Qwen3.8 27B API in India

Qwen3.8 27B is an open-weights, vision-capable model from Alibaba's Qwen line, priced at ₹16.32 per 1M input tokens and ₹48.96 per 1M output tokens on unoblox — callable from India on the same ₹-billed, OpenAI-compatible endpoint as every other model, with one monthly GST invoice instead of a foreign-currency charge.

What Qwen3.8 27B brings: open weights plus vision

Two things stand out about this model in the catalogue: it ships as open weights, and it accepts image inputs alongside text in the same request. That combination makes it a practical choice for teams that want vision capability without committing to a closed vendor's roadmap, or that want the option to self-host the same weights later while running production traffic through unoblox's endpoint today.

₹ pricing for Qwen3.8 27B

Model	Input (₹ / 1M tokens)	Output (₹ / 1M tokens)
Qwen3 1.7B	Free (₹0)	Free (₹0)
Qwen3.8 27B	16.32	48.96
Qwen3 235B-A22B	9.07	55.44
Qwen3 Max	120.95	604.77

Qwen3.8 27B sits in the middle of the Qwen line on price, above the free 1.7B tier and below Qwen3 Max, while offering vision support that the smaller free tier doesn't carry.

Calling Qwen3.8 27B with an image

curl https://api.unoblox.ai/v1/chat/completions \
  -H "Authorization: Bearer ub-gw-xxxxxxxxxxxxxxxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen/qwen3.8-27b",
    "messages": [{"role": "user", "content": "Describe what is happening in this photo."}]
  }'

The request format matches the OpenAI chat completions shape, so vision-enabled requests built for another provider typically need only the model field and base URL changed.

Qwen3.8 27B vs the rest of the Qwen line

• Qwen3 1.7B — free, for text-scale workloads and prototyping where cost needs to be zero.
• Qwen3.8 27B — the open-weights, vision-capable middle tier, priced for production use without flagship-level cost.
• Qwen3 235B-A22B — larger active-parameter model for heavier reasoning, at a lower input cost than 27B but a higher output cost.
• Qwen3 Max — the top of the line, for tasks where quality matters more than per-token cost.

Frequently asked questions

Is Qwen3.8 27B available in India through unoblox? Yes, qwen/qwen3.8-27b is callable on https://api.unoblox.ai/v1 right after signup, billed in rupees.

What does Qwen3.8 27B cost on unoblox? ₹16.32 per 1M input tokens and ₹48.96 per 1M output tokens — check the model page for the current live rate.

Does Qwen3.8 27B support image inputs? Yes, it accepts images alongside text in the same request, in the standard OpenAI-compatible message format.

Is Qwen3.8 27B an open-weights model? Yes, it's part of Alibaba's open-weights Qwen line, callable here on unoblox's rupee-billed endpoint.

Does using Qwen3.8 27B through unoblox mean data stays in India? No, it runs on the upstream provider's infrastructure. The India-specific part is ₹ billing, a GST invoice and one endpoint, not data residency.

Is GST input tax credit available on Qwen3.8 27B usage? Yes, it's included in the same monthly GST invoice as every other model, and is claimable as input tax credit.

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