# Chat Completions

**Sync Type: Incremental**

## Overview

The OpenAI Chat Completions input fetches stored chat completion records from the OpenAI API for monitoring model usage, token consumption, and content policy events. Only completions created with `store: true` are returned. This integration enables tracking of AI model utilization, cost analysis through token consumption metrics, and auditing of chat interactions across your OpenAI organization.

## Prerequisites

### 1. OpenAI Organization Access
- Active OpenAI organization account
- API key with access to the Chat Completions API

### 2. Stored Completions Enabled
Chat completions must be created with the `store: true` parameter to appear in the API response. Completions created without this flag will not be fetched by this connector. [Learn More](https://developers.openai.com/api/reference/resources/chat/subresources/completions/subresources/messages/methods/list#(resource)%20chat.completions.messages%20%3E%20(method)%20list)

## API Key Setup

1. **Access Settings**
   - From the OpenAI platform home page, click the **Settings** icon in the top-right corner.

2. **Navigate to API Keys**
   - In the left navigation panel, select **API Keys**.

3. **Create New Key**
   - Click the **Create new secret key** button.

4. **Configure Key Settings**
   - **Name:** Provide a descriptive name (e.g., "Monad Chat Completions").
   - **Permissions:** The key needs read access to the Chat Completions API.

5. **Save and Store Key**
   - Copy the generated API key immediately.
   - Store it securely - it cannot be retrieved later if lost.

## Configuration

### Settings

| Setting | Type | Required | Description |
|---------|------|----------|-------------|
| Model | string | No | Filter completions by model (e.g. gpt-4o). Leave empty to fetch all models. |
| API Rate Limit | object | No | Optional limit on the connector's outbound request rate to the source API. Leave blank to use the connector's default behavior. See [API Rate Limiting](../../../guides/rate-limiting) for the field format, limits, and how to choose a value. |

### Secrets

| Secret | Type | Required | Description |
|--------|------|----------|-------------|
| API Key | string | Yes | The API key generated from the OpenAI platform. |

## Related Articles

- [OpenAI Chat Completions API Reference](https://developers.openai.com/api/reference/resources/chat/subresources/completions/methods/list)
- [OpenAI Stored Completions](https://developers.openai.com/api/reference/chat-completions/overview)
- [OpenAI Platform](https://platform.openai.com/home)

## Sample Record

```json
{
  "object": "chat.completion",
  "id": "chatcmpl-e4174b5d-3aa2-c9f9-60c2-2bc7767f826b",
  "model": "gpt-5.4",
  "created": 1780074647,
  "request_id": "req_986cd465-b592-abbc-3607-15c437fbb008",
  "tool_choice": null,
  "usage": {
    "total_tokens": 609,
    "completion_tokens": 275,
    "prompt_tokens": 420
  },
  "seed": 2615205,
  "top_p": 1.0,
  "temperature": 1.0,
  "presence_penalty": 0.0,
  "frequency_penalty": 0.0,
  "system_fingerprint": "fp_87dc40bd-273f-1305-ab7f-efd7145c3b59",
  "input_user": null,
  "service_tier": "default",
  "tools": null,
  "metadata": {},
  "choices": [
    {
      "index": 0,
      "message": {
        "content": "Hello! How can I help you today?",
        "role": "assistant",
        "tool_calls": null,
        "function_call": null
      },
      "finish_reason": "stop",
      "logprobs": null
    }
  ],
  "response_format": null
}
```

## Sync frequency

By default this input polls approximately every 10 seconds, with each sync beginning after the previous one completes. A cron schedule configured on the pipeline overrides this cadence. See [Input Sync Frequency](../../guides/sync-frequency) for details.