> ## Documentation Index
> Fetch the complete documentation index at: https://docs.forii.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Introduction

> Forii — India's Sovereign Inference Platform. Run any frontier model on Indian infrastructure, independent of US providers. 30% lower cost, full data sovereignty.

<img src="https://mintcdn.com/forii-docs/cNsW6DAG7qkXCpMH/docs/banner.svg?fit=max&auto=format&n=cNsW6DAG7qkXCpMH&q=85&s=1046a9c3a8987de6df9bc2f9c6b08e43" width="1200" height="480" data-path="docs/banner.svg" />

## What is Forii?

Forii is India's Sovereign Inference Platform — run any frontier model on Indian infrastructure, independent of US cloud providers. Your data stays in India, your costs drop 30%, and you pay in rupees. DeepSeek-V3, LLaMA-4-Scout, Gemma-3, Qwen3 — all production-ready. Change two lines of code, deploy in minutes.

## Why Forii?

<CardGroup cols={3}>
  <Card title="30% Lower Cost" icon="chart-line">
    Continuous batching, INT4/AWQ quantization, and prompt caching compound to deliver frontier inference at 30% below self-deployment cost.
  </Card>

  <Card title="OpenAI-Compatible" icon="code">
    Swap `base_url` and `api_key` — that's it. Works with LangChain, LlamaIndex, Vercel AI SDK, and every OpenAI SDK out of the box.
  </Card>

  <Card title="Data Sovereignty" icon="globe">
    Indian data centers, Indian jurisdiction. No data routed through US servers, no US subpoenas, no CLOUD Act exposure. INR pricing.
  </Card>
</CardGroup>

## Core Capabilities

<CardGroup cols={3}>
  <Card title="Chat Completions" icon="message-square">
    Text generation with streaming, structured outputs, and function calling. The endpoint every framework calls first.
  </Card>

  <Card title="Embeddings" icon="search">
    Semantic search over Hindi and English documents. Power RAG pipelines with low-latency embeddings from Indian servers.
  </Card>

  <Card title="Frontier Models" icon="layers">
    DeepSeek-V3, LLaMA-4-Scout, Gemma-3, Qwen3, and forii/embed-v3. Curated, quantized, quality-verified before deployment.
  </Card>
</CardGroup>

## Who is this for?

* **Developers** building AI products for Indian users — chatbots, document processors, voice agents, RAG systems
* **Startups** paying in USD for inference routed through US data centers
* **Enterprises** that need data sovereignty — Indian jurisdiction, no US cloud dependency, INR pricing

## Make your first request

```python theme={null}
from openai import OpenAI

client = OpenAI(
    base_url="https://api.forii.in/inference/v1",
    api_key=os.environ["FORII_API_KEY"],
)

response = client.chat.completions.create(
    model="forii/deepseek-v3",
    messages=[{"role": "user", "content": "नमस्ते, कैसे हो?"}],
    max_tokens=512,
)

print(response.choices[0].message.content)
```

Follow the [Quick Start](/docs/quickstart) guide to get your API key and make your first request.