# Input message

Represents a message input to the model with role-based instruction hierarchy.

## Properties

**`role`** string required

The role of the message input. One of `user`, `system`, or `assistant`.

**`texts`** array optional

Array of text content items.

details
summary
Show structure
Each text item:

**`text`** string required

The text content.

Example: `[{ "text": "Hello, how are you?" }]`

**`images`** array optional

Array of image inputs.

details
summary
Show structure
Each image item can have:

**`fileId`** string optional

Reference to an uploaded file.

**`url`** string optional

Direct image URL.

Example: `[{ "fileId": "file_abc123" }]` or `[{ "url": "https://example.com/image.jpg" }]`

**`audio`** array optional

Array of audio inputs.

details
summary
Show structure
Each audio item:

**`fileId`** string required

Reference to uploaded audio file.

Example: `[{ "fileId": "file_audio123" }]`

**`files`** array optional

Array of file attachments for context (PDFs, documents, etc.).

details
summary
Show structure
Each file item:

**`fileId`** string required

Reference to uploaded file.

Example: `[{ "fileId": "file_doc123" }]`

**`id`** string optional

The unique ID of the input message. Populated when items are returned via API.

## Usage

This object is used in:

- [Create a model response](/docs/api-reference/responses/create) - `inputs` parameter


## Examples

Text Only

```json
{
  "role": "user",
  "texts": [
    { "text": "Hello, how are you?" }
  ]
}
```

System Prompt

```json
{
  "role": "system",
  "texts": [
    { "text": "You are a helpful Python expert. Always include code examples." }
  ]
}
```

With Image URL

```json
{
  "role": "user",
  "texts": [
    { "text": "What is in this image?" }
  ],
  "images": [
    { "url": "https://example.com/image.jpg" }
  ]
}
```

With Uploaded Image

```json
{
  "role": "user",
  "texts": [
    { "text": "What's in this image?" }
  ],
  "images": [
    { "fileId": "file_abc123" }
  ]
}
```

Multi-modal

```json
{
  "role": "user",
  "texts": [
    { "text": "Analyze these documents" }
  ],
  "files": [
    { "fileId": "file_doc123" },
    { "fileId": "file_doc456" }
  ],
  "images": [
    { "fileId": "file_img789" }
  ]
}
```