# Create new chat

### API Documentation: Create Chat Completion

#### Endpoint

```
POST /v1/chat/completions
```

#### Description

This endpoint creates a chat completion based on a conversation between the user and the AI model.

#### Request

**cURL Example:**

```
curl --location 'https://api.1for.ai/v1/chat/completions' \
--header 'Content-Type: application/json' \
--header 'api-key: {API_KEY}' \
--data '{
  "model": "auto",
  "messages": [
    {"role": "user", "content": "How are you doing today?"}
  ]
}'
```

Replace `{API_KEY}` with your actual API key.

**Request Body:**

* `model`: (string) Model name to use. Use `"auto"` for automatic selection. or choose from [here](https://1for-ai.gitbook.io/docs/model/retrieve-model-list)
* `messages`: (array) A list of message objects with:
  * `role`: (string) "user" or "system".
  * `content`: (string) The text content of the message.

#### Response

The response will be a JSON object containing the AI's reply and metadata:

```
{
    "text": String,
    "cost": Double,
    "role": "system",
    "chat_id": String,
    "model": String
}
```

* `text`: The generated text response.
* `cost`: The amount charged for this interaction.
* `role`: The role from which the response originates (typically "system").
* `chat_id`: A unique identifier for the conversation session. can be user later to continue conversation for that topic.
* `model`: The name of the model used to generate the completion.

#### Notes

* Ensure you send valid JSON in your request body.
* Costs depend on model usage and token counts.
* Using `"model": "auto"` allows automatic selection based on request text you send.