family
Qwen 3.8 2.4T-A95B
MoEotherReleased Aug 12, 2026
Alibaba's open-weight Max-class Qwen 3.8 model, a sparse Mixture-of-Experts system with 2.4T total parameters and about 95B active parameters per token. The text model targets coding, research, complex reasoning, and long-horizon agentic workflows with a native 262K context window that can be extended to about one million tokens and is served by hosted providers with 1M context.
ChatText completionFunction callingCode generationReasoningtext · code
Available from 2 providers
Cheapest
Alibaba Model Studio
$2.00 / $6.00
Alibaba Model Studio, OpenRouter
Providers (2)
Sorted by total cost (input + output per 1M tokens). Select a row to view provider details.
| Provider | Pricing (per 1M) | Rate limits | Regions | Health | Latency |
|---|---|---|---|---|---|
| In: $2.00Out: $6.00 | 5K RPM / 5.0M TPM | ap-east-1 | Healthy | 0ms |
| In: $2.00Out: $6.00 | 60 RPM / 200K TPM | us-east-1 | Healthy | 0ms |
Quick start
Use this model via Alibaba Model Studio with an OpenAI-compatible SDK.
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.alibaba-model-studio.com/v1",
apiKey: process.env.ALIBABA_MODEL_STUDIO_API_KEY,
});
const response = await client.chat.completions.create({
model: "qwen3.8-2.4t-a95b",
messages: [
{ role: "user", content: "Hello!" }
],
});
console.log(response.choices[0].message.content);Using Alibaba Model Studio API · OpenAI-compatible SDK