> This page is for version v2026-02-09 (default).
> 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.

# Latency Optimization

> Quick guide to reducing extraction latency with the most impactful configuration changes.

When processing high-volume documents or building real-time applications, latency becomes a critical factor. This guide provides the most impactful settings to reduce latency.

> **Note**
>
> Many latency-sensitive settings involve trade-offs with accuracy for complex documents. See [Configuration](/extraction/configuration) for detailed explanations of each setting.

## Quick Reference

Use this checklist when optimizing for latency:

**Advanced Options**

* **Use `extraction_light`** for simple document types (verify accuracy with evaluation sets)
* **Turn off model reasoning insights** (`modelReasoningInsightsEnabled: false`) - only needed for debugging
* **Disable advanced multimodal** (`advancedMultimodalEnabled: false`) - unless processing scans/handwritten content
* **Turn off bounding box citations** (`citationsEnabled: false`) - removes spatial location references

**Extraction Chunking Options**

* **Limit page ranges** if data is on specific pages
* **Increase `pageChunkSize`** for non-array extraction so the document fits in fewer chunks and skips merging
* **Use `confidence` or `take_first` merging** instead of `intelligent`
* **Use `large_array_heuristics`** array strategy if processing large arrays

**Parser Configuration**

* **Disable figure parsing** - unless documents contain important charts/diagrams
* **Disable formula parsing** - unless documents contain mathematical equations
* **Disable agentic OCR** - unless processing handwritten/poor quality scans

**Workflow**

* **Split into parallel extractors** if you have both simple fields and complex arrays

---

## Light Extraction

The biggest change you can make to reduce latency is selecting **Extraction Light** instead of the default Extraction Performance.

![Core performance settings in Extend Studio](/_fern-img/27c0c7bb6a92db2796f7c9c0b50203c49f2c2164b2c2b690d1300f5638772b7b.webp)

```json
{
  "config": {
    "baseProcessor": "extraction_light"
  }
}
```

Extraction Light is faster and cheaper, but removes support for advanced visual features like figure parsing and signature detection. See the [Extraction Light versioning page](/model-versioning/extraction/extraction-light) for details.

---

## Disabling Advanced Options

Each of these options adds processing overhead. Disable what you don't need:

| Option                       | What disabling does                                                                                               | Config                                 |
| ---------------------------- | ----------------------------------------------------------------------------------------------------------------- | -------------------------------------- |
| **Bounding Box Citations**   | Removes spatial location references for extracted values. See [Citations](/extraction/response-format#citations). | `citationsEnabled: false`              |
| **Advanced Multimodal**      | Skips vision-language model processing. Keep enabled for scans/handwriting.                                       | `advancedMultimodalEnabled: false`     |
| **Model Reasoning Insights** | Removes decision-making explanations. Only needed for debugging.                                                  | `modelReasoningInsightsEnabled: false` |

---

## Chunking Optimizations

![Chunking options in Extend Studio](/_fern-img/77b6f0e85473723f7ea8c961db61bd064791c189d5357eb0ab21980b86eb9980.webp)

**For non-array extraction:** Increase `pageChunkSize` so the document fits in a single chunk, which skips intelligent merging entirely—the fastest option.

**For large array extraction:** Use `large_array_heuristics` array strategy with smaller chunk sizes.

**Merging strategy:** Switch from `intelligent` to `confidence`, `take_first`, or `take_last` to avoid extra processing overhead.

![Merging strategy settings in Extend Studio](/_fern-img/e70572260b9318b054544fcd6386fad14c60476a184995906923fb0ed285bec6.webp)

| Merging Strategy | Speed   | Use when                                      |
| ---------------- | ------- | --------------------------------------------- |
| `intelligent`    | Slowest | Accuracy is critical (default)                |
| `confidence`     | Fast    | General purpose, good default for latency     |
| `take_first`     | Fastest | Authoritative values appear at document start |
| `take_last`      | Fastest | Authoritative values appear at document end   |

---

## Disable Advanced Parsing Options

![Parser block options in Extend Studio](/_fern-img/1d6b0290540210c8b5d6cd57285c8c46eddb424af55dc085773ffeec3cd058be.webp)

* **Figure parsing** - Disable unless documents contain important charts/diagrams
* **Formula parsing** - Disable unless documents contain mathematical equations
* **Signature detection** - Disable unless signature verification is needed
* **Agentic OCR** - Disable unless processing handwritten or poor-quality scans

---

## Parallel Extractors

For large extractions or schemas, consider breaking a single extractor into multiple extractors that run in parallel within a [Workflow](/workflows/overview). This is particularly effective when you have both simple top-level fields and complex array extractions.

![Workflow showing a financial document split into two parallel extractors](/_fern-img/2e4b6854e457a23d1956ad8dc26335a8b85b61875cde67eb1be78450ac0f8f9d.webp)

The workflow above splits a financial document into two parallel extractors — one for high-level fields and one for the line-item details — which run at the same time and are recombined in the workflow output.

**Use when:**

* Documents have both simple fields and complex arrays
* Array extraction is significantly slower than the other fields
* Total latency is critical to your use case

---

## Related Topics

* See [Configuration](/extraction/configuration) for detailed explanations of each setting
* Understand [Field Names and Prompt Crafting](field-names-and-prompt-crafting) for schema optimization
* Explore [Evaluation Sets](/evaluation/overview) to validate accuracy when optimizing for speed