> This page is for version v2025-04-21.
> For other versions, use one of these documentation indexes:
> - v2026-02-09 (default): https://docs.extend.ai/2026-02-09/llms.txt
> - v2025-04-21: https://docs.extend.ai/2025-04-21/llms.txt
> - v2024-12-23: https://docs.extend.ai/2024-12-23/llms.txt

> ## Documentation Index
> Fetch the complete documentation index at: https://docs.extend.ai/llms.txt
> Use this file to discover all available pages before exploring further.
>
> ## API version
> The current API version is `2026-02-09`, served at the site root (no version prefix in URLs).
> If this page URL contains `/2025-04-21/` or `/2024-12-23/`, you are reading an older API version.
> Prefer the current docs at https://docs.extend.ai/llms.txt unless the user explicitly needs that older version.
> Do not treat older-version pages as the source of truth for new integrations.

## Authentication

The Extend API uses Bearer token authentication for all API requests. You’ll need to use your API token when instantiating the client if you’re using the SDK or in the `Authorization` header of each request if you’re using the API directly.

Log in to the Extend dashboard and obtain an Extend API key from the [Developer Settings page](https://dashboard.extend.ai/developers). [More details](/2025-04-21/developers/authentication) on authentication, including error handling.

## Example Usage

### Request

POST [https://api.extend.ai/parse](https://api.extend.ai/parse)

```curl
curl -X POST https://api.extend.ai/parse \
     -H "x-extend-api-version: 2025-04-21" \
     -H "Authorization: Bearer <token>" \
     -H "Content-Type: application/json" \
     -d '{
  "file": {}
}'
```

```python
from extend_ai import Extend

client = Extend(
    token="YOUR_TOKEN_HERE",
    extend_api_version="2025-04-21",
)

client.parse()

```

```java
package com.example.usage;

import ai.extend.ExtendClient;
import ai.extend.requests.ParseRequest;

public class Example {
    public static void main(String[] args) {
        ExtendClient client = ExtendClient
            .builder()
            .token("YOUR_TOKEN_HERE")
            .extendApiVersion("2025-04-21")
            .build();

        client.parse(
            ParseRequest
                .builder()
                .build()
        );
    }
}
```

## Coding with an agent?

Use our curated platform context file to seed coding assistants with Extend platform context — open [`https://docs.extend.ai/agents.md`](https://docs.extend.ai/agents.md) (identical content whether you save it as `AGENTS.md` or `CLAUDE.md`):

```bash
# Codex, Cursor, and most harnesses
curl -fsSL https://docs.extend.ai/agents.md -o AGENTS.md

# Claude Code
curl -fsSL https://docs.extend.ai/agents.md -o CLAUDE.md
```

#### How do I use this?

1. Save the file in your project root as `CLAUDE.md` or `AGENTS.md`.
2. Run your coding agent from that same project root so it can discover the file.
3. If your agent does not auto-load root guidance, explicitly reference the file in your prompt (for example: "Use `./CLAUDE.md` for project instructions.").
4. For Codex/agent-style tools, keep `AGENTS.md` in the working directory root where commands are executed.
5. For Claude Code, keep `CLAUDE.md` at repository root and start the session from that directory.
6. In web LLM chats (for example ChatGPT, Claude, Gemini), upload `CLAUDE.md` or `AGENTS.md` as an attachment at the start of the conversation.
7. If attachments are not available, paste the file content into your first prompt and ask the model to follow it for the rest of the session.

## Next Steps

* [Follow our 5-minute quickstart](/2025-04-21/product/extraction/quick-start-5-minutes) to get started with structured data extraction.
* Try out our [SDKs](/2025-04-21/developers/sdks) in multiple languages