API Documentation

Access AI models using the OpenRouter and OpenAI APIs

What is iTtech?

iTtech is a Bangladesh-based platform that provides AI API access through OpenRouter and OpenAI.

With OpenRouter you can use Claude, GPT, Gemini, Grok and 400+ AI models through a single API. With OpenAI you can use GPT, image, speech and embedding models directly. Buy credits from Bangladesh with bKash or Nagad — no international payment method required.

OpenRouter Documentation

400+ models, endpoints, streaming, error codes

OpenRouter Docs

OpenAI Documentation

Chat, images, audio, embeddings

OpenAI Docs

OpenRouter or OpenAI — which one, when?

A quick comparison:

OpenRouter Pay-as-you-go

400+ models in one place (GPT, Claude, Gemini, Llama, DeepSeek)
Exact charge per request — fully transparent cost
Ideal if you want to compare multiple providers
Switch models with a single line change

OpenAI Direct Project credit

Only OpenAI's own models (GPT, image, Sora, embeddings)
Direct credit — OpenAI's official pricing
Images, audio, embeddings — all with the same key
Simpler if you only use the OpenAI stack

Quickstart

Get your first API response in under 5 minutes.

Create an account

Add balance

Topup via bKash/Nagad. Admin verification activates your balance.

Generate an API key

Create your API key from the dashboard and copy it somewhere safe.

Send your first request

Copy the cURL example below and run it in your terminal.

curl https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-4.1-mini",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

You're all set!

Explore the code examples and use-case tutorials below to build more.

Code Examples

Ready-to-use snippets in your favorite language or tool.

curl https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-4.1-mini",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Works directly from any terminal — great for quick testing.

Use-case Tutorials

Practical, copy-paste examples for common projects.

Build a mini chatbot

Keep a messages array, push each user message, send the whole array to /chat/completions and append the assistant reply. Use a cheap model like openai/gpt-4.1-mini.

Generate images

Pick an image model (e.g. google/gemini-2.5-flash-image) from the Models page, send a prompt in messages and read the image from the response.

Automate an email reply with n8n

Gmail Trigger → HTTP Request (chat/completions with the email body) → Gmail Reply node using the model's answer.

Troubleshooting FAQ

Common issues and how to fix them.

❌ Getting "401 Unauthorized" / "Invalid API key"

Check that the header is exactly 'Authorization: Bearer YOUR_KEY' with no extra spaces, and that the key is not revoked.

💳 "402 Insufficient Credits" — what should I do?

Your balance is empty. Top up via bKash/Nagad and wait for admin verification.

🤔 Which model should I pick? (cheap vs premium)

Start with a mini/flash model for everyday tasks. Use Claude or GPT premium models only for hard reasoning or coding.

⏱️ Requests are slow or timing out

Use streaming (stream: true), lower max_tokens, or switch to a faster model.