# Output Targets

Promptfire supports multiple output targets so you can tailor context for different LLMs.

## Built-in Targets

| Target | Tokens | Format | Strategy |
|--------|--------|--------|----------|
| **Promptfire** | 200,000 | XML | Summarize headers |
| **GPT-4o** | 128,000 | Markdown | Summarize headers |
| **Compact** | 8,000 | Plain | Drop sections |

## Configuration

Each target can be configured with:

- **Name** - Display name (e.g., "Claude", "GPT-4")
- **Max tokens** - Token limit for truncation
- **Format** - `markdown`, `xml`, or `plain`
- **Strategy** - `summarize-headers`, `drop-sections`, `truncate`
- **Wrapper** - Prefix/suffix text around content (e.g., `<context>...</context>`)

## Primary vs Secondary Targets

- **Primary target** output goes to your clipboard.
- **Secondary targets** are saved as files in the configured output folder.

This lets you generate context for multiple LLMs in a single action.

## Output Folder

Configure where secondary target files are saved in **Settings > Promptfire > Output Targets**.