GLM vs Qwen in India: what unoblox offers

If you're weighing GLM against Qwen, know one thing first: Zhipu's GLM models are not available on unoblox. Alibaba's Qwen line is. We don't serve GLM, so this page doesn't make claims about it. It lays out the Qwen models you can call today, billed in rupees, so you can pick a size.

The Qwen line on unoblox

Rates below are as listed on 7 October 2026; the model page always shows the live rate.

Model	Model id	Input (₹ / 1M)	Output (₹ / 1M)	Input types	Context window
Qwen3.8-27B	qwen/qwen3.8-27b	₹0	₹0	text and image	262,144
Qwen3 235B A22B	qwen/qwen3-235b-a22b-instruct-2507	₹9.11	₹55.70	text only	262,144
Qwen3.6 35B A3B	qwen/qwen3.6-35b-a3b	₹10.12	₹96.20	text and image	262,144
Qwen3.8 Flash	qwen/qwen3.8-flash	₹11.44	₹38.68	text only	1,000,000
Qwen3 VL 235B A22B	qwen/qwen3-vl-235b-a22b-instruct	₹20.25	₹89.11	text and image	262,144
Qwen3.5 397B A17B	qwen/qwen3.5-397b-a17b	₹45.57	₹303.80	text and image	262,144
Qwen3 Max	qwen/qwen3-max	₹121.52	₹607.61	text only	256,000
Qwen3.8 Max	qwen/qwen3.8-max	₹167.09	₹501.38	text only	256,000

Qwen3 Max's rate depends on prompt length. The rate shown covers prompts up to 32,000 tokens. Longer prompts move the whole request to a higher tier: ₹243.04 / ₹1,215.23 from 32,001 prompt tokens, and ₹303.80 / ₹1,519.04 from 128,001. Every listed rate already includes unoblox's 5% platform fee, and you are charged exactly the listed rate.

Choosing a Qwen model

• Free, for prototyping and light production: qwen/qwen3.8-27b is ₹0 and accepts images. A fair-use limit of 10 requests per minute per workspace applies; see Freemium access.
• Low-cost paid text: among the paid Qwen models, Qwen3 235B A22B has the lowest input rate (₹9.11) and Qwen3.8 Flash the lowest output rate (₹38.68). Qwen3.8 Flash lists a 1,000,000-token context window.
• Image input on a paid model: Qwen3.6 35B A3B, Qwen3 VL 235B A22B and Qwen3.5 397B A17B.
• Top of the line: Qwen3.8 Max and Qwen3 Max cost more. Check their quality on your own prompts before you commit.

Calling Qwen

curl https://api.unoblox.ai/v1/chat/completions \
  -H "Authorization: Bearer ub-gw-xxxxxxxxxxxxxxxx" \
  -H "Content-Type: application/json" \
  -d '{"model":"qwen/qwen3.8-flash","messages":[{"role":"user","content":"Translate this paragraph into Hindi."}]}'

Frequently asked questions

Is GLM available on unoblox? No. GLM is not in the catalog.

Which Qwen models run in India? Qwen3.8-27B runs on unoblox's own GPUs in India. The paid Qwen models run at upstream providers outside India.

How is usage billed? Usage is paid from a prepaid rupee wallet. GST at 18% is added when you top up (pay ₹118 and ₹100 of credit lands in your wallet), and one GST tax invoice is issued for each top-up; individual requests carry no separate invoice.

Where are live rates? On each model page, for example Qwen3.8-27B and Qwen3.8 Flash.

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