Flagship multimodal reasoning for coding, professional agents, and 1M-token context
Qwen 3.8 Max 0902 TL1
Fast multimodal reasoning, agentic coding, and office automation with 1M context
Pricing
Prices for this trust level. Other trust levels are listed below. Prices are per 1M tokens.
| Trust Level | Region | Context | Max output | Input / 1M | Cache / 1M | Output / 1M | §203 |
|---|---|---|---|---|---|---|---|
| TL1 | SG | — | — | 2.00 € 2.20 $ | 0.40 € 0.44 $ | 5.50 € 6.06 $ | — |
USD prices are converted from EUR at the ECB reference rate of 1 EUR = 1.1014 USD (2026-11-16). EUR prices are authoritative.
Prices as of 16.11.2026.
Other Trust Levels
Prices for the other trust levels available for this model.
| Trust Level | Region | Context | Max output | Input / 1M | Cache / 1M | Output / 1M | §203 |
|---|---|---|---|---|---|---|---|
| TL0 | US | — | — | 1.80 € 1.98 $ | 0.25 € 0.28 $ | 5.50 € 6.06 $ | — |
About this model
Qwen3.8-Flash is Alibaba's production multimodal reasoning model, based on the open-weight Qwen3.8-Flash-Next architecture introduced as a preview of Qwen4. Its Mixture-of-Experts backbone has 125B parameters with 6B active per token, supplemented by 51B n-gram embedding parameters. Gated DeltaNet compresses long-range history, while Qwen Sparse Attention retrieves relevant context efficiently. The model is served with a 1M-token context window, extending the architecture's 262K native limit. It processes text, images, and video and generates text for repository-scale coding, document and chart analysis, long-video understanding, and multi-step office automation. Function calling, structured outputs, and selectable thinking levels support agentic workflows. Licensed under commercial terms by Alibaba B.V.
API
qwen3.8-max-0902-tl1
OpenAI compatibleAnthropic compatible
Base URL https://api.aki.io/v1
from openai import OpenAI
client = OpenAI(
api_key="YOUR_AKI_API_KEY",
base_url="https://api.aki.io/v1",
)
response = client.chat.completions.create(
model="qwen3.8-max-0902-tl1",
messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)
import OpenAI from "openai";
const client = new OpenAI({
apiKey: "YOUR_AKI_API_KEY",
baseURL: "https://api.aki.io/v1",
});
const response = await client.chat.completions.create({
model: "qwen3.8-max-0902-tl1",
messages: [{ role: "user", content: "Hello!" }],
});
console.log(response.choices[0].message.content);
curl https://api.aki.io/v1/chat/completions \
-H "Authorization: Bearer $AKI_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "qwen3.8-max-0902-tl1",
"messages": [{"role": "user", "content": "Hello!"}]
}'