Qwen3 1.7B free API in India: use Qwen3.8-27B

Qwen3 1.7B is offline on unoblox. It is not in the live model list (/v1/models). If you came here for a free Qwen API, the free model to use now is Qwen3.8-27B. Gemma 4 26B A4B is free too. Both cost ₹0 per token and use the same OpenAI-compatible endpoint and ub-gw- key as every paid model.

The free models

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
Gemma 4 26B A4B Instruct	google/gemma-4-26b-a4b-it	₹0	₹0	text and image	262,144

Both models list tool calling, reasoning and structured output (response_format). Both run on unoblox's own GPUs in India.

The limits

These models are tagged Freemium. Because their price is ₹0, a call costs nothing whatever your balance, even at zero. A fair-use limit of 10 requests per minute per workspace still applies. Past that limit you get HTTP 429, so wait a moment and retry. Freemium access and Rate limits have the exact rules. There's no monthly cap.

Calling Qwen3.8-27B

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": "Rewrite this sentence in plain English."}]
  }'

If your code called qwen/qwen3-1.7b, change the model field to qwen/qwen3.8-27b. Qwen3.8-27B is a much larger model than 1.7B, so its outputs and token counts will differ. Re-check any prompts you tuned for the small model.

When you outgrow the free tier

Moving to a paid model is a one-line change to the model field. Some low-cost paid options, at live rates per 1M tokens:

Model	Model id	Input (₹ / 1M)	Output (₹ / 1M)
gpt-oss 20B	openai/gpt-oss-20b	₹3.03	₹14.17
DeepSeek V4 Flash	deepseek-ai/deepseek-v4-flash	₹9.11	₹18.22
Qwen3 235B A22B	qwen/qwen3-235b-a22b-instruct-2507	₹9.11	₹55.70

Every listed rate already includes unoblox's 5% platform fee, and you are charged exactly the listed rate. 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.

Frequently asked questions

Can I still call Qwen3 1.7B? No. It is offline and not in the live model list. Use qwen/qwen3.8-27b instead.

Is Qwen3.8-27B really free? Yes. It is priced at ₹0 for input and output tokens. The fair-use limit of 10 requests per minute per workspace applies.

Do I need to top up to use the free models? No. A ₹0 price never draws on your wallet, so there is no insufficient-balance error.

Does Qwen3.8-27B accept images? Yes. The catalog lists text and image input. Gemma 4 26B A4B does too.

Where do the free models run? On unoblox's own GPUs in India.

Where can I check the current terms? On the Qwen3.8-27B model page and in Freemium access. A model's freemium status and price can change.

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