qwen/qwen3.5-397b-a17b — Free AI Model & API

Verified
nvidia-nim/qwen-qwen3-5-397b-a17b
chat
Get API key →
Context Window 262K
Max Output 66K
Rate Limit Up to 40 RPM
Cost $0.00 FREE
Free Period Since Feb 16, 2026
Credit Card Not required
Status Online

Overview

Qwen3.5 397B (17B active via MoE) is Alibaba's largest publicly-hosted model, free on NVIDIA NIM with up to 40 RPM and no daily token cap. The enormous expert pool at 397B total parameters brings frontier-level capability while 17B active parameters maintain manageable inference cost. OpenAI-compatible API. Requires NVIDIA Developer Program membership and phone verification.

Model ID
qwen/qwen3.5-397b-a17b
Base URL
https://integrate.api.nvidia.com/v1
Specifications
Context: 262K · Output: 66K · Modality: text, image · OpenAI Compat: Yes ·Released: Feb 16, 2026

Quick Start

Integrate qwen/qwen3.5-397b-a17b with 3 lines of code. See the config generator for Claude Code, Cursor, and more.

from openai import OpenAI

client = OpenAI(
 base_url="https://integrate.api.nvidia.com/v1",
 api_key="YOUR_API_KEY"
)

response = client.chat.completions.create(
 model="qwen/qwen3.5-397b-a17b",
 messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)
import OpenAI from "openai";

const openai = new OpenAI({
 baseURL: "https://integrate.api.nvidia.com/v1",
 apiKey: "YOUR_API_KEY",
});

const completion = await openai.chat.completions.create({
 model: "qwen/qwen3.5-397b-a17b",
 messages: [{ role: "user", content: "Hello!" }],
});

console.log(completion.choices[0].message.content);
curl https://integrate.api.nvidia.com/v1/chat/completions \
 -H "Content-Type: application/json" \
 -H "Authorization: Bearer YOUR_API_KEY" \
 -d '{
 "model": "qwen/qwen3.5-397b-a17b",
 "messages": [{"role": "user", "content": "Hello!"}]
 }'

Other Free Models from NVIDIA NIM

deepseek-ai/deepseek-v4-flash

1.0M context · No card

deepseek-ai/deepseek-v4-pro

131K context · No card

meta/llama-3.1-70b-instruct

131K context · No card

meta/llama-3.2-11b-vision-instruct

131K context · No card

meta/llama-3.2-1b-instruct

131K context · No card

Rate Limits & Constraints

Rate Limit Up to 40 RPM
Context Window 262K
Max Output Tokens 66K
Cost Free — since Feb 16, 2026
Credit Card Not required
OpenAI Compatible Yes — drop-in replacement

NVIDIA NIM Platform Limitations

  • ~40 RPM shared across all models, not per-model
  • Some models require additional registration per model family
  • Unavailable models listed in catalog but uncallable with standard key

Features & Use Cases

Best For

Chat

Modality Support

textimage

NVIDIA NIM Highlights

  • 100+ open models available
  • No daily token cap
  • ~40 RPM free tier
  • No credit card required

Playground — Test qwen/qwen3.5-397b-a17b

Test qwen/qwen3.5-397b-a17b directly in your browser. Your API key is sent directly to NVIDIA NIM — never stored.

Model: qwen/qwen3.5-397b-a17b Get Key

🔒 Your key is never stored — sent directly to the model provider via our server proxy.

Ready to chat with qwen/qwen3.5-397b-a17b.

Frequently Asked Questions

How do I get an API key for qwen/qwen3.5-397b-a17b?

Sign up at NVIDIA NIM to get your API key. No credit card is required — just an email sign-up. Once you have the key, use the code snippets in the Quick Start section above.

Is qwen/qwen3.5-397b-a17b really free?

Yes. qwen/qwen3.5-397b-a17b is available on NVIDIA NIM's free tier and has been free since Feb 16, 2026. Rate limits apply: Up to 40 RPM. Always check the provider's terms for any changes to the free tier.

What are qwen/qwen3.5-397b-a17b's rate limits?

Up to 40 RPM Context window: 262K. Max output: 66K. No credit card required.

What are the best free alternatives to qwen/qwen3.5-397b-a17b?

Popular free alternatives include inclusionAI: Ring-2.6-1T, Baidu Qianfan: CoBuddy (free), Owl Alpha. You can also browse all 147+ free models on our site.

More questions? See our full FAQ →

Similar Free Models

inclusionAI: Ring-2.6-1T

OpenRouter · chat

Baidu Qianfan: CoBuddy (free)

OpenRouter · chat

Owl Alpha

OpenRouter · chat