Quick Start

Get up and running with Forii. You’ll make your first inference request before the page finishes loading.

Step 1: Get your API key

Sign up at app.forii.in
Navigate to Dashboard → API Keys
Click Create New Key
Copy the key — it starts with forii_sk_ and is shown only once

Your free tier includes ₹50 in credits — enough for thousands of inference calls. No credit card needed to start.

Step 2: Install the SDK

Forii is OpenAI-compatible. Use the official OpenAI SDK — no Forii SDK needed.

Python
JavaScript
cURL

pip install openai

npm install openai

Step 3: Make your first request

Python
JavaScript
cURL

import os
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": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Explain quantum computing in simple terms"},
    ],
    temperature=0.7,
    max_tokens=512,
)

print(response.choices[0].message.content)
print(f"\nTokens: {response.usage.total_tokens}")

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.FORII_API_KEY,
  baseURL: "https://api.forii.in/inference/v1",
});

const response = await client.chat.completions.create({
  model: "forii/deepseek-v3",
  messages: [
    { role: "system", content: "You are a helpful assistant." },
    { role: "user", content: "Explain quantum computing in simple terms" },
  ],
  temperature: 0.7,
  max_tokens: 512,
});

console.log(response.choices[0].message.content);
console.log(`\nTokens: ${response.usage.total_tokens}`);

curl https://api.forii.in/inference/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $FORII_API_KEY" \
  -d '{
    "model": "forii/deepseek-v3",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "Explain quantum computing in simple terms"}
    ],
    "temperature": 0.7,
    "max_tokens": 512
  }'

Step 4: Stream a response

Python
JavaScript

stream = client.chat.completions.create(
    model="forii/deepseek-v3",
    messages=[{"role": "user", "content": "Tell me a story"}],
    stream=True,
)

for chunk in stream:
    if chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="")

const stream = await client.chat.completions.create({
  model: "forii/deepseek-v3",
  messages: [{ role: "user", content: "Tell me a story" }],
  stream: true,
});

for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content || "");
}

What’s next?

Chat Completions

Full reference for all completion modes — streaming, structured outputs, function calling.

Models

Browse available models, context windows, and pricing.

Pricing

INR pricing, credits system, and plans — frontier models at 30% lower cost.

Home

Concepts

API Reference

Dashboard

Observability

Support

Step 1: Get your API key

Step 2: Install the SDK

Step 3: Make your first request

Step 4: Stream a response

What’s next?

Chat Completions

Models

Pricing

​Step 1: Get your API key

​Step 2: Install the SDK

​Step 3: Make your first request

​Step 4: Stream a response

​What’s next?

Chat Completions

Models

Pricing

Step 1: Get your API key

Step 2: Install the SDK

Step 3: Make your first request

Step 4: Stream a response

What’s next?