Skip to content
DeepSeek API · India

DeepSeek API, India — billed in rupees.

DeepSeek V4 Flash, V4.1 Flash and V3.2 through one OpenAI-compatible endpoint. Rupee pricing, a GST invoice, and up to 1M-token context — no international card, no rewrite.

OpenAI-compatible · ₹-native billing · GST invoice · 1M context

Available models

The DeepSeek family, in ₹

Three models, one key. Prices are per million tokens; the platform fee and GST are added at billing.

DeepSeek V4 Flash
deepseek-ai/deepseek-v4-flash
1M ctx

Input / 1M

₹9.07/M

Output / 1M

₹18.14/M

Text · reasoning · tools · 1M-token context. The cheapest way to run high-volume DeepSeek in India.

DeepSeek V4.1 Flash
deepseek-ai/deepseek-v4.1-flash
1M ctx

Input / 1M

₹20.15/M

Output / 1M

₹60.46/M

Text · reasoning · tools · 1M-token context. Stronger reasoning when V4 Flash isn't enough.

DeepSeek V3.2
deepseek-ai/deepseek-v3.2
164K ctx

Input / 1M

₹26.20/M

Output / 1M

₹38.29/M

Text · tools. The established V3.2 workhorse for general chat and extraction.

Indicative pricing — the live rate for each model, and the platform fee, is on its model page and in the pricing docs.

Why here

DeepSeek, on an Indian invoice

  • 1M-token context — V4 Flash and V4.1 Flash take up to a million tokens per request.
  • Reasoning built in — Thinking mode and tool calls, exposed through the standard API.
  • No rewrite — It is the OpenAI API — change the base URL and the model id.
  • ₹ GST invoice — Billed in rupees from an Indian entity, ITC where registered.
curl
curl https://api.unoblox.ai/v1/chat/completions \
  -H "Authorization: Bearer $UNOBLOX_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-ai/deepseek-v4-flash",
    "messages": [{ "role": "user", "content": "Extract the totals from this invoice." }]
  }'
Route smart

Mix DeepSeek with everything else

Send high-volume work to DeepSeek Flash and reserve frontier models for the hard requests — all under one key and one rupee bill.

FAQ

DeepSeek in India, answered

Which DeepSeek models are available in India?

DeepSeek V4 Flash and V4.1 Flash (up to 1M-token context, with reasoning and tools) and DeepSeek V3.2 — all through one OpenAI-compatible endpoint.

How much does DeepSeek cost in rupees?

DeepSeek V4 Flash is ₹9.07 per 1M input and ₹18.14 per 1M output; DeepSeek V4.1 Flash is ₹20.15 per 1M input and ₹60.46 per 1M output; DeepSeek V3.2 is ₹26.20 per 1M input and ₹38.29 per 1M output. These are indicative — live rates are on each model page.

When should I use V4 Flash vs V4.1 Flash?

Start on V4 Flash for the cheapest 1M-context calls. Move to V4.1 Flash when you need its stronger reasoning and can accept the higher rate.

Do I have to rewrite my app?

No. Point your OpenAI SDK at https://api.unoblox.ai/v1 and set the model to deepseek-ai/deepseek-v4-flash. Streaming, tool calls and JSON mode work unchanged.

How is this billed?

In rupees from a prepaid wallet, on a monthly GST invoice from an Indian entity, with input tax credit where you're GST-registered. No international card is required.

Where does DeepSeek inference run?

On DeepSeek's API infrastructure. unoblox provides the gateway, the Indian contract, ₹ billing and spend controls; assess DeepSeek's terms for any data-residency obligations your business carries.

Call DeepSeek in rupees

Create a key and run DeepSeek V4 through one OpenAI-compatible endpoint — priced in ₹, on a GST invoice.