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

# Migration FAQ

> Common questions about moving from Chunkr to Extend

## Accounts and access

<AccordionGroup>
  <Accordion title="Will my Chunkr API key work on Extend?">
    No. Extend is a separate platform with its own accounts and keys. Create an account at [extend.ai](https://extend.ai) and generate a key from the Developers page. See [Getting Started](/pages/migrate-to-extend/getting-started).
  </Accordion>

  <Accordion title="Are my documents and task outputs migrated to Extend?">
    No. Retrieve anything you need from Chunkr via `tasks.parse.get`, `tasks.extract.get`, or the dashboard, and re-upload source files to Extend with `files.upload`.
  </Accordion>

  <Accordion title="Can I run both in parallel while I validate?">
    Yes, and we recommend it. Process a representative sample through both APIs and compare. Extend's [evaluation sets](https://docs.extend.ai/evaluation/overview) let you store expected outputs and measure extraction accuracy as you tune configuration.
  </Accordion>
</AccordionGroup>

## Deployment

<AccordionGroup>
  <Accordion title="I use Chunkr on-premise. What are my options?">
    Extend offers three deployment models: Extend-managed cloud (US or EU region), **BYOC** (deployed into your own cloud account and VPC), and **Hybrid** (documents stay in your cloud, inference runs in Extend's). Extend does not currently offer a fully air-gapped deployment. See [Extend deployment options](https://docs.extend.ai/security/deployment-options).
  </Accordion>

  <Accordion title="Does Extend offer an EU region?">
    Yes. Use the EU1 region at `https://api.eu1.extend.ai`. Set `base_url` / `baseUrl` on the SDK client. See [regions](https://docs.extend.ai/api-reference/deployments).
  </Accordion>
</AccordionGroup>

## Legacy (v1) API customers

<AccordionGroup>
  <Accordion title="I'm still on the Chunkr v1 API. Does this guide apply to me?">
    Yes. The v1 API's `TaskResponse` output (chunks containing segments with `segment_type`, `bbox`, `content`) is structurally the same as the current API, so the [Parse migration](/pages/migrate-to-extend/parse) applies directly. The main difference is that v1 used `chunkr.upload(file)` and `chunkr.get_task(id)` rather than `client.tasks.parse.*`. See the [Legacy docs](/pages/v1/get-started/overview) for v1 reference.
  </Accordion>

  <Accordion title="I self-host Chunkr with Docker Compose or Kubernetes. What should I do?">
    See the on-premise answer above about Extend's BYOC and Hybrid deployments.
  </Accordion>
</AccordionGroup>

## Features

<AccordionGroup>
  <Accordion title="Is anything from Chunkr missing on Extend?">
    A few things have no direct equivalent. The [Concept Mapping](/pages/migrate-to-extend/concepts) page flags each one. In short:

    * Rendered **page images** are not returned. Render pages from the original file.
    * **Base64** file input is not accepted. Use `files.upload`.
    * **Token-based chunking** is replaced by character-based chunking.
    * **`extended_context`** has no equivalent; `blockOptions.figures.customInstructions` can steer figure descriptions.
    * **`segmentation_strategy: Page`** (full-page VLM) has no equivalent.
    * **`expires_in`** auto-deletion is replaced by explicit `delete` calls.
    * Spreadsheet **`ss_sheet_name`** and citation-level **`ss_ranges`** are not exposed.
  </Accordion>

  <Accordion title="What's new on Extend that Chunkr didn't have?">
    <CardGroup cols={2}>
      <Card title="Classification" href="https://docs.extend.ai/classification/overview" icon="tags">
        Sort documents into categories you define, with confidence and reasoning.
      </Card>

      <Card title="Splitting" href="https://docs.extend.ai/splitting/overview" icon="scissors">
        Break a multi-document PDF into typed sub-documents with page ranges.
      </Card>

      <Card title="Editing" href="https://docs.extend.ai/editing/overview" icon="pen-to-square">
        Detect and fill PDF form fields from data or natural-language instructions.
      </Card>

      <Card title="Workflows" href="https://docs.extend.ai/workflows/overview" icon="diagram-project">
        Chain classify, split, extract, validation, and human review into a pipeline.
      </Card>

      <Card title="Evaluation sets" href="https://docs.extend.ai/evaluation/overview" icon="flask">
        Benchmark extractors against ground truth and track accuracy per field.
      </Card>

      <Card title="Human review" href="https://docs.extend.ai/workflows/human-review" icon="user-check">
        Route low-confidence runs to a review queue and consume corrected output.
      </Card>
    </CardGroup>
  </Accordion>

  <Accordion title="Can a coding agent do the migration for me?">
    Mostly, yes. Extend publishes an [agent context file](https://docs.extend.ai/agents.md), a [docs MCP server](https://docs.extend.ai/mcp), and an `extend-api` skill. Point your agent at this migration guide plus those resources, and have it rewrite your integration. Review schema changes and bounding-box code by hand; those are where subtle differences live.
  </Accordion>
</AccordionGroup>


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.