# Chat

## Create chat completion

## Create chat completion

<mark style="color:green;">`POST`</mark> `https://api.forefront.ai/v1/chat/completions`

Creates a model response for the given chat conversation.

#### Request Body

| Name                                       | Type    | Description |
| ------------------------------------------ | ------- | ----------- |
| model<mark style="color:red;">\*</mark>    | string  |             |
| messages<mark style="color:red;">\*</mark> | array   |             |
| max\_tokens                                | integer |             |
| temeperature                               | number  |             |
| stop                                       | array   |             |

{% tabs %}
{% tab title="200: OK Successfully returned the chat completion." %}

```typescript
{
  "choices": [
    {
      "message": {
        "role": "assistant",
        "content": "Of course! I'm here to help."
      }
    }
  ],
  "usage": {
    "input_tokens": 28,
    "output_tokens": 10,
    "total_tokens": 38
  },
  "message": {
    "content": "Of course! I'm here to help."
  }
}
```

{% endtab %}
{% endtabs %}

### Example request

{% tabs %}
{% tab title="Python" %}

```python
from forefront import ForefrontClient

ff = ForefrontClient(api_key="YOUR_API_KEY")

completion = ff.chat.completions.create(
    messages=[
        {"role": "system", "content" "You are a gourmet chef"},
        {"role": "user", "content": "Write a recipe for an italian dinner"},
    ],
    model="MODEL_STRING", # replace with the name of the model 
    temperature=0,
    max_tokens=10,
)
```

{% endtab %}

{% tab title="Node.js" %}

```typescript
import Forefront from "forefront";

const client = new Forefront("YOUR_API_KEY");

const completion = await client.chat.completions.create({
  model: "MODEL_STRING",
  messages: [
    {
      role: "user",
      content: "Write a recipe for an italian dinner",
    },
  ],
  max_tokens: 256,
  stream: false,
});
```

{% endtab %}

{% tab title="cURL" %}

```
curl https://api.forefront.ai/v1/chat/completions \
--header 'content-type: application/json' \
--header 'authorization: Bearer $FOREFRONT_API_KEY' \
--data '{
    "model": "REPLACE_WITH_MODEL_STRING",
    "messages": [
       {
          "role": "user", 
          "content": "Write a recipe for an italian dinner"
       }
    ],
    "temperature": 0.1,
    "max_tokens": 128,
}'
```

{% endtab %}
{% endtabs %}


---

# 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.forefront.ai/api-reference/chat.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.