Overview

Qwen 3.5 397B delivers enterprise-grade performance using an advanced Mixture of Experts architecture designed for complex workloads. With 397 billion parameters and a 32,768 token context window, this vision-enabled model excels at multimodal reasoning and detailed document analysis. Developers can integrate these capabilities seamlessly via our standardized API, enabling rapid prototyping and first API calls within minutes. The FP16 quantization ensures high precision for research pipelines requiring rigorous benchmark validation against leading global alternatives, making it ideal for demanding AI applications. We provide comprehensive documentation to accelerate your integration process further.

Licensed under APACHE-2.0, this model offers significant flexibility for commercial deployment without restrictive barriers. While the 3.5x credit multiplier reflects its advanced computational demands, our transparent pricing structure allows for accurate budget forecasting in any preferred currency. It is production-ready for high-stakes applications, supporting robust Arabic and English language tasks essential for regional scalability and diverse user bases. Start building immediately with our starter tier access to leverage state-of-the-art intelligence without infrastructure overhead. Our platform ensures consistent uptime for critical business operations.

Specifications

Display Name Qwen 3.5 397B

Family Qwen

Category Vision

Parameters 397B

Context Window 32,768 tokens

Quantization FP16

License APACHE-2.0

Min Tier Starter

Status Available

Pricing

3.5×

credits per token

1K 3,500 Credits

10K 35,000 Credits

100K 350,000 Credits

View Pricing Plans

Code Examples

from openai import OpenAI

client = OpenAI(
    base_url="https://llmapi.resayil.io/v1/",
    api_key="YOUR_API_KEY"
)

response = client.chat.completions.create(
    model="qwen3.5:397b",
    messages=[
        {"role": "user", "content": "Hello!"}
    ]
)

print(response.choices[0].message.content)

const response = await fetch(
    "https://llmapi.resayil.io/v1/chat/completions",
    {
        method: "POST",
        headers: {
            "Content-Type": "application/json",
            "Authorization": "Bearer YOUR_API_KEY"
        },
        body: JSON.stringify({
            model: "qwen3.5:397b",
            messages: [
                { role: "user", content: "Hello!" }
            ]
        })
    }
);

const data = await response.json();
console.log(data.choices[0].message.content);

curl https://llmapi.resayil.io/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "qwen3.5:397b",
    "messages": [
      {"role": "user", "content": "Hello!"}
    ]
  }'

Use Cases

Analyzing complex charts and graphs in financial reports

Converting user interface screenshots into functional frontend code

Extracting and summarizing text from scanned document images

Detailed visual reasoning for scientific diagram interpretation

Multimodal content moderation for images and associated text

In-Depth Guide

Full Guide

Complete Guide to Qwen 3.5 397B — LLM Resayil

Qwen 3.5 397B