# GLM 5.2 API

Complete API reference for GLM 5.2 LLM models powered by Z.ai.

## Model Variants

This API supports one model variant:

| Model | ID | Description |
|-------|----|-------------|
| **GLM 5.2 Text to Text** | `glm-5.2-text-to-text` | General text reasoning and writing |

## Quick Comparison

| Feature | Text to Text |
|---------|--------------|
| Text input | Required ✅ |
| Image input | Not supported ❌ |
| File input | Not supported ❌ |
| Streaming response | SSE |
| `max_tokens` | Optional |
| `top_p` | Optional |
| `top_k` | Optional |

## GLM 5.2 Text to Text

### Endpoint

```http
POST /api/v1/chat/completions
```

### Request Parameters

#### Required

| Parameter | Type | Description |
|-----------|------|-------------|
| `model` | string | Must be `"glm-5.2-text-to-text"` |
| `messages` | array | Ordered messages. See LLM API for the message structure. |
| `stream` | boolean | `true` for SSE, `false` for a single JSON response. |

#### Message Support

| Field | Text | File | Image |
|-------|------|------|-------|
| `messages` | Required ✅ | Not supported ❌ | Not supported ❌ |

#### Optional

| Parameter | Type | Range | Description |
|-----------|------|-------|-------------|
| `max_tokens` | integer | `> 0` | Maximum output tokens. |
| `top_p` | number | `0.0` - `1.0` | Limits cumulative probability mass for candidate tokens. |
| `top_k` | integer | `0` - `100` | Limits the number of candidate tokens. |

### Example Request

```javascript
const response = await fetch('https://api.flaq.ai/api/v1/chat/completions', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer YOUR_API_KEY',
    'Accept': 'text/event-stream',
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    model: 'glm-5.2-text-to-text',
    messages: [
      {
        role: 'user',
        content: 'Write a four-line modern poem about a programmer drinking coffee.'
      }
    ],
    stream: true,
    max_tokens: 500,
    top_p: 0.5,
    top_k: 1
  })
});
```

## Response Format

GLM 5.2 returns OpenAI-compatible completion responses. With `stream: true`, the response is Server-Sent Events; with `stream: false`, the response is a single JSON object.

## Best Practices

- GLM 5.2 currently supports text-only input through this route.
- Use `top_p` and `top_k` together when you need tighter control over output diversity.
- Keep prompts structured when generating long-form content or code.