# GPT 5.5 API

Complete API reference for GPT 5.5 LLM models powered by OpenAI.

## Model Variants

This API supports four model variants:

| Model | ID | Description |
|-------|----|-------------|
| **GPT 5.5 Text to Text** | `gpt-5.5-text-to-text` | General text reasoning and writing |
| **GPT 5.5 Image to Text** | `gpt-5.5-image-to-text` | Image understanding with text instructions |
| **GPT 5.5 Web Search** | `gpt-5.5-web-search` | Text LLM workflow with web-search capability |
| **GPT 5.5 File Analysis** | `gpt-5.5-file-analysis` | File analysis with text instructions |

## Quick Comparison

| Feature | Text to Text | Image to Text | Web Search | File Analysis |
|---------|--------------|---------------|------------|---------------|
| Text input | Required ✅ | Optional | Required ✅ | Optional |
| Image input | Not supported ❌ | Optional | Optional | Optional |
| File input | Not supported ❌ | Not supported ❌ | Optional | Optional |
| Streaming response | SSE | SSE | SSE | SSE |
| `max_tokens` | Optional | Optional | Optional | Optional |

## GPT 5.5 Text to Text

### Endpoint

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

### Request Parameters

#### Required

| Parameter | Type | Description |
|-----------|------|-------------|
| `model` | string | Must be `"gpt-5.5-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 | `> 1` | Maximum output 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: 'gpt-5.5-text-to-text',
    messages: [
      {
        role: 'user',
        content: 'Write a short launch announcement for a new AI feature.'
      }
    ],
    stream: true,
    max_tokens: 2048
  })
});
```

## GPT 5.5 Image to Text

### Endpoint

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

### Request Parameters

#### Required

| Parameter | Type | Description |
|-----------|------|-------------|
| `model` | string | Must be `"gpt-5.5-image-to-text"` |
| `messages` | array | Ordered messages. See LLM API and Message Attachments. |
| `stream` | boolean | `true` for SSE, `false` for a single JSON response. |

#### Message Support

| Field | Text | File | Image |
|-------|------|------|-------|
| `messages` | Optional | Not supported ❌ | Optional |

#### Optional

| Parameter | Type | Range | Description |
|-----------|------|-------|-------------|
| `max_tokens` | integer | `> 1` | Maximum output 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: 'gpt-5.5-image-to-text',
    messages: [
      {
        role: 'user',
        content: [
          { type: 'text', text: 'Describe the image and extract any visible text.' },
          {
            type: 'image_url',
            image_url: {
              url: 'https://example.com/sample-image.jpg'
            }
          }
        ]
      }
    ],
    stream: true,
    max_tokens: 2048
  })
});
```

## GPT 5.5 Web Search

### Endpoint

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

### Request Parameters

#### Required

| Parameter | Type | Description |
|-----------|------|-------------|
| `model` | string | Must be `"gpt-5.5-web-search"` |
| `messages` | array | Ordered messages. See LLM API and Message Attachments. |
| `stream` | boolean | `true` for SSE, `false` for a single JSON response. |

#### Message Support

| Field | Text | File | Image |
|-------|------|------|-------|
| `messages` | Required ✅ | Optional | Optional |

#### Optional

| Parameter | Type | Range | Description |
|-----------|------|-------|-------------|
| `max_tokens` | integer | `> 1` | Maximum output 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: 'gpt-5.5-web-search',
    messages: [
      {
        role: 'user',
        content: 'Find recent product launch trends in AI developer tools.'
      }
    ],
    stream: true,
    max_tokens: 2048
  })
});
```

## GPT 5.5 File Analysis

### Endpoint

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

### Request Parameters

#### Required

| Parameter | Type | Description |
|-----------|------|-------------|
| `model` | string | Must be `"gpt-5.5-file-analysis"` |
| `messages` | array | Ordered messages. See LLM API and Message Attachments. |
| `stream` | boolean | `true` for SSE, `false` for a single JSON response. |

#### Message Support

| Field | Text | File | Image |
|-------|------|------|-------|
| `messages` | Optional | Optional | Optional |

#### Optional

| Parameter | Type | Range | Description |
|-----------|------|-------|-------------|
| `max_tokens` | integer | `> 1` | Maximum output 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: 'gpt-5.5-file-analysis',
    messages: [
      {
        role: 'user',
        content: [
          { type: 'text', text: 'Summarize this document and list the key action items.' },
          {
            type: 'file',
            file: {
              filename: 'demo.pdf',
              file_data: 'https://example.com/demo.pdf'
            }
          }
        ]
      }
    ],
    stream: true,
    max_tokens: 2048
  })
});
```

## Response Format

GPT 5.5 LLM models return OpenAI-compatible completion responses. With `stream: true`, the response is Server-Sent Events; with `stream: false`, the response is a single JSON object.

### Successful Response

```text
data: {"id":"chatcmpl-...","object":"chat.completion.chunk","created":1710000000,"model":"gpt-5.5-image-to-text","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}

data: {"id":"chatcmpl-...","object":"chat.completion.chunk","created":1710000000,"model":"gpt-5.5-image-to-text","choices":[{"index":0,"delta":{"content":"The image shows"},"finish_reason":null}]}

data: {"id":"chatcmpl-...","object":"chat.completion.chunk","created":1710000000,"model":"gpt-5.5-image-to-text","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}

data: {"id":"chatcmpl-...","object":"chat.completion.chunk","created":1710000000,"model":"gpt-5.5-image-to-text","choices":[],"usage":{"prompt_tokens":12,"completion_tokens":8,"total_tokens":20}}

data: [DONE]
```

### Error Response

```text
event: error
data: {"error":{"message":"API requests too frequent, exceeding rate limit","type":"rate_limit_error","code":"1302","param":null}}
```

## Best Practices

1. **Keep messages structured:** Use `messages[]` for conversation history instead of flattening context into one prompt.
2. **Attach files and images to messages:** Put `image_url` and `file` parts inside the message that introduced them.
3. **Use SSE parsing:** Append `choices[0].delta.content` for incremental display and treat `data: [DONE]` as successful completion.
4. **Send only supported inputs:** Match text, image, and file parts to the selected model variant.
5. **Store request state locally:** Chunks include a completion `id`, but clients should still route chunks through the active request state.