Qwen3.5-397B-A17B

Text

Flagship open-weight Qwen3.5 vision MoE (17B active); 256K context; OpenAI-compatible API

Input $0.60 / 1M tokens | Output $3.60 / 1M tokens Qwen3.5-397B-A17B API reference →

Model health Insufficient data

runapi.ai

# Base URL
https://runapi.ai

# Endpoints
POST /v1/chat/completions
POST /v1/responses
POST /v1/messages
POST /v1beta/models/qwen3.5-397b-a17b:generateContent
POST /v1beta/models/qwen3.5-397b-a17b:streamGenerateContent

curl https://runapi.ai/v1/chat/completions \
  -H "Authorization: Bearer $RUNAPI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "qwen3.5-397b-a17b",
  "messages": [
    {
      "role": "user",
      "content": "Read this screenshot of a failing dashboard, explain what the error message means, and suggest the code change that would fix it."
    }
  ]
}'

from openai import OpenAI

client = OpenAI(
    base_url="https://runapi.ai/v1",
    api_key="your-runapi-key"
)

response = client.chat.completions.create(
    model="qwen3.5-397b-a17b",
    messages=[{"role": "user", "content": "Read this screenshot of a failing dashboard, explain what the error message means, and suggest the code change that would fix it."}]
)

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://runapi.ai/v1",
  apiKey: "your-runapi-key"
});

const response = await client.chat.completions.create({
  model: "qwen3.5-397b-a17b",
  messages: [{ role: "user", content: "Read this screenshot of a failing dashboard, explain what the error message means, and suggest the code change that would fix it." }]
});

https://runapi.ai 5 endpoints

9 versions available

OVERVIEW

What Qwen3.5-397B-A17B is built for

Qwen3.5-397B-A17B is the flagship open-weight model of Alibaba's Qwen3.5 generation, released under Apache 2.0 on February 16, 2026. It is a native vision-language model that combines hybrid linear attention with a sparse Mixture-of-Experts design: 397B total parameters and 17B active per token. Alibaba targets it at language, reasoning, coding, agents, image and video understanding, and GUI interaction.

It is a hybrid model with thinking and non-thinking modes, and Alibaba's API turns thinking on by default. The context window is 262,144 tokens, with up to 65,536 output tokens. Alibaba lists function calling and structured outputs as supported.

On RunAPI, call qwen3.5-397b-a17b through the OpenAI-compatible Chat Completions endpoint (/v1/chat/completions) with an OpenAI SDK pointed at https://runapi.ai/v1. Images go in image_url parts inside messages[].content[], and tools use the standard OpenAI tools format.

Model ID

qwen3.5-397b-a17b

Released

February 16, 2026

Architecture

MoE, 397B total / 17B active, Apache 2.0 weights

Context window

262,144 tokens

Max output

65,536 tokens

Thinking

Hybrid, on by default

Endpoint on RunAPI

OpenAI Chat Completions, text and image input

Playground

Try Qwen3.5-397B-A17B

Pick any model and generate in seconds.

Specifications

Provider	Alibaba
Model ID	qwen3.5-397b-a17b
Modality	Text
Task types	Synchronous
API endpoint	/v1/chat/completions
	/v1/responses

	/v1/messages
	/v1beta/models/qwen3.5-397b-a17b:generateContent
	/v1beta/models/qwen3.5-397b-a17b:streamGenerateContent
Billing unit	1K tokens
Catalog status	Operational

HOW IT WORKS

Use This Model in 3 Steps

Get Your Key

Sign up for free and create an API key for qwen3.5-397b-a17b from the dashboard.
Send a Request

POST to /v1/chat/completions with the qwen3.5-397b-a17b model slug and your parameters.
Get Results

Read the completed qwen3.5-397b-a17b response directly from the endpoint.

What this model offers

Endpoint coverage

Exposes 1 public endpoint(s): chat_completion.

Usage-based billing

Metered by 1K tokens with no subscription requirement.

Qwen3.5-397B-A17B Pricing

Endpoint

Price

chat_completion

Input: $0.60 / 1M tokens Output: $3.60 / 1M tokens

API REFERENCE

Endpoint Specification

Endpoint: POST /v1/chat/completions
Model ID: qwen3.5-397b-a17b
Task Types: chat_completion

Request parameters

No request parameters are published for this endpoint.

USE CASES

Customer support

Answer customer questions from a private knowledge base, reducing ticket volume.

Document analysis

Draft contract summaries and flag key clauses for attorney review.

Code generation

Auto-generate unit tests, code reviews, and refactoring suggestions in CI.

Trusted by developers

API Calls / Day

100.0%

Success Rate

10.6s

Avg Generation

Verified customer feedback is not available for this model yet.

FAQ

Frequently asked questions about Qwen3.5-397B-A17B

Which Qwen3.5 model should I choose?

Qwen3.5-397B-A17B is the largest. Alibaba ranks Qwen3.5-122B-A10B second, rates Qwen3.5-27B as comparable to the 122B model overall, and rates Qwen3.5-35B-A3B as comparable to the 27B model. All four have a 262,144-token context window and accept images.

Can Qwen3.5-397B-A17B read images?

Yes. It is a native vision-language model. On RunAPI, send image_url parts with your text in a Chat Completions request. Alibaba also lists video input; video requests are not verified on RunAPI.

Does Qwen3.5-397B-A17B support function calling?

Yes. Alibaba lists function calling and structured outputs as supported. On RunAPI, send tools in the OpenAI format on Chat Completions and read tool_calls from the response.

Is Qwen3.5-397B-A17B the newest Qwen model?

No. Alibaba has released Qwen3.6 since and now lists the Qwen3.5 models among its previous-generation models, though it still serves them. Qwen reports that Qwen3.6-27B, also on RunAPI, surpasses Qwen3.5-397B-A17B in agentic coding.

How do I select qwen3.5-397b-a17b?

Pass the model ID shown in the quickstart.

What's the rate limit on this variant?

Per-key rate limits scale with your usage tier. The pricing page shows current limits. If you need higher throughput, contact support to discuss tier upgrades.

Can I switch variants later?

Yes. Variant is a parameter in the request. Switch by changing the model ID — no code changes, no re-authentication, no separate billing setup. All variants share the same API key and request shape.

Does it stream?

Where streaming is available, RunAPI streams end-to-end. LLM models support token-level streaming. Media models use async task polling or webhook callbacks for result delivery.

Where do I report quality issues?

Open an issue on the public GitHub repo or email support at [email protected]. Include the task ID and model ID so the team can investigate the specific generation.

Do I need a separate provider account?

No. Your RunAPI API key is enough to access this variant and every other model in the catalog. You do not need accounts with the underlying provider.

Building with a team?

We're here to help with enterprise setup, integrations, and technical questions.