# Core Concepts

## What You'll Learn

This section covers the fundamental concepts you need to know:

* [**Model Profiles**](/03-concepts/01-profiles.md) - How Halfred simplifies model selection with curated profiles
* [**Pricing & Credits**](/03-concepts/02-pricing.md) - How the prepaid credit system works
* [**Tokens Explained**](/03-concepts/03-tokens.md) - Understanding tokens, context limits, and usage measurement

## The Halfred Philosophy

Halfred was built on a simple principle: **developers shouldn't need to become AI experts to build AI-powered features**.

Instead of:

* Comparing dozens of models
* Managing multiple provider accounts
* Worrying about which model is best for each task
* Dealing with different APIs and billing systems

You get:

* **Profile-based selection** - Choose based on your needs (speed, cost, quality)
* **Automatic routing** - Halfred picks the best model behind the scenes
* **Unified interface** - One API for all providers
* **Transparent pricing** - Simple prepaid credit system

## Key Concepts at a Glance

### Model Profiles

Halfred organizes AI models into profiles based on use cases:

| Profile       | Best For                    | Price           |
| ------------- | --------------------------- | --------------- |
| **LITE**      | Simple tasks, UI assistants | $0.50/M tokens  |
| **STANDARD**  | Most production apps        | $2.50/M tokens  |
| **DEEPTHINK** | Complex reasoning, R\&D     | $12.50/M tokens |
| **DEV**       | Testing & development       | Free            |

*For the most up-to-date pricing, please refer to the* [*Profile Dashboard*](https://halfred.ai/app/project-profile) *(requires login).*

→ [Learn more about profiles](/03-concepts/01-profiles.md)

### Credits & Billing

* **Prepaid system**: Add credits before use
* **No surprises**: You can't spend more than your balance
* **Transparent costs**: Each request shows token usage and price
* **Flexible packages**: Buy credits as needed

→ [Learn more about pricing](/03-concepts/02-pricing.md)

### Tokens

* **What**: Small units of text that models process
* **Why it matters**: Billing is based on tokens
* **Context limits**: Each profile has a maximum token capacity
* **Optimization**: Shorter prompts = lower costs

→ [Learn more about tokens](/03-concepts/03-tokens.md)

## Design Principles

### 1. Simplicity First

Choose a profile, not a model. Halfred handles the complexity.

### 2. Transparent Pricing

Know exactly what you'll pay before making a request.

### 3. Multi-Provider Access

Access the best models from multiple providers through one API.

### 4. Developer Experience

Built by developers, for developers. Clean APIs, great docs, fast support.

## Next Steps

1. **Understand profiles**: Start with [Model Profiles](/03-concepts/01-profiles.md)
2. **Learn about costs**: Read [Pricing & Credits](/03-concepts/02-pricing.md)
3. **Optimize usage**: Explore [Tokens Explained](/03-concepts/03-tokens.md)
4. **Start building**: Go to [Quick Start Guide](/01-getting-started/01-quickstart.md)

## Questions?

* Check our [FAQ](https://halfred.ai/#faq)
* Email <support@halfred.ai>
* Join our [Discord community](https://discord.gg/wS2awX4EV7)


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.halfred.ai/03-concepts.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.