> ## Documentation Index
> Fetch the complete documentation index at: https://docs.gloo.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Completions V1

> Conversational Chat Completions

<Warning>
  **Deprecated**: The Completions V1 API has been deprecated in favor of Completions v2.

  **Key differences from V1:**

  * New endpoint: `/ai/v2/chat/completions`
  * Smart routing with `auto_routing: true`
  * Provider selection with `model_family`
  * Theology-aware responses with `tradition`

  [View V2 Guide](/api-guides/completions-v2) | [Migration Steps](/api-guides/completions-v2#migrating-from-completions-v1)
</Warning>

<Info>
  Tool calling is supported in both V1 and V2, but the [Tool Use Guide](/api-guides/tool-use) now focuses on V2. Please migrate to V2 for the latest tool calling features and examples.
</Info>

Standard chat completions—like OpenAI's `chat/completions` endpoint—are quickly becoming the industry default for building conversational AI. Whether you're developing a chatbot, virtual assistant, or AI-powered automation, here's why sticking with the standard just makes sense.

> The Gloo AI Completions API allows you to build with many of the leading open-source models and ensures that it has Human Flourishing alignment and guardrails for any use.

***

## Why Use Standard Chat Completions?

### Familiar Developer Experience

If you've used tools like OpenAI, Anthropic, or other LLM providers, you've likely already encountered the `chat` format: a sequence of messages between `system`, `user`, and `assistant`.

```json theme={null}
[
  { "role": "system", "content": "You are a helpful assistant." },
  { "role": "user", "content": "How do I reset my password?" }
]
```

This simple, message-based interface has become the **standard across APIs**, making it easier to build, test, and scale without needing to relearn a custom format for every provider.

### Plug-and-Play with Tools and SDKs

Standard chat completions are supported out-of-the-box by:

* **Popular SDKs** (OpenAI, LangChain, LlamaIndex, etc.)
* **Prompt engineering tools**
* **Debugging/observability dashboards**
* **Prompt versioning platforms**
* **Orchestration frameworks**

That means less boilerplate and more productivity.

### Easily Portable Across Models

Using a standard chat format lets you switch between:

* OpenAI GPT and o-series
* Anthropic Claude
* Google Gemini
* Open-source chat models like DeepSeek, LLaMA, or Mistral

...all without rewriting your app logic. Standardization lets you **benchmark models**, compare outputs, and even build model-agnostic fallbacks or ensembles.

### Better Alignment with Human Intent

The chat format encourages natural interaction flow, including:

* Clarification (multi-turn)
* Function/tool calling
* Role-based prompting (e.g. system as context setter)

It also makes features like **memory**, **tool use**, and **retrieval-augmented generation (RAG)** feel native, rather than bolted on.

### Built-In Support for Advanced Features

Using chat completions gives you access to:

* Function/tool calling
* JSON mode
* Temperature/top\_p control
* Streaming support
* Multi-turn context windows

These features are essential for reliable, context-aware, and real-time applications.

### Supported by the Ecosystem

From hosting providers to vector databases, the whole AI tooling ecosystem now expects the standard chat format. It’s the easiest way to stay compatible and future-proof your codebase.

***

## TL;DR: Why Use Standard Chat Completions?

| Benefit               | Description                                                                                               |
| --------------------- | --------------------------------------------------------------------------------------------------------- |
| **Familiar**          | Common API shape across many providers.                                                                   |
| **Pluggable**         | Compatible with SDKs and tools.                                                                           |
| **Portable**          | Easy to swap or compare models.                                                                           |
| **Powerful**          | Supports advanced features like tool calling.                                                             |
| **Ecosystem-Ready**   | Plays nicely with the AI stack.                                                                           |
| **Human Flourishing** | Build with AI and Human Flourishing capabilities at its core with the world's leading open source models. |

**Ready to build?** The chat format is your foundation for production-ready AI apps—backed by best practices, trusted by industry, and ready to scale.