---
title: Chat Completions | Lightcone
description: OpenAI-compatible text generation with tool calling and streaming.
---

The Chat Completions API is fully OpenAI-compatible. If you’re already using the OpenAI SDK or any OpenAI-compatible client, you can point it at Lightcone with minimal changes.

This API is separate from Lightcone’s browser automation features. Use it for text generation, chatbots, and tool-calling workflows. For browser-related AI tasks, see [Agent Tasks](/guides/agent-tasks/index.md) or the [Responses API](/guides/responses-api/index.md).

## Basic usage

```
from tzafon import Lightcone


client = Lightcone()


result = client.chat.create_completion(
    model="tzafon.sm-1",
    messages=[
        {"role": "user", "content": "What is the capital of France?"},
    ],
)
print(result)
```

```
import Lightcone from "@tzafon/lightcone";


const client = new Lightcone();


const result = await client.chat.createCompletion({
  model: "tzafon.sm-1",
  messages: [
    { role: "user", content: "What is the capital of France?" },
  ],
});
console.log(result);
```

## Streaming

Set `stream: true` to receive tokens as they’re generated:

```
result = client.chat.create_completion(
    model="tzafon.sm-1",
    messages=[
        {"role": "user", "content": "Write a haiku about programming"},
    ],
    stream=True,
)
```

```
const result = await client.chat.createCompletion({
  model: "tzafon.sm-1",
  messages: [
    { role: "user", content: "Write a haiku about programming" },
  ],
  stream: true,
});
```

## Tool calling

Define functions the model can call:

```
result = client.chat.create_completion(
    model="tzafon.sm-1",
    messages=[
        {"role": "user", "content": "What's the weather in San Francisco?"},
    ],
    tools=[
        {
            "type": "function",
            "function": {
                "name": "get_weather",
                "description": "Get the current weather for a location",
                "parameters": {
                    "type": "object",
                    "properties": {
                        "location": {"type": "string", "description": "City name"},
                    },
                    "required": ["location"],
                },
            },
        },
    ],
)
```

```
const result = await client.chat.createCompletion({
  model: "tzafon.sm-1",
  messages: [
    { role: "user", content: "What's the weather in San Francisco?" },
  ],
  tools: [
    {
      type: "function",
      function: {
        name: "get_weather",
        description: "Get the current weather for a location",
        parameters: {
          type: "object",
          properties: {
            location: { type: "string", description: "City name" },
          },
          required: ["location"],
        },
      },
    },
  ],
});
```

## Available models

| Model                       | Description                       | Input          | Output         |
| --------------------------- | --------------------------------- | -------------- | -------------- |
| `tzafon.sm-1`               | Small, fast general-purpose model | $0.20/M tokens | $0.30/M tokens |
| `tzafon.northstar-cua-fast` | Optimized for computer-use tasks  | $0.30/M tokens | $0.50/M tokens |

List models programmatically:

```
models = client.models.list()
print(models)
```

```
const models = await client.models.list();
console.log(models);
```

## Key parameters

| Parameter               | Description                                            |
| ----------------------- | ------------------------------------------------------ |
| `model`                 | Model to use                                           |
| `messages`              | Conversation history                                   |
| `temperature`           | Randomness (0 = deterministic, higher = more creative) |
| `max_completion_tokens` | Maximum tokens to generate                             |
| `stream`                | Enable streaming responses                             |
| `tools`                 | Function definitions for tool calling                  |
| `tool_choice`           | `"auto"`, `"none"`, or `"required"`                    |
| `response_format`       | Force `"json_object"` or JSON schema output            |

## Using with OpenAI SDK

Since the API is OpenAI-compatible, you can use the OpenAI SDK directly:

```
from openai import OpenAI


client = OpenAI(
    api_key="sk_your_tzafon_key",
    base_url="https://api.tzafon.ai",
)


response = client.chat.completions.create(
    model="tzafon.sm-1",
    messages=[{"role": "user", "content": "Hello!"}],
)
```

```
import OpenAI from "openai";


const client = new OpenAI({
  apiKey: "sk_your_tzafon_key",
  baseURL: "https://api.tzafon.ai",
});


const response = await client.chat.completions.create({
  model: "tzafon.sm-1",
  messages: [{ role: "user", content: "Hello!" }],
});
```

## See also

- [**Responses API**](/guides/responses-api/index.md) — computer-use agent interface (also OpenAI-compatible)
- [**Agent Tasks**](/guides/agent-tasks/index.md) — autonomous agents for browser tasks
- [**How Lightcone works**](/guides/how-lightcone-works/index.md) — how Chat Completions fits into the platform