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

# File attachment support across models

export const plans_0 = "Any"

export const deployments_0 = "Any"

export const data_plane_version_0 = undefined

export const use_case_0 = undefined

<Note>
  **Applies to:**

  * Plan - {plans_0}
  * Deployment - {deployments_0}
  * {data_plane_version_0}
  * {use_case_0}
</Note>

## Summary

Attach files (PDFs, images, text files, etc.) to prompts in the playground. Support depends on the model and provider API.

## Model Compatibility

File attachments are supported by:

* **OpenAI Chat Completions API models:** Models using the Chat Completions API generally support file attachments
* **OpenAI Responses API models:** Standard/larger Responses API models (some mini/nano variants may not support file attachments)
* **Anthropic models:** Claude models generally support file attachments
* **Google models:** Gemini models generally support file attachments

## Configuration Steps

### Step 1: Select a Compatible Model

Select a compatible model in the playground.

### Step 2: Add File Attachment

Add a user message, then click "+ Message Part" → "File".

### Step 3: Upload Your File

Upload your file using the paperclip icon or paste a file URL.

## Notes

* The "File" option appears for all models where file inputs are supported - if a model doesn't support file inputs then this option will not show up for the model