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

# Files

> Upload and manage files with Anthropic through Portkey

Portkey supports Anthropic's [Files API](https://docs.anthropic.com/en/docs/build-with-claude/files) (beta), enabling you to upload, list, retrieve, and delete files through the gateway. Uploaded files can be referenced in chat completions using `file_id` instead of re-uploading content each request.

<Note>
  The Files API is in beta and requires the `files-api-2025-04-14` beta header. Portkey sets this automatically for file endpoints when using the SDK. For cURL requests, include the `anthropic-beta: files-api-2025-04-14` header.
</Note>

## Upload a file

<Tabs>
  <Tab title="Python">
    ```python theme={"system"}
    from portkey_ai import Portkey

    portkey = Portkey(
        api_key="PORTKEY_API_KEY",
        provider="@anthropic"
    )

    file = portkey.files.create(
        purpose="assistants",
        file=open("document.pdf", "rb")
    )

    print(file.id)
    ```
  </Tab>

  <Tab title="NodeJS">
    ```js theme={"system"}
    import Portkey from 'portkey-ai';
    import fs from 'fs';

    const portkey = new Portkey({
        apiKey: "PORTKEY_API_KEY",
        provider: "@anthropic"
    });

    const file = await portkey.files.create({
        purpose: "assistants",
        file: fs.createReadStream("document.pdf")
    });

    console.log(file.id);
    ```
  </Tab>

  <Tab title="REST">
    ```sh theme={"system"}
    curl -X POST https://api.portkey.ai/v1/files \
      -H "x-portkey-api-key: $PORTKEY_API_KEY" \
      -H "x-portkey-provider: @anthropic" \
      -H "anthropic-beta: files-api-2025-04-14" \
      -F 'file=@"document.pdf"'
    ```
  </Tab>

  <Tab title="OpenAI Python">
    ```python theme={"system"}
    from openai import OpenAI
    from portkey_ai import PORTKEY_GATEWAY_URL, createHeaders

    client = OpenAI(
        api_key="PORTKEY_API_KEY",
        base_url=PORTKEY_GATEWAY_URL,
        default_headers=createHeaders(
            provider="@anthropic",
            api_key="PORTKEY_API_KEY"
        )
    )

    file = client.files.create(
        purpose="assistants",
        file=open("document.pdf", "rb")
    )

    print(file.id)
    ```
  </Tab>

  <Tab title="OpenAI NodeJS">
    ```js theme={"system"}
    import OpenAI from 'openai';
    import { PORTKEY_GATEWAY_URL, createHeaders } from 'portkey-ai';
    import fs from 'fs';

    const client = new OpenAI({
        apiKey: "PORTKEY_API_KEY",
        baseURL: PORTKEY_GATEWAY_URL,
        defaultHeaders: createHeaders({
            provider: "@anthropic",
            apiKey: "PORTKEY_API_KEY"
        })
    });

    const file = await client.files.create({
        purpose: "assistants",
        file: fs.createReadStream("document.pdf")
    });

    console.log(file.id);
    ```
  </Tab>
</Tabs>

## Use uploaded files in chat completions

Once a file is uploaded, reference it by `file_id` in your chat completions requests:

<Tabs>
  <Tab title="Python">
    ```python theme={"system"}
    from portkey_ai import Portkey

    portkey = Portkey(api_key="PORTKEY_API_KEY")

    response = portkey.chat.completions.create(
        model="@anthropic/claude-sonnet-4-5-20250929",
        max_tokens=1024,
        messages=[{
            "role": "user",
            "content": [
                {"type": "text", "text": "Please summarize this document."},
                {"type": "file", "file": {"file_id": "<file_id>", "mime_type": "application/pdf"}}
            ]
        }]
    )

    print(response.choices[0].message.content)
    ```
  </Tab>

  <Tab title="NodeJS">
    ```js theme={"system"}
    import Portkey from 'portkey-ai';

    const portkey = new Portkey({
        apiKey: "PORTKEY_API_KEY"
    });

    const response = await portkey.chat.completions.create({
        model: "@anthropic/claude-sonnet-4-5-20250929",
        max_tokens: 1024,
        messages: [{
            role: "user",
            content: [
                { type: "text", text: "Please summarize this document." },
                { type: "file", file: { file_id: "<file_id>", mime_type: "application/pdf" } }
            ]
        }]
    });

    console.log(response.choices[0].message.content);
    ```
  </Tab>

  <Tab title="REST">
    ```sh theme={"system"}
    curl -X POST https://api.portkey.ai/v1/chat/completions \
      -H "x-portkey-api-key: $PORTKEY_API_KEY" \
      -H "anthropic-beta: files-api-2025-04-14" \
      -H "Content-Type: application/json" \
      -d '{
        "model": "@anthropic/claude-sonnet-4-5-20250929",
        "max_tokens": 1024,
        "messages": [
          {
            "role": "user",
            "content": [
              {
                "type": "text",
                "text": "Please summarize this document."
              },
              {
                "type": "file",
                "file": {
                  "file_id": "<file_id>",
                  "mime_type": "application/pdf"
                }
              }
            ]
          }
        ]
      }'
    ```
  </Tab>
</Tabs>

<Note>
  When using the SDK, the `anthropic-beta` header is set automatically for file endpoints. For chat completions with file references via cURL, include `anthropic-beta: files-api-2025-04-14` in your request headers.
</Note>

## List files

<Tabs>
  <Tab title="Python">
    ```python theme={"system"}
    from portkey_ai import Portkey

    portkey = Portkey(
        api_key="PORTKEY_API_KEY",
        provider="@anthropic"
    )

    files = portkey.files.list()

    print(files)
    ```
  </Tab>

  <Tab title="NodeJS">
    ```js theme={"system"}
    import Portkey from 'portkey-ai';

    const portkey = new Portkey({
        apiKey: "PORTKEY_API_KEY",
        provider: "@anthropic"
    });

    const files = await portkey.files.list();

    console.log(files);
    ```
  </Tab>

  <Tab title="REST">
    ```sh theme={"system"}
    curl https://api.portkey.ai/v1/files \
      -H "x-portkey-api-key: $PORTKEY_API_KEY" \
      -H "x-portkey-provider: @anthropic" \
      -H "anthropic-beta: files-api-2025-04-14"
    ```
  </Tab>

  <Tab title="OpenAI Python">
    ```python theme={"system"}
    from openai import OpenAI
    from portkey_ai import PORTKEY_GATEWAY_URL, createHeaders

    client = OpenAI(
        api_key="PORTKEY_API_KEY",
        base_url=PORTKEY_GATEWAY_URL,
        default_headers=createHeaders(
            provider="@anthropic",
            api_key="PORTKEY_API_KEY"
        )
    )

    files = client.files.list()

    print(files)
    ```
  </Tab>

  <Tab title="OpenAI NodeJS">
    ```js theme={"system"}
    import OpenAI from 'openai';
    import { PORTKEY_GATEWAY_URL, createHeaders } from 'portkey-ai';

    const client = new OpenAI({
        apiKey: "PORTKEY_API_KEY",
        baseURL: PORTKEY_GATEWAY_URL,
        defaultHeaders: createHeaders({
            provider: "@anthropic",
            apiKey: "PORTKEY_API_KEY"
        })
    });

    const files = await client.files.list();

    console.log(files);
    ```
  </Tab>
</Tabs>

## Get file

<Tabs>
  <Tab title="Python">
    ```python theme={"system"}
    from portkey_ai import Portkey

    portkey = Portkey(
        api_key="PORTKEY_API_KEY",
        provider="@anthropic"
    )

    file = portkey.files.retrieve(file_id="<file_id>")

    print(file)
    ```
  </Tab>

  <Tab title="NodeJS">
    ```js theme={"system"}
    import Portkey from 'portkey-ai';

    const portkey = new Portkey({
        apiKey: "PORTKEY_API_KEY",
        provider: "@anthropic"
    });

    const file = await portkey.files.retrieve("<file_id>");

    console.log(file);
    ```
  </Tab>

  <Tab title="REST">
    ```sh theme={"system"}
    curl https://api.portkey.ai/v1/files/<file_id> \
      -H "x-portkey-api-key: $PORTKEY_API_KEY" \
      -H "x-portkey-provider: @anthropic" \
      -H "anthropic-beta: files-api-2025-04-14"
    ```
  </Tab>

  <Tab title="OpenAI Python">
    ```python theme={"system"}
    from openai import OpenAI
    from portkey_ai import PORTKEY_GATEWAY_URL, createHeaders

    client = OpenAI(
        api_key="PORTKEY_API_KEY",
        base_url=PORTKEY_GATEWAY_URL,
        default_headers=createHeaders(
            provider="@anthropic",
            api_key="PORTKEY_API_KEY"
        )
    )

    file = client.files.retrieve("<file_id>")

    print(file)
    ```
  </Tab>

  <Tab title="OpenAI NodeJS">
    ```js theme={"system"}
    import OpenAI from 'openai';
    import { PORTKEY_GATEWAY_URL, createHeaders } from 'portkey-ai';

    const client = new OpenAI({
        apiKey: "PORTKEY_API_KEY",
        baseURL: PORTKEY_GATEWAY_URL,
        defaultHeaders: createHeaders({
            provider: "@anthropic",
            apiKey: "PORTKEY_API_KEY"
        })
    });

    const file = await client.files.retrieve("<file_id>");

    console.log(file);
    ```
  </Tab>
</Tabs>

## Delete file

<Tabs>
  <Tab title="Python">
    ```python theme={"system"}
    from portkey_ai import Portkey

    portkey = Portkey(
        api_key="PORTKEY_API_KEY",
        provider="@anthropic"
    )

    response = portkey.files.delete(file_id="<file_id>")

    print(response)
    ```
  </Tab>

  <Tab title="NodeJS">
    ```js theme={"system"}
    import Portkey from 'portkey-ai';

    const portkey = new Portkey({
        apiKey: "PORTKEY_API_KEY",
        provider: "@anthropic"
    });

    const response = await portkey.files.delete("<file_id>");

    console.log(response);
    ```
  </Tab>

  <Tab title="REST">
    ```sh theme={"system"}
    curl -X DELETE https://api.portkey.ai/v1/files/<file_id> \
      -H "x-portkey-api-key: $PORTKEY_API_KEY" \
      -H "x-portkey-provider: @anthropic" \
      -H "anthropic-beta: files-api-2025-04-14"
    ```
  </Tab>

  <Tab title="OpenAI Python">
    ```python theme={"system"}
    from openai import OpenAI
    from portkey_ai import PORTKEY_GATEWAY_URL, createHeaders

    client = OpenAI(
        api_key="PORTKEY_API_KEY",
        base_url=PORTKEY_GATEWAY_URL,
        default_headers=createHeaders(
            provider="@anthropic",
            api_key="PORTKEY_API_KEY"
        )
    )

    response = client.files.delete("<file_id>")

    print(response)
    ```
  </Tab>

  <Tab title="OpenAI NodeJS">
    ```js theme={"system"}
    import OpenAI from 'openai';
    import { PORTKEY_GATEWAY_URL, createHeaders } from 'portkey-ai';

    const client = new OpenAI({
        apiKey: "PORTKEY_API_KEY",
        baseURL: PORTKEY_GATEWAY_URL,
        defaultHeaders: createHeaders({
            provider: "@anthropic",
            apiKey: "PORTKEY_API_KEY"
        })
    });

    const response = await client.files.delete("<file_id>");

    console.log(response);
    ```
  </Tab>
</Tabs>

## Supported file types

Anthropic's Files API supports the following file types:

| Type   | MIME types                                           |
| ------ | ---------------------------------------------------- |
| PDF    | `application/pdf`                                    |
| Images | `image/jpeg`, `image/png`, `image/gif`, `image/webp` |

## Limitations

* The Files API is only available on **direct Anthropic API** — it is not supported on Bedrock or Vertex AI
* Files API is currently in **beta** and requires the `files-api-2025-04-14` beta header for cURL requests
* Refer to [Anthropic's documentation](https://docs.anthropic.com/en/docs/build-with-claude/files) for the latest file size and rate limits