GPT-4o API in India

GPT-4o is OpenAI's multimodal workhorse — strong at vision, reasoning, and real-time interaction. On unoblox it's priced at ₹252 per million input tokens and ₹1008 per million output tokens, billed monthly in rupees with a GST invoice.

Why GPT-4o

GPT-4o handles text and images in the same request, supports tool-calling and JSON mode, and has a 128K-token context window — enough for long documents, multi-turn conversations, or a sizable RAG context in a single call.

GPT-4o pricing and capabilities

Feature	Value
Input cost	₹252 per 1M tokens
Output cost	₹1008 per 1M tokens
Vision	Native, no extra per-image fee
Context window	128K tokens
Platform uptime	99.95% SLA on unoblox

When to use GPT-4o

• Web apps — streaming, multimodal responses for real-time chat UIs.
• Document processing — pull text, tables, and metadata out of images and PDFs.
• Vision tasks — read screenshots, charts, diagrams, and photos.
• API backends — tool-calling and strong general reasoning for automation.

Integration in two minutes

1. Create an account → https://unoblox.ai/sign-in.
2. Copy your API key → from the "API Keys" section.
3. Update your base URL → https://api.unoblox.ai/v1, model openai/gpt-4o.

const OpenAI = require('openai');
const client = new OpenAI({
    apiKey: process.env.UNOBLOX_KEY,
    baseURL: 'https://api.unoblox.ai/v1',
});
const response = await client.chat.completions.create({
    model: 'openai/gpt-4o',
    messages: [
        {
            role: 'user',
            content: [
                { type: 'text', text: 'Describe this image' },
                { type: 'image_url', image_url: { url: 'https://...' } },
            ],
        },
    ],
});

Production advantages

• Fixed rupee pricing — the rate you see is the rate you pay, today and next month.
• GST invoice — automatic monthly billing with input-tax credit eligibility.
• Instant scaling — no quota approvals; pay for what you use as you grow.
• One key, full catalog — LangChain, Vercel AI SDK, or custom code all work unchanged.

Frequently asked questions

Can GPT-4o replace GPT-4 Turbo entirely? For most teams, yes — it's generally faster and cheaper while matching or beating Turbo on quality for everyday tasks.

What image formats does GPT-4o support? JPEG, PNG, GIF, and WebP, with multiple images allowed in a single request.

Is there a limit on images per request? No fixed limit — response time scales with the number and resolution of images you send.

Can I use function calling with GPT-4o? Yes — full support for OpenAI's tool-calling format, which makes it a solid fit for agentic workflows.

What would a typical document-analysis request cost? For roughly 500 input tokens (an image plus a short query) and 200 output tokens: (500 ÷ 1,000,000 × ₹252) + (200 ÷ 1,000,000 × ₹1008) ≈ ₹0.13 + ₹0.20 = about ₹0.33 per request. Your dashboard shows the exact per-request cost in real time.

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