Qwen3.6-35B-A3B API

Alibaba's newest open-source mixture-of-experts model activates just 3 billion parameters at inference time, yet it goes toe-to-toe with dense models four to nine times its active size on agentic coding, reasoning, and multimodal tasks.

Modalities: Text, ImageText
In / Out price: $0.375/$2.25per 1M
Context window: 250K tokens
Released: Apr 23, 2026

Qwen3.6-35B-A3B overview

Qwen3.6-35B-A3B specs

Model ID: alibaba/qwen3.6-35b-a3b
Developer: Alibaba Cloud
Context window: 256,000 tokens
Max output: 252,000 tokens
Input: Text, Image
Output: Text
API: OpenAI-compatible, base URL https://api.aimlapi.com/v1

What It Is

Qwen3.6-35B-A3B is the latest open-source release from Alibaba's Qwen team, following the proprietary Qwen3.6-Plus launch. It's built on a sparse Mixture-of-Experts architecture, meaning only a small slice of the model is "awake" for any given token, which dramatically reduces compute without sacrificing output quality.

Exceptional Compute Efficiency

With just 3B active parameters, Qwen3.6-35B-A3B handles inference at the cost of a sub-4B dense model. You get the reasoning depth of something much larger without the GPU budget to match.

Built for Agentic Workflows

The model was explicitly trained and evaluated for multi-step coding agents, tool use, and MCP server interactions. It's not just a chat model, it's designed to plan, execute, and iterate inside automated pipelines.

Native Multimodal Understanding

Vision is a first-class citizen, not an add-on. The model processes images, diagrams, documents, and video frames natively, and its visual reasoning benchmarks are surprisingly strong for a model of this active-parameter count.

Thinking and Non-Thinking Modes

Switch between extended chain-of-thought reasoning (thinking mode) and fast, direct responses (non-thinking mode) within the same model. Both modes are supported via a simple API flag, no separate model download needed.

Model Architecture

The MoE design isn't just a numbers game. The way Qwen3.6-35B-A3B routes information through its expert layers is what separates it from earlier sparse models that struggled with coherence and reasoning depth.

Use cases

Qwen3.6 35B A3B is documented as suited to agentic coding, including frontend workflows and repository-level reasoning. It is also documented as a coding assistant that can be integrated with third-party coding tools to streamline development workflows. The model is described as suitable for long-horizon programming tasks and terminal-based programming, with benchmark references including NL2Repo and Terminal-Bench 2.0. It is also documented for multimodal reasoning across text, image, and video inputs.

Capabilities

Function calling
Streaming
Structured outputs
Reasoning
Web search

Qwen3.6-35B-A3B benchmarks by Artificial Analysis

See how Qwen3.6-35B-A3B compares in generation speed and latency. Data retrieved Nov 3, 2026.

Speed#74 / 219134Output tokens / second Latency#143 / 2162.04Seconds to first token Humanity's Last Exam#131 / 45822.2%Score GPQA Diamond#105 / 43984.1%Score

Speed

Output tokens / second

Benchmark results

Compare 9 models available on AI/ML API across 5 independent benchmarks.

Humanity's Last Exam

Expert-written questions across academic subjects.

Qwen3.6-35B-A3B API pricing

Qwen3.6-35B-A3B pricing in US dollars
Usage	Price	Unit
Input	$0.375	1M tokens
Output	$2.25	1M tokens

Prices from the AI/ML API price list, checked on Nov 4, 2026.

Qwen3.6-35B-A3B vs other models: token prices

AI/ML API input and output rates for 5 models, per million tokens.

AI/ML API model prices in USD per million tokens
Model	Input	Output
Qwen3.6-35B-A3B	$0.375	$2.25
Qwen3.8 Omni Flash	$0.15	$0.47
Qwen3.8-Flash	$0.16	$0.47
Qwen 3.8 27B	$0.4761	$3.39
Qwen3.8 Max Prime	$4.23	$12.7

How to use the Qwen3.6-35B-A3B API

View docs

Build with your agent

Give your agent the model details, code and documentation.

1Get your API key

Create API key

export AIMLAPI_KEY="8f2b4c7d9a1e6b3f…"

2Make your first request

curl 'https://api.aimlapi.com/v1/chat/completions' \
  -H "Authorization: Bearer $AIMLAPI_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "alibaba/qwen3.6-35b-a3b",
  "messages": [
    {
      "role": "user",
      "content": "Write a haiku about the ocean."
    }
  ]
}'

import os
import requests

headers = {
    "Authorization": f"Bearer {os.environ['AIMLAPI_KEY']}",
    "Content-Type": "application/json",
}
payload = {
    "model": "alibaba/qwen3.6-35b-a3b",
    "messages": [
        {
            "role": "user",
            "content": "Write a haiku about the ocean."
        }
    ]
}

response = requests.post("https://api.aimlapi.com/v1/chat/completions", headers=headers, json=payload, timeout=120)
response.raise_for_status()
print(response.json())

const response = await fetch("https://api.aimlapi.com/v1/chat/completions", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "model": "alibaba/qwen3.6-35b-a3b",
    "messages": [
      {
        "role": "user",
        "content": "Write a haiku about the ocean."
      }
    ]
  }),
});

if (!response.ok) throw new Error(`HTTP ${response.status}`);
console.log(await response.json());

All posts

Qwen3.6-35B-A3B FAQ

What is the context window of Qwen3.6-35B-A3B?

Qwen3.6-35B-A3B has a 256,000 tokens context window and can return up to 252,000 tokens.

What inputs and outputs does Qwen3.6-35B-A3B support?

Qwen3.6-35B-A3B takes image, text as input and returns text.

What is the model ID for Qwen3.6-35B-A3B?

Use alibaba/qwen3.6-35b-a3b as the model id. Requests go to https://api.aimlapi.com/v1/chat/completions.

When was Qwen3.6-35B-A3B released?

Qwen3.6-35B-A3B became available on April 23, 2026.

How much does Qwen3.6-35B-A3B cost?

Qwen3.6-35B-A3B costs $0.375 input and $2.25 output per 1M tokens on AI/ML API, billed as you go with no subscription.

Does Qwen3.6-35B-A3B support streaming?

Yes, Qwen3.6-35B-A3B can stream responses as they are generated.

Can Qwen3.6-35B-A3B read images?

Yes, Qwen3.6-35B-A3B accepts image input alongside text.

Who created Qwen3.6-35B-A3B?

Qwen3.6-35B-A3B was built by Alibaba Cloud.

Can Qwen3.6-35B-A3B process both images and text?

Yes, it accepts image and text input and produces text output, supporting vision tasks.

Does Qwen3.6-35B-A3B use reasoning capabilities?

Yes, reasoning is listed as one of its features and capabilities.

Start building with Qwen3.6-35B-A3B

Get API key

Qwen3.6-35B-A3B API

alibaba/qwen3.6-35b-a3b

Build with your agent

Give your agent the model details, code and documentation.

1Get your API key

Create API key

export AIMLAPI_KEY="8f2b4c7d9a1e6b3f…"

2Make your first request

curl 'https://api.aimlapi.com/v1/chat/completions' \
  -H "Authorization: Bearer $AIMLAPI_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "alibaba/qwen3.6-35b-a3b",
  "messages": [
    {
      "role": "user",
      "content": "Write a haiku about the ocean."
    }
  ]
}'

import os
import requests

headers = {
    "Authorization": f"Bearer {os.environ['AIMLAPI_KEY']}",
    "Content-Type": "application/json",
}
payload = {
    "model": "alibaba/qwen3.6-35b-a3b",
    "messages": [
        {
            "role": "user",
            "content": "Write a haiku about the ocean."
        }
    ]
}

response = requests.post("https://api.aimlapi.com/v1/chat/completions", headers=headers, json=payload, timeout=120)
response.raise_for_status()
print(response.json())

const response = await fetch("https://api.aimlapi.com/v1/chat/completions", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "model": "alibaba/qwen3.6-35b-a3b",
    "messages": [
      {
        "role": "user",
        "content": "Write a haiku about the ocean."
      }
    ]
  }),
});

if (!response.ok) throw new Error(`HTTP ${response.status}`);
console.log(await response.json());

Docs for AI agents Plain-text index · llms.txt API documentation API reference and examples

Talk to our sales team

Thanks for reaching out

Qwen3.6-35B-A3B API

Qwen3.6-35B-A3B overview

Qwen3.6-35B-A3B specs

What It Is

Exceptional Compute Efficiency

Built for Agentic Workflows

Native Multimodal Understanding

Thinking and Non-Thinking Modes

Model Architecture

Use cases

Capabilities

Qwen3.6-35B-A3B benchmarks by Artificial Analysis

Speed

Benchmark results

Humanity's Last Exam

GPQA Diamond

Terminal-Bench 4.0

AA-LCR

SciCode

Qwen3.6-35B-A3B API pricing

Qwen3.6-35B-A3B vs other models: token prices

How to use the Qwen3.6-35B-A3B API

Build with your agent

1Get your API key

2Make your first request

Related articles

Qwen3.6-35B-A3B FAQ

Start building with Qwen3.6-35B-A3B

Qwen3.6-35B-A3B API

Build with your agent

1Get your API key

2Make your first request

Qwen3.6-35B-A3B API

Qwen3.6-35B-A3B overview

Qwen3.6-35B-A3B specs

What It Is

Exceptional Compute Efficiency

Built for Agentic Workflows

Native Multimodal Understanding

Thinking and Non-Thinking Modes

Model Architecture

Use cases

Capabilities

Speed

Benchmark results

Humanity's Last Exam

GPQA Diamond

Terminal-Bench 4.0

AA-LCR

SciCode

Qwen3.6-35B-A3B API pricing

Qwen3.6-35B-A3B vs other models: token prices

How to use the Qwen3.6-35B-A3B API

Build with your agent

1Get your API key

2Make your first request

Models similar to Qwen3.6-35B-A3B

Qwen3.8 Max Prime

Qwen3.8 Omni Flash

Qwen3.8-Flash

Small 3.1 24B

LFM2.5-2.6B

Muse Glimmer 30B

Related articles

Best AI Models for Agentic Workflows and Tool Use in 2026

Best LLMs for Long-Context & Multimodal Tasks in 2026

Qwen3.6-35B-A3B FAQ

Start building with Qwen3.6-35B-A3B