Qwen3.6 35B A3B API in India

Qwen3.6 35B A3B is a compact open-weight multimodal model from Alibaba, live on unoblox as qwen/qwen3.6-35b-a3b. It supports text and image input, reasoning and tools at one of the lower prices in the catalogue, billed in rupees.

What Qwen3.6 35B A3B is

Alibaba released Qwen3.6 35B A3B in April 2026. It is a sparse mixture-of-experts model with 35 billion total and about 3 billion active parameters per token, using a hybrid of linear and standard attention. Alibaba targets agentic coding, long-context reasoning and visual understanding such as chart reasoning and document parsing. unoblox lists a context length of 262,144 tokens.

With so few active parameters it is built to be inexpensive per request.

Where it fits

• Budget vision tasks like reading charts, invoices and screenshots.
• Lightweight coding assistants and agent loops.
• High-volume text workloads that still benefit from reasoning.

Choose it when cost matters and you still want image input. Move up to Qwen3.5 397B A17B or Qwen3.8 Max for harder problems.

₹ pricing for Qwen3.6 35B A3B

On unoblox, Qwen3.6 35B A3B costs ₹9.63 per million input tokens and ₹91.47 per million output tokens. That displayed price is what you are billed per token; nothing is added on top. The model's context length on unoblox is 262,144 tokens.

Model	Input (₹ / 1M tokens)	Output (₹ / 1M tokens)
Qwen3.6 35B A3B	₹9.63	₹91.47
Qwen3.5 397B A17B	₹43.33	₹288.85
gpt-oss 20B	₹2.89	₹13.48
DeepSeek V4 Flash (0731)	₹5.78	₹17.33

As a worked example, a month with 20 million input tokens and 4 million output tokens comes to about ₹558.48 on Qwen3.6 35B A3B (₹192.60 for input plus ₹365.88 for output). Live rates are always on the model page, and each request is rounded up to the nearest paisa.

Calling Qwen3.6 35B A3B from the unoblox endpoint

unoblox is OpenAI-compatible, so any OpenAI SDK works by changing the base URL and key.

curl https://api.unoblox.ai/v1/chat/completions \
  -H "Authorization: Bearer YOUR_UNOBLOX_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen/qwen3.6-35b-a3b",
    "messages": [{"role": "user", "content": "Summarise this support ticket in two lines."}],
    "max_tokens": 512
  }'

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_UNOBLOX_API_KEY",
    base_url="https://api.unoblox.ai/v1",
)
resp = client.chat.completions.create(
    model="qwen/qwen3.6-35b-a3b",
    messages=[{"role": "user", "content": "Summarise this support ticket in two lines."}],
    max_tokens=512,
)
print(resp.choices[0].message.content)

For image input, pass an image_url content part:

resp = client.chat.completions.create(
    model="qwen/qwen3.6-35b-a3b",
    messages=[{"role": "user", "content": [
        {"type": "text", "text": "What does this chart show?"},
        {"type": "image_url", "image_url": {"url": "https://example.com/chart.png"}},
    ]}],
    max_tokens=512,
)

Get a key at https://unoblox.ai/sign-in and top up your wallet in rupees.

Notes on parameters, billing and data

Use max_tokens for output limits. The model runs at an external provider and not in India, so no data-residency claim is made. unoblox provides rupee pricing, GST invoicing and one endpoint. Cached-prompt pricing is not listed for this model.

Frequently asked questions

Is Qwen3.6 35B A3B available in India? Yes, as qwen/qwen3.6-35b-a3b on https://api.unoblox.ai/v1.

Does it accept images? unoblox lists text and image input.

What is the context length? 262,144 tokens.

What does A3B mean? About 3 billion active parameters per token out of 35 billion total.

Does it support tools and reasoning? Yes, the catalogue lists both.

How is it billed? In rupees per million tokens with a GST invoice.

Get started in rupees → https://unoblox.ai/sign-in