Skip to content
Start freeGPT-5 · Claude · DeepSeek V4 · Qwen3 — in ₹One OpenAI-compatible endpointBilled in rupeesGST invoiceNo international cardGet started →Start freeGPT-5 · Claude · DeepSeek V4 · Qwen3 — in ₹One OpenAI-compatible endpointBilled in rupeesGST invoiceNo international cardGet started →
Model API Guides

Qwen3 VL 235B A22B API in India

Qwen3 VL 235B A22B: ₹19.26 input, ₹84.73 output per 1M tokens in India. Alibaba's large vision-language model for documents and screenshots.

Qwen3 VL 235B A22B Instruct is Alibaba's large vision-language model, live on unoblox as qwen/qwen3-vl-235b-a22b-instruct. It reads images alongside text, supports tool calling, and bills in rupees with a GST invoice.

What Qwen3 VL 235B A22B is

This is the instruction-tuned version of Qwen3-VL-235B-A22B, a mixture-of-experts model with 235 billion total and 22 billion active parameters. It handles interleaved text, images and video in Alibaba's design, and unoblox exposes text and image input with text output over a 262,144-token context. Alibaba highlights OCR across 32 languages, including difficult conditions such as blur or tilt, and the ability to read GUI screenshots and plan actions.

It is an Instruct model, so it answers directly rather than producing a separate reasoning trace.

Where it fits

  • Document OCR and extraction from scans, forms and invoices.
  • Screenshot understanding for UI testing and support tooling.
  • Chart and diagram Q&A combined with written questions.

Use it when vision is the main need. For a model with reasoning plus vision, look at Qwen3.5 397B A17B. For text-only work, a text model is usually cheaper.

₹ pricing for Qwen3 VL 235B A22B

On unoblox, Qwen3 VL 235B A22B costs ₹19.26 per million input tokens and ₹84.73 per million output tokens. That displayed price is what you are billed per token; nothing is added on top. Cached input tokens are listed at ₹10.59 per million. The model's context length on unoblox is 262,144 tokens.

ModelInput (₹ / 1M tokens)Output (₹ / 1M tokens)
Qwen3 VL 235B A22B₹19.26₹84.73
Qwen3.5 397B A17B₹43.33₹288.85
Qwen3.6 35B A3B₹9.63₹91.47
Qwen3 235B A22B₹8.67₹52.96

As a worked example, a month with 20 million input tokens and 4 million output tokens comes to about ₹724.12 on Qwen3 VL 235B A22B (₹385.20 for input plus ₹338.92 for output). Live rates are always on the model page, and each request is rounded up to the nearest paisa.

Calling Qwen3 VL 235B A22B 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-vl-235b-a22b-instruct",
    "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-vl-235b-a22b-instruct",
    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-vl-235b-a22b-instruct",
    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. Send images as image_url content parts, either HTTPS URLs or base64 data URLs. The model runs at an external provider and not in India, so we claim no data residency. Check any document you process against your own privacy obligations before sending it.

Frequently asked questions

Is Qwen3 VL 235B available in India? Yes, as qwen/qwen3-vl-235b-a22b-instruct on https://api.unoblox.ai/v1.

Does it support video? Alibaba describes video support in the model, but unoblox lists text and image input only.

What is the context length? 262,144 tokens.

Does it support reasoning mode? This is the Instruct variant and the catalogue lists tools, not reasoning.

Is it good at OCR? Alibaba highlights OCR in 32 languages; test on your own documents.

Do I get a GST invoice? Yes.

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

qwen3 vl 235b a22b api indiallmqwenqwen3-vl-235b-a22b-instruct
ShareLinkedInWhatsAppTelegram

Start building in rupees

Call every major model through one OpenAI-compatible endpoint, billed in ₹ on a GST invoice.