> ## Documentation Index
> Fetch the complete documentation index at: https://chainlit-5-wd-prompt.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.
# Generation
The following objects can be passed to a [step](/concepts/step)
## ChatGeneration
```python
@dataclass
class ChatGeneration(BaseGeneration):
messages: List[GenerationMessage] = Field(default_factory=list)
type = GenerationType.CHAT
```
List of messages sent to the LLM. Following the openai chat format.
The provider of the LLM, like `openai`.
The model used for the generation, like `gpt-4`.
The error message if the generation failed.
The settings of the LLM, like `temperature`...
The variables used to format the prompt.
Optional tags to add to the generation.
The prompt used for the generation.
The tools used to generate the completion, following the openai format.
The message returned by the LLM, following the openai chat format.
The token count of the completion.
The token count of the input.
The token count of the output.
The time it took to generate the first token. Only available when streaming.
The token throughput in tokens per second. Only available when streaming.
The duration of the generation in ms.
## CompletionGeneration
The provider of the LLM, like `openai`.
The model used for the generation, like `gpt-4`.
The error message if the generation failed.
The settings of the LLM, like `temperature`...
The variables used to format the prompt.
Optional tags to add to the generation.
The prompt used for the generation.
The completion returned by the LLM.
The token count of the completion.
The token count of the input.
The token count of the output.
The time it took to generate the first token. Only available when streaming.
The token throughput in tokens per second. Only available when streaming.
The duration of the generation in ms.