Qwen 3.8 27B TL5

TL5 §203Open weights

Dense multimodal coding, visual reasoning, and agents with 256K native context

Pricing

Prices for this trust level. Prices are per 1M tokens.

Trust levels for this model
Trust Level Region Context Max outputInput / 1MCache / 1MOutput / 1M§203
TL5 DE 262K 66K 0.15 € 0.17 $ 0.075 € 0.083 $ 0.65 € 0.72 $ §203

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.

About this model

Qwen3.8 27B is Alibaba's open-weight, dense multimodal model for agentic software engineering, professional work, and visual reasoning. Its 27B-parameter transformer combines Gated DeltaNet linear attention with gated attention across 64 layers, supporting a native 262,144-token context window, extensible to 1M tokens. It accepts text, images, and video and generates text for repository-scale coding, debugging, document and chart interpretation, visual question answering, and long-video analysis. Function calling enables multi-step agents that plan, use tools, and adapt to feedback. Thinking is enabled by default but can be disabled; low, medium, and xhigh reasoning-effort settings and preserved thinking give developers control across turns. The model weights are available under Apache 2.0 for commercial use.

API

Model ID qwen3.8-27b 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="qwen3.8-27b",
    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: "qwen3.8-27b",
  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": "qwen3.8-27b",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Frequently Asked Questions

How much does Qwen 3.8 27B TL5 cost?
Input: 0.15 € per 1M tokens, Cache read: 0.075 € per 1M tokens, Output: 0.65 € per 1M tokens. Prices are exclusive of VAT.
What is the context window of Qwen 3.8 27B TL5?
Qwen 3.8 27B TL5 supports up to 262K tokens.
Which trust levels are available for Qwen 3.8 27B TL5?
Qwen 3.8 27B TL5 is available at TL5 (Germany Sovereign, DE).
Is Qwen 3.8 27B TL5 open weights?
Yes. The model weights are available on Hugging Face under the linked license.
Is Qwen 3.8 27B TL5 available with zero data retention?
Yes. Qwen 3.8 27B TL5 is served at TL5 (Germany Sovereign) with zero data retention and no model training.
How do I use Qwen 3.8 27B TL5 with the OpenAI SDK?
Use the model ID qwen3.8-27b with the OpenAI-compatible endpoint at https://api.aki.io/v1.

Start Building with Qwen 3.8 27B TL5