Qwen: Qwen3.6 35B A3B

qwen/qwen3.6-35b-a3b

262KContext Window

4KMax Output

Normal

Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per token. It uses a hybrid sparse mixture-of-experts architecture combining Gated DeltaNet linear attention with standard gated attention layers, enabling efficient inference at a fraction of the compute cost. The model supports a 262K token native context window (extensible to 1M via YaRN) and accepts text, image, and video inputs. It includes integrated thinking mode with reasoning traces preserved across multi-turn conversations, function calling, and structured output. Released under the Apache 2.0 license.

Capabilities

Text GenerationVideo Generation

Technical Specs

Input Modality

Text

Output Modality

Text

Arch

—

Pricing

Pay per use, no monthly fees

Billing Type	Unit	Price
Text Input	—	$0.1612/M tokens
Text Output	—	$0.9653/M tokens
Cache Read	—	$0.1612/M tokens

Quick Start

from openai import OpenAI

client = OpenAI(
    base_url="https://api.uniontoken.ai/v1",
    api_key="YOUR_UNIONTOKEN_API_KEY",
)

response = client.chat.completions.create(
    model="qwen/qwen3.6-35b-a3b",
    messages=[
        {"role": "user", "content": "Hello!"}
    ],
)

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