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

# Chat completions

> Call /chat/completions with the C# SDK.

**Method**: `client.GenerateText(...)` or `client.CreateChatCompletion(...)`

### Example

```csharp theme={null}
using AiStatsSdk;

var client = new AIStats(apiKey);
var response = await client.GenerateText(new Dictionary<string, object>
{
    ["model"] = "openai/gpt-5-nano",
    ["messages"] = new[]
    {
        new Dictionary<string, object>
        {
            ["role"] = "user",
            ["content"] = "Write a limerick about lighthouses."
        }
    }
});
```

### Key parameters

* `model` (required): Target model id.
* `messages` (required): Ordered messages with roles `system|user|assistant|tool`; content as strings or parts.
* Sampling: `temperature` (0–2), `top_p` (0–1), `top_k` (>=1), `seed` (int, optional).
* Length/penalties: `max_output_tokens` (int), `presence_penalty` and `frequency_penalty` (-2 to 2), `stop` (string|string\[]).
* Tools: `tools` (definitions), `tool_choice` (auto/none/specific tool), `max_tool_calls` (int), `parallel_tool_calls` (bool).
* Logprobs: `logprobs` (bool), `top_logprobs` (0–20).
* Output: `response_format` (json/text), `meta` (object passthrough), `stream` (bool), `service_tier`.
* Gateway extras: `usage` (bool to request usage), `meta` (bool to include meta block).

### Returns

`ChatCompletionsResponse`

```json theme={null}
{
  "id": "chatcmpl-123",
  "object": "chat.completion",
  "created": 1677652288,
  "model": "gpt-3.5-turbo-0125",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello there, how may I assist you today?"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 9,
    "completion_tokens": 12,
    "total_tokens": 21
  }
}
```