Back to models
Model · Qwen
Qwen

Qwen 3.8 2.4T A95B

alibaba/qwen3.8-2.4t-a95b
Try in Agents

Open-weight release of Qwen 3.8 — 95B active of 2.4T params with mostly-linear attention for affordable 262K context

reasoning
Specs
Context
262K
Max output
131K
Provider
Qwen
Input
$1.65/ 1M tokens
Output
$4.95/ 1M tokens
Cache read
—
Try it
Chat with Qwen 3.8 2.4T A95BTerramind API
⌘+Enter to run
Code
import { streamText } from "ai";
import { createOpenAICompatible } from "@ai-sdk/openai-compatible";

const terramind = createOpenAICompatible({
  name: "terramind",
  baseURL: "https://terramind.com/api/v1",
  apiKey: process.env.TERRAMIND_API_KEY!,
});

const result = streamText({
  model: terramind("qwen3.8-2.4t-a95b"),
  prompt: "Why is the sky blue?",
});

for await (const chunk of result.textStream) {
  process.stdout.write(chunk);
}

Want to run this in your app? Grab an API key · Full chat reference

More by Qwen
ModelContextInOutCapabilities
Qwenalibaba/qwen3-coder131K$0.650$3.25
reasoning
Qwenalibaba/qwen3-coder-flash256K$0.500$1.20
Qwenalibaba/qwen3-coder-next262K$0.120$0.750
Qwenalibaba/qwen3.5-flash1M$0.065$0.260
vision
Qwenalibaba/qwen3.6-plus1M$0.500$3.00
reasoningvisioncaching
Qwenalibaba/qwen3-max262K$0.780$3.90
reasoningvisioncaching
Qwenalibaba/qwen3.8-max1M$2.00$6.00
reasoningvisioncaching
Qwenalibaba/qwen3.8-27b262K$0$0
reasoningvisionvideo