Best Cheap LLM API in India: ₹ Price List

If you're building in India and every rupee of inference cost matters, the good news is unoblox's catalog has real range — from completely free models to paid models under ₹11 per million input tokens that are cheap enough to run at high volume without a second thought. Here's the ₹ price list as of 6 October 2026, cheapest input price first; the live rate is always on each model page.

The cheapest models on unoblox today, ranked

Model	Model id	Input (₹ / 1M tokens)	Output (₹ / 1M tokens)
Qwen3.8-27B	qwen/qwen3.8-27b	₹0 (free)	₹0 (free)
gpt-oss 20B	openai/gpt-oss-20b	₹3.03	₹14.17
GPT-5 nano	openai/gpt-5-nano	₹5.06	₹40.48
Nemotron 3.5 Lightning	nvidia/nemotron-3.5-lightning	₹6.06	₹16.20
DeepSeek V4 Flash (0731)	deepseek-ai/deepseek-v4-flash-0731	₹6.06	₹18.21
Mistral Small 3.2 24B	mistralai/mistral-small-3.2-24b-instruct-2506	₹7.59	₹20.24
DeepSeek V4 Flash	deepseek-ai/deepseek-v4-flash	₹9.11	₹18.21
Qwen3 235B-A22B	qwen/qwen3-235b-a22b-instruct-2507	₹9.11	₹55.67
Llama 4 Scout	meta-llama/llama-4-scout-17b-16e-instruct	₹10.12	₹30.36

Qwen3.8-27B and Gemma 4 26B A4B cost nothing to call — free models, not a time-boxed trial. Among paid models, gpt-oss 20B has both the lowest input price (₹3.03) and the lowest output price (₹14.17 per million tokens) in this table.

Why "cheap" still needs a fit check

A low ₹ rate only saves money if the model is actually good enough for your task — routing production traffic to a model that produces unusable output and needs a retry, or a fallback to a pricier model, can end up costing more than picking the right model the first time. Treat this list as a shortlist to test, not a guarantee.

Where each tier tends to fit

• Free models (Qwen3.8-27B, Gemma 4 26B A4B): prototyping, internal tools, low-stakes classification, or anywhere you want zero marginal cost while you validate an idea.
• Under ₹11 per million input tokens (gpt-oss 20B, GPT-5 nano, Nemotron 3.5 Lightning, DeepSeek V4 Flash, Mistral Small, Qwen3 235B-A22B, Llama 4 Scout): high-volume production workloads — support triage, tagging, extraction — where per-call cost needs to stay low. Compare output prices too: they range from ₹14.17 to ₹55.67 per million tokens across this group.
• Vision on a budget: Qwen3.8-27B accepts image input and is free.
• GPT-5 mini (₹25.30 / ₹202.46, not in the table above): a budget option if you specifically want OpenAI's ecosystem and tuning at a lower price than the GPT-5 flagship.

Calling the cheapest tier from your existing code

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":"Tag this ticket as billing, technical, or general."}]}'

Every model above uses the identical request shape — only the model id changes, and your GST invoice covers all of them together.

Frequently asked questions

Is Qwen3.8-27B really free, with no catch? Yes — it's priced at ₹0 for both input and output tokens on unoblox; there's no separate trial period tied to it.

What's the cheapest paid model for high-output workloads? gpt-oss 20B, at ₹14.17 per million output tokens, is the lowest output rate among the paid models listed here; Nemotron 3.5 Lightning (₹16.20) and DeepSeek V4 Flash (₹18.21) are next.

Will a cheap model be good enough for my use case? It depends entirely on the task — test it against your own prompts before routing production traffic, since ₹ cost and output quality are separate questions.

Are there hidden fees on top of the per-token ₹ rate? unoblox bills usage with a GST tax invoice issued at each top-up; check your dashboard and the model's live page for the current rate before scaling up.

Can I mix a free model and paid models under one account? Yes — one key and one invoice cover every model in the catalog, free or paid.

Do these cheap models support the same features as premium ones, like streaming and tool calls? Yes, all models are served through the same OpenAI-compatible endpoint with consistent streaming and tool-calling support.

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