Qwen3.5 35B A3B API

Call Qwen3.5 35B A3B from the OpenAI SDK for reasoning, code, images, and tool calling, from $0.126 per million input tokens.

Get API key Read the docs

262K context window
36B total parameters
3B active parameters
Apache 2.0 open license

from openai import OpenAI

client = OpenAI(
    base_url="https://api.modelsheep.com",
    api_key=API_KEY_MODELSHEEP,
)

response = client.chat.completions.create(
    model="Qwen/Qwen3.5-35B-A3B",
    messages=[
        {
            "role": "user",
            "content": "Why do sheep count people?"
        }
    ],
)

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

How to use the Qwen3.5 35B A3B API

1
Create a ModelSheep account and copy an API key from the dashboard.
2
Point the OpenAI SDK at the base url https://api.modelsheep.com and set the model to Qwen/Qwen3.5-35B-A3B.
3
Send your messages to /chat/completions, read the answer from choices[0].message.content, and pass chat_template_kwargs: { enable_thinking: false } to skip the reasoning the model runs by default.

What Qwen3.5 35B A3B is

Qwen3.5 35B A3B is a mixture of experts model from the Qwen team at Alibaba. It has 36B parameters and activates 3B per token. One request touches a small part of the weights. Text, images, and video enter one backbone because Qwen3.5 trains vision and text together instead of adding a vision model later. The Qwen3.5 flagship is larger. This size keeps the same architecture, the same 262K window, and support for 201 languages.

What it does well

Picks a function from your tool list and returns the arguments as JSON so an
Reads a scanned invoice, screenshot, or video and returns the fields in the
Writes and reviews code and works through the problem in a reasoning block

What it is not for

Reasoning runs by default and spends output tokens before the answer starts.
The window stops at 262K tokens. Qwen documents a longer one through

Calling it

Send a POST to /chat/completions with any OpenAI client. Name the model Qwen/Qwen3.5-35B-A3B because the API serves the FP8 build and rejects the plain repo id. The model reasons before it answers. Pass chat_template_kwargs: { enable_thinking: false } to get the answer alone.

Qwen/Qwen3.5-35B-A3B /chat/completions

SDKs and languages

Qwen3.5 35B A3B answers on an HTTP endpoint, so any language that can post JSON reaches it. These are the ones the box above writes out.

OpenAI SDK: PythonTypeScriptGoJavaC#PHPRust
Anthropic SDK: PythonTypeScriptGoJavaC#PHPRust
HTTP: cURLPythonTypeScriptGoRustJavaC#PHP

Specifications

Author	Qwen
Category	language
Accepts	text, image, video
Returns	text
Total parameters	36B
Active parameters	3B
Score	19.3 on Artificial Analysis intelligence index
Languages	201Qwen counts languages and dialects together, so it is not 201 distinct languages. Programming languages are not in the count.
Precision served	FP8
Context	262K tokensQwen documents an extension to about 1M with YaRN, which the serving config has to enable.
Vector	n/a
Pulls	1.8M in the last 30 daysWeights pulled from Hugging Face, read on 2026-09-24. It counts the repository, not this API.
License	Apache 2.0

Price

Input

$0.126

per million tokens

Output

$0.900

per million tokens

Against OpenRouter

10%

below the cheapest of 6 providers

The cheapest OpenRouter price for this model was $0.140 in and $1.000 out, with a median of $0.225 and $1.300 across the comparable providers. Read on 2026-09-17.

License

The weights ship under Apache 2.0. It permits commercial use, changes, and redistribution as long as you keep the license notice. You can ship on this model without reading a separate vendor term.

Similar models

MiMo V2.5XiaomiMiMo/MiMo-V2.5 🤗

Parameters: 310.8B, 15B
Context: 1.1M
Input per 1M: $0.126
Output per 1M: $0.252
Released: Apr 2026
Pulls, 30 days: 282.1K
License: MIT

Kimi K2.6moonshotai/Kimi-K2.6 🤗

Parameters: 1T, 32B
Context: 262K
Input per 1M: $0.513
Output per 1M: $2.160
Released: Apr 2026
Pulls, 30 days: 441K
License: Modified MIT

Minimax M3MiniMaxAI/MiniMax-M3 🤗

Parameters: 427B, 23B
Context: 1M
Input per 1M: $0.252
Output per 1M: $0.990
Released: Jun 2026
Pulls, 30 days: 167.7K
License: MiniMax Community

Start using Qwen3.5 35B A3B

Point the OpenAI SDK at api.modelsheep.com. Your prompts stay in Germany, and nothing is retained.

Get API key Read the quickstart