Qwen3.5-35b-a3b

Active

qwen/qwen3.5-35b-a3b

Qwen3.5系列35B-A3B原生视觉语言模型，基于混合架构设计，融合了线性注意力机制与稀疏混合专家模型，实现了更高的推理效率。该模型的综合表现接近于Qwen3.5-27B。

ChatQwenTool callingVisionLong context

Pricing

Pay as you go · priced in CNY

Pay as you go · priced in CNYToken pricing

Input

¥0.400

/ 1M tokens

Output

¥3.20

/ 1M tokens

Cache read

—

Not listed

Cache write

—

Not listed

Providers and quotes

1 routes · pay as you go

Provider	Input	Output	Cache read	Context length	Latency	Uptime	Status
dashscope dashscope/qwen3.5-35b-a3b	¥0.800	¥4.80	—	256K	3.8s	88.70%	Lowest

API examples

OpenAI compatible

Endpoint/chat/completionsmodel: qwen/qwen3.5-35b-a3b

python

from openai import OpenAI

client = OpenAI(
  base_url="https://api.openroute.cn/v1",
  api_key="<ONTOROUTE_API_KEY>",
)

completion = client.chat.completions.create(
  model="qwen/qwen3.5-35b-a3b",
  messages=[
    {
      "role": "user",
      "content": "Write a one-sentence bedtime story about a unicorn.",
    }
  ],
)

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

OpenRoute exposes an OpenAI-compatible Chat Completions API across 400+ models and providers. Call it directly or via the OpenAI SDK. Third-party SDKs are also available.

Request parameters

Calls (30d)

1 supply routes

Avg. latency

3838ms

Time to first token

Usage trend

近 14 天 3.1K tokens

10-0910-22

Connectivity

Last 84 hours · Proxy probes