Models / Qwen3.8 2.4T A95B

Qwen3.8 2.4T A95B

Proprietary

Qwen3.8 flagship MoE (2.4T total / 95B active) with extended thinking.

qwen/qwen3.8-2.4t-a95b
Context Window
262K
Max Output
66K
Released
2026-09

Capabilities

ChatCodeReasoningThinkingToolsStreaming

Price

Prices shown are the official rate published by the model provider, before any platform discounts. Your actual rate may be lower based on your account's discount tier.

PriceLatency p50Latency p95Status
$1.65 /M in · $4.95 /M out300ms800ms

Quick Start

Python
import magicrouter

mr = magicrouter.Client(api_key="mr-your-key")

response = mr.chat(
    "qwen/qwen3.8-2.4t-a95b",
    "Your prompt here"
)
print(response.choices[0].message.content)
TypeScript
import { MagicRouter } from "magicrouter";

const mr = new MagicRouter({ apiKey: "mr-your-key" });

const response = await mr.chat({
  model: "qwen/qwen3.8-2.4t-a95b",
  messages: [{ role: "user", content: "Your prompt here" }]
});
console.log(response.choices[0].message.content);
cURL
curl https://api.magicrouter.ai/v1/chat/completions \
  -H "Authorization: Bearer mr-your-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen/qwen3.8-2.4t-a95b",
    "messages": [{"role": "user", "content": "Your prompt here"}]
  }'

Use this model

Sign up for free and test Qwen3.8 2.4T A95B in the playground

Get Started