Quickstart
Start making requests to any supported AI model in minutes.
Prerequisites
- Node.js 18 or later (or equivalent environment for Python/etc)
- An InferHood account
- An InferHood API Key (generate one in your dashboard)
Step 1: Install the SDK
The official @inferhood/sdk package is the quickest way in - no base URL to configure.
bash
npm install @inferhood/sdkInferHood is also fully OpenAI-compatible, so the official OpenAI SDK works if you would rather keep an existing client. See SDKs for that setup.
Step 2: Make your first request
Create a client with your API key and specify the model you want to use.
typescript
import { InferHood } from '@inferhood/sdk';
const client = new InferHood({
apiKey: process.env.INFERHOOD_API_KEY!,
});
const response = await client.chat.completions.create({
model: 'anthropic/claude-sonnet-4',
messages: [
{ role: 'user', content: 'What is InferHood?' }
],
});
console.log(response.choices[0].message.content);Step 3: Try the Playground
Want to test models without writing code? Visit the Playground to experiment with different models, system prompts, and parameters.