> ## Documentation Index
> Fetch the complete documentation index at: https://pythonaisdk.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Data types

> Pydantic models used by the SDK – message hierarchy, token usage, tool calls and more.

All public result objects & helper parameters rely on a small set of **immutable** Pydantic models defined in `ai_sdk.types`.

***

## Messages

### CoreMessage subclasses

| Class                  | Role        | Typical usage                                              |
| ---------------------- | ----------- | ---------------------------------------------------------- |
| `CoreSystemMessage`    | `system`    | Set behaviour & identity of the assistant.                 |
| `CoreUserMessage`      | `user`      | Explicit user instructions (text / images / files).        |
| `CoreAssistantMessage` | `assistant` | Model responses (text, reasoning, tool calls).             |
| `CoreToolMessage`      | `tool`      | Container for tool <em>results</em> fed back to the model. |

Each subclass exposes a `.to_dict()` helper that returns the OpenAI-compatible representation, so you can seamlessly drop them into the low-level `LanguageModel` interface if needed.

### Content parts

```python parts_breakdown.py lines icon="python" theme={null}
from ai_sdk.types import TextPart, ImagePart, ToolCallPart, ToolResultPart
```

Parts make multimodal messages explicit. For example a user message containing both text <em>and</em> an image:

```python theme={null}
CoreUserMessage(
content=[
  TextPart(text="Describe this painting"),
  ImagePart(image="https://example.com/monet.jpg", mime_type="image/jpeg"),
]
)
```

***

## TokenUsage

Simple container holding `prompt_tokens`, `completion_tokens`, `total_tokens` – populated on all helpers when the provider returns usage data.

## ToolCall / ToolResult

Used internally for the tool-calling loop but exposed on `GenerateTextResult` so you can inspect or persist the chain-of-thought.

## OnStepFinishResult

Object passed to the optional `on_step` callback after <strong>every</strong> model ↔ tool interaction. Fields include:

* `step_type` – one of `initial`, `continue`, `tool-result`.
* `finish_reason`, `usage`, `text`, `tool_calls`, `tool_results`, …

***

<Tip>
  All types are **frozen** (`pydantic.ConfigDict(frozen=True)`) meaning you can safely log & share
  them without accidental mutation.
</Tip>