---
title: "Arabic OCR API comparison (2026) | BroadRouter"
description: "Which OCR APIs officially support Arabic, printed and handwritten, what each returns and what it costs per 1,000 pages, compared with vision LLM APIs."
url: https://broadrouter.com/blog/arabic-ocr-api-comparison/
lang: en
updated: 2026-11-15
publisher: BroadRouter (a BroadNet site); API by BroadNet Inference, https://inference.broadnet.ai
---

# Arabic OCR API comparison: Google, Azure, Textract, Mistral, LLMs

By the BroadNet Inference team · 8 min read · Published 2026-11-15 · Updated 2026-11-16

Four OCR APIs list Arabic printed text in their own docs: Google Cloud Vision, Azure AI Document Intelligence, Amazon Textract and Mistral OCR. Google, Azure Read and Textract each charge USD 1.50 per 1,000 pages at entry volume. Only Azure lists Arabic handwriting. Vision LLMs, such as Qwen3.8 27B on BroadNet, bill a page as tokens and return the fields you ask for.

## Key takeaways

-   Arabic printed text is listed by Google Cloud Vision, Azure Document Intelligence (Read and Layout), Amazon Textract and Mistral OCR (checked 2026-11-15).
-   Arabic handwriting is listed only by Azure Document Intelligence v4.0. Textract says handwriting is English only; Google's handwriting script table does not include Arabic.
-   Plain OCR costs USD 1.50 per 1,000 pages at entry volume on Google, Azure Read and Textract (checked 2026-11-15), with lower rates at high volume. Azure's invoice and layout models cost USD 10 per 1,000 pages.
-   A vision LLM bills a page as input tokens plus the answer, so cost depends on image size and output length. Measure it with usage.prompt\_tokens.
-   No vendor publishes an independent Arabic accuracy test we could verify. Score 50 to 100 of your own pages before you choose.

**On this page**

1.  Which OCR APIs officially support Arabic?
2.  What does each Arabic OCR API cost per 1,000 pages?
3.  What does a vision LLM cost per page?
4.  How do the integration details differ?
5.  Which Arabic OCR API should you choose?
6.  How do you test Arabic OCR APIs on your own documents?
7.  Where BroadNet Inference fits

Search for “Arabic OCR API” and most results are ranking sites that don’t say where their scores come from. This page does the narrower job a buyer needs. For each API, it shows what the vendor’s own documentation says about Arabic, what the API returns and what a page costs. Every figure was read from the vendor’s page on 15 November 2026. BroadRouter is BroadNet’s website, and BroadNet sells one of the options below (vision LLMs, not OCR), so we say where the others do better.

If you are still deciding between OCR and a vision LLM in principle, start with [Arabic OCR vs vision LLMs](https://broadrouter.com/blog/arabic-ocr-vision-llm/). It explains why connected script, dots and mixed-direction lines make Arabic hard. This post assumes you know that and want to pick a vendor.

## Which OCR APIs officially support Arabic?

| API | Arabic printed text | Arabic handwriting | What it returns |
| --- | --- | --- | --- |
| Google Cloud Vision (`DOCUMENT_TEXT_DETECTION`) | Yes, `ar`, listed as Modern Standard | Not listed (Arabic script is not in the handwriting table) | Text with page, block, paragraph, word and break information |
| Azure AI Document Intelligence, Read (`prebuilt-read`) | Yes, `ar` | Yes, in v4.0 (not in v3.1) | Printed and handwritten text |
| Azure AI Document Intelligence, Layout (`prebuilt-layout`) | Yes, `ar` | Yes, in v4.0 | Text, tables, document structure and selection marks |
| Azure prebuilt invoice and receipt | Invoice lists Arabic (`ar`); thermal receipts list Arabic | n/a | Named invoice and receipt fields |
| Amazon Textract (Detect Document Text) | Yes, among 40+ languages | No: “handwriting … in English only” | Words and lines, each with a bounding box and confidence score |
| Mistral OCR (`mistral-ocr-latest`) | Yes, listed under Middle Eastern languages | Not stated | Per-page Markdown plus JSON fields: tables, images, headers, footers, blocks, confidence scores |
| Vision LLM (Qwen3.8 27B, Gemma 4 VL 26B, DeepSeek V4.1 Flash on BroadNet) | Reads Arabic images; not an OCR engine | Not documented | Whatever you ask for: text, fields, JSON, a translation |

Two details matter more than the yes/no columns:

-   **Textract limits more than handwriting.** Its FAQ says “Handwriting, Invoices, and Receipts, Identity documents, and Queries processing are in English only.” On Arabic documents, Textract gives you text and positions, not invoice fields.
-   **Azure’s Arabic handwriting is new in v4.0.** The v3.1 handwriting table does not include Arabic. Pin the API version you test against.

Mistral’s language page says its list reflects “languages with strong expected performance”, which is a vendor statement, not a measured score.

## What does each Arabic OCR API cost per 1,000 pages?

Prices in US dollars, read on 15 November 2026 from each vendor’s pricing source:

| API and feature | Free allowance | Entry price per 1,000 pages | High-volume price |
| --- | --- | --- | --- |
| Google Cloud Vision, Document Text Detection | First 1,000 units a month | USD 1.50 (units 1,001 to 5,000,000) | USD 0.60 above 5M units a month |
| Azure Document Intelligence, Read (East US) | 500 pages a month on the free tier | USD 1.50 | USD 0.60 after the first 1M pages |
| Azure Document Intelligence, Layout and prebuilt models (East US) | Same free tier | USD 10 | Commitment tiers are listed on Azure’s pricing page (prices load in the browser; check your region) |
| Amazon Textract, Detect Document Text (US West, Oregon) | 1,000 pages a month for new AWS customers, for three months | USD 1.50 (first 1M pages a month) | USD 0.60 after 1M pages |
| Mistral OCR | Not stated | Priced per 1,000 pages; the amount is not in the page’s static HTML, so we could not confirm it | Mistral says batch processing halves its API prices |

Google bills each PDF page as one image, and each feature as a separate unit. Asking for two features on one page costs two units. Azure’s prebuilt price covers layout, invoice and receipt. If you need structured invoice fields from Azure, plan on the USD 10 rate, not the USD 1.50 Read rate.

## What does a vision LLM cost per page?

A vision LLM has no per-page price. On BroadNet pay-as-you-go keys, the docs say an image “counts as input tokens at the model’s input price”, and a larger image uses more tokens. The page cost is the image tokens plus your prompt, plus the answer at the output price.

Image tokens vary by model and resolution. Gemma 4 uses budgets of 70, 140, 280, 560 or 1,120 tokens per image, and Google’s docs recommend a higher budget for the best accuracy on visual tasks. As a planning shape, not a measurement, take about 1,000 input tokens and 300 output tokens per page:

| BroadNet model | Input per 1M | Output per 1M | 1,000 pages at about 1M input and 0.3M output |
| --- | --- | --- | --- |
| Gemma 4 VL 26B | $0.10 | $0.22 | $0.10 plus three tenths of $0.22 |
| Qwen3.8 27B | $0.175 | $2.17 | $0.175 plus three tenths of $2.17, plus reasoning |
| DeepSeek V4.1 Flash | $0.175 | $0.52 | $0.175 plus three tenths of $0.52, plus reasoning |

Qwen3.8 27B and DeepSeek V4.1 Flash reason before they answer, and reasoning is billed as output. Keep `max_tokens` at 1,000 or more, or set `reasoning_effort` to `low`, or the answer can come back empty ([why](https://broadrouter.com/guides/reasoning-tokens-empty-response/)). Measure your own pages: send ten, read `usage.prompt_tokens` and `usage.completion_tokens`, and multiply. The [image token calculator](https://broadrouter.com/tools/image-token-calculator/) and [vision LLM cost per image](https://broadrouter.com/blog/cheapest-vision-llm-api/) do the arithmetic.

The comparison is not like for like. USD 1.50 per 1,000 pages buys raw text and positions. A vision LLM call can return the vendor, VAT number, date and total as JSON in the same request, which saves you the parsing step. Gemma 4 VL 26B is also covered by the $5 starting credit. Qwen3.8 27B and DeepSeek V4.1 Flash need a top-up.

## How do the integration details differ?

|  | Google Cloud Vision | Azure Document Intelligence | Amazon Textract | Mistral OCR | BroadNet vision LLMs |
| --- | --- | --- | --- | --- | --- |
| Input | Images; PDF and TIFF through `DOCUMENT_TEXT_DETECTION` | See the Read model’s file-type list | See the Textract file-type list | `image_url` (PNG, JPEG, AVIF and more) or `document_url` (PDF, PPTX, DOCX and more) | One image per content item as a `data:` URL; render PDF pages to images first |
| Language hint | Optional `ar` hint | Optional; Microsoft advises not to set it unless you are sure | Not covered in the FAQ | Not stated | Say “the document is in Arabic” in the prompt |
| Structured fields | No (text hierarchy only) | Yes, prebuilt invoice and receipt | Invoices, receipts and Queries are English only | Optional document annotations | Ask for JSON; structured output is documented for Qwen3.8 27B only |
| API shape | Google Cloud API | Azure REST and SDKs | AWS SDKs | Mistral `/v1/ocr` | OpenAI-compatible `/v1/chat/completions` |

Microsoft’s note on language codes is worth reading if your documents mix Arabic and English: “Don’t provide the language code as the parameter unless you are sure of the language … Otherwise, the service may return incomplete and incorrect text.”

## Which Arabic OCR API should you choose?

There is no single answer, and no vendor publishes an independent Arabic accuracy test we could verify. Choose by output first, then test:

1.  **You need searchable text from long scanned archives.** Google Cloud Vision, Azure Read or Textract. All three list Arabic printed text at the same entry price. Choose the cloud you already use for storage and identity.
2.  **You need handwritten Arabic.** Azure Document Intelligence v4.0 is the only OCR API here that lists it. Also test a vision LLM on the same pages, since none of them document handwriting either way.
3.  **You need invoice fields from Arabic invoices.** Compare Azure’s prebuilt invoice model (USD 10 per 1,000 pages) with a vision LLM that returns JSON. On BroadNet, Qwen3.8 27B is the model with documented structured output. [Read Arabic invoices with a vision model](https://broadrouter.com/guides/read-arabic-invoices-with-vision/) has working code.
4.  **You want Markdown with tables for RAG.** Mistral OCR returns per-page Markdown with tables and blocks. Confirm its current per-page price on Mistral’s pricing page.
5.  **You need fields, translation and a summary in one call.** A vision LLM. The pipeline, with validation, is in [extract invoice data to JSON with a vision LLM](https://broadrouter.com/blog/extract-data-from-documents-with-vision-llm/).

## How do you test Arabic OCR APIs on your own documents?

1.  **Pick 50 to 100 real pages**: clean PDFs, phone photos, faded thermal receipts, stamped invoices and, if you have them, handwritten forms.
2.  **Type a ground truth** for the fields you care about. Keep Eastern Arabic digits (٠١٢٣) as printed, and note them separately.
3.  **Score characters and fields separately.** [Character error rate](https://broadrouter.com/glossary/character-error-rate/) shows reading quality. Field accuracy (total, date, VAT number) shows business quality. A one-digit error in a total matters more than ten in a footer.
4.  **Check order on mixed lines.** A line such as “الإجمالي: 1,250.00 SAR” can come back with the number before the label. That is a bidirectional-order problem, not a recognition error, but your parser still has to cope with it.
5.  **Validate numbers in code** whatever you choose: line items sum to the total, VAT matches the rate and dates parse. Send failures to a [human review queue](https://broadrouter.com/blog/document-review-queues/).

## Where BroadNet Inference fits

BroadRouter is BroadNet’s website. BroadNet Inference does not sell an OCR engine. It sells vision LLMs on one OpenAI-compatible API: Qwen3.8 27B, BroadNet Gemma 4 VL 26B and DeepSeek V4.1 Flash, all of which accept images. If you need the cheapest raw text from millions of scanned pages, or Arabic handwriting with positions, a classic OCR API listed above is a better fit. BroadNet fits when you want fields or JSON from Arabic documents, with [zero data retention](https://broadrouter.com/zero-data-retention/): BroadNet says inference content is not retained. Try Gemma 4 VL 26B on the $5 starting credit, or read the [API reference](https://inference.broadnet.ai/docs?utm_source=broadrouter&utm_medium=referral&utm_campaign=blog-arabic-ocr-api-comparison&utm_content=body) and [get a key](https://inference.broadnet.ai/?utm_source=broadrouter&utm_medium=referral&utm_campaign=blog-arabic-ocr-api-comparison&utm_content=body).

Free tools for this

-   [Arabic token counter](https://broadrouter.com/tools/arabic-token-counter/) Arabic vs English token counts per tokenizer: the "Arabic tax" in tokens and money.
-   [Arabic text normalizer](https://broadrouter.com/tools/arabic-text-normalizer/) Tashkeel, tatweel, alef, ya, ta marbuta, digits and invisible characters, with a matching Python function.
-   [Speech-to-text cost calculator](https://broadrouter.com/tools/speech-to-text-cost-calculator/) Hours, calls or voice notes to a monthly transcription bill, against your current provider.

[All free tools](https://broadrouter.com/tools/)

## Terms in this article

[Token](https://broadrouter.com/glossary/token/)

A token is the unit of text a language model reads and writes: a word, part of a word, a punctuation mark or a byte sequence produced by the model's tokenizer. LLM APIs count, limit and usually bill usage in tokens.

[Input and output tokens](https://broadrouter.com/glossary/input-and-output-tokens/)

Input tokens are the tokens a language model reads in a request, including the system prompt, conversation history, tool definitions and images. Output tokens are the tokens it generates in reply, including any reasoning. LLM APIs usually price them separately, and output usually costs more.

[Image tokens](https://broadrouter.com/glossary/image-tokens/)

Image tokens are the input tokens a vision language model uses to represent an image in a prompt. Providers compute them from the image's size, usually by splitting it into fixed-size patches or tiles after resizing, and bill them like text input tokens, so larger images cost more.

[Structured output](https://broadrouter.com/glossary/structured-output/)

Structured output is an LLM API feature that constrains a model's reply to a format the developer specifies, usually a JSON Schema, so code can parse it reliably. It is stricter than JSON mode, which guarantees valid JSON but not a particular shape.

[Character error rate (CER)](https://broadrouter.com/glossary/character-error-rate/)

Character error rate (CER) measures transcription or OCR accuracy at the character level: the substitutions, deletions and insertions needed to turn the output into the reference text, divided by the number of characters in the reference. Lower is better, and 0 is a perfect match.

[OpenAI-compatible API](https://broadrouter.com/glossary/openai-compatible-api/)

An OpenAI-compatible API is an HTTP API that accepts the same request and response formats as the OpenAI API, such as POST /v1/chat/completions, so OpenAI SDKs and tools can use it by changing only the base URL, the API key and the model name.

[Pay-as-you-go](https://broadrouter.com/glossary/pay-as-you-go/)

Pay-as-you-go is a pricing model in which you pay only for what you use, metered per unit such as tokens, requests or audio minutes, with no subscription or minimum commitment. Most LLM APIs bill this way, from a prepaid balance or a periodic invoice.

[Prepaid credit](https://broadrouter.com/glossary/prepaid-credit/)

Prepaid credit is money added to an API account before use. Each request deducts its cost from the balance, and when the balance runs out, metered requests stop until you top up. It caps spend at what you have paid in.

## Questions

### Which OCR API supports Arabic?

On 15 November 2026, Google Cloud Vision, Azure AI Document Intelligence, Amazon Textract and Mistral OCR all listed Arabic printed text in their own documentation. Vision LLM APIs such as Qwen3.8 27B, Gemma 4 VL 26B and DeepSeek V4.1 Flash on BroadNet Inference also read Arabic images, but they are chat models, not OCR engines.

### Which API reads handwritten Arabic?

Of the four OCR APIs, only Azure Document Intelligence v4.0 lists Arabic for handwritten text, in both the Read and Layout models. Textract says handwriting is English only, and Google's handwriting script table does not include Arabic script. Vision LLMs do not publish handwriting support either way, so test them on your own samples.

### How much does Arabic OCR cost per 1,000 pages?

At entry volume, USD 1.50 per 1,000 pages on Google Cloud Vision Document Text Detection, Azure Document Intelligence Read and Amazon Textract Detect Document Text (checked 15 November 2026). All three drop to USD 0.60 at high volume. Azure's layout and prebuilt invoice models cost USD 10 per 1,000 pages.

### Is Amazon Textract able to read Arabic?

Yes for printed text. The Textract FAQ (checked 15 November 2026) says it detects printed text, including right-to-left and mixed-script documents, in more than 40 languages including Arabic. It also says handwriting, invoices and receipts, identity documents and Queries are English only.

### Should I use an OCR API or a vision LLM for Arabic invoices?

Use OCR when you need every word with its position, for search or archives. Use a vision LLM when you need named fields such as vendor, VAT number and total as JSON. A common pattern is both: OCR for searchable text, a vision LLM for the fields you act on, then checks in code.

### Which BroadNet model can return structured JSON from an Arabic document?

Qwen3.8 27B. BroadNet's docs list tools and structured output for Qwen3.8 27B and GLM 5.3, and GLM 5.3 is text only. Gemma 4 VL 26B and DeepSeek V4.1 Flash accept images, but structured output is not listed for them, so ask for JSON in the prompt and validate it.

## Keep reading

-   [Arabic OCR vs vision LLMs: reading Arabic documents and invoices](https://broadrouter.com/blog/arabic-ocr-vision-llm/)
-   [Cheapest vision LLM API: cost per image and per page, worked out](https://broadrouter.com/blog/cheapest-vision-llm-api/)
-   [Extract invoice, receipt and form data to JSON with a vision LLM](https://broadrouter.com/blog/extract-data-from-documents-with-vision-llm/)
-   [JSON mode vs json\_schema: structured output that holds up](https://broadrouter.com/blog/structured-output-json-schema/)
-   [Make human review part of your document AI workflow](https://broadrouter.com/blog/document-review-queues/)
-   [Add diacritics to Arabic text with an LLM: prompt, checks, DER](https://broadrouter.com/blog/arabic-diacritization-llm/)
-   [Arabic grammar and spelling correction with an LLM: a how-to](https://broadrouter.com/blog/arabic-grammar-spelling-correction-llm/)
-   [Guide: Read Arabic invoices and receipts with a vision model](https://broadrouter.com/guides/read-arabic-invoices-with-vision/)
-   [Guide: Why a reasoning model returns an empty answer](https://broadrouter.com/guides/reasoning-tokens-empty-response/)

Try it on your real workload. New accounts start with $5 of credit for Gemma and transcription. DeepSeek, GLM and Qwen3.8 need a top-up.

[Get started](https://inference.broadnet.ai/account/?utm_source=broadrouter&utm_medium=referral&utm_campaign=blog-arabic-ocr-api-comparison&utm_content=page-cta) ·

**Sources**

-   [Google Cloud Vision, OCR language support: Arabic (ar) supported, handwriting script table (checked 2026-11-15)](https://docs.cloud.google.com/vision/docs/languages)
-   [Google Cloud Vision, detect text in images: TEXT\_DETECTION vs DOCUMENT\_TEXT\_DETECTION output (checked 2026-11-15)](https://docs.cloud.google.com/vision/docs/ocr)
-   [Google Cloud Vision pricing: Document Text Detection per 1,000 units, first 1,000 free, PDF pages billed as images (checked 2026-11-15)](https://cloud.google.com/vision/pricing)
-   [Microsoft Learn, Document Intelligence Read and Layout language support: Arabic printed and handwritten in v4.0 (checked 2026-11-15)](https://learn.microsoft.com/en-us/azure/ai-services/document-intelligence/language-support/ocr?view=doc-intel-4.0.0)
-   [Microsoft Learn, Document Intelligence prebuilt model language support: invoice and receipt list Arabic (checked 2026-11-15)](https://learn.microsoft.com/en-us/azure/ai-services/document-intelligence/language-support/prebuilt?view=doc-intel-4.0.0)
-   [Azure Retail Prices API, Azure Document Intelligence S0 meters in East US: Read and Pre-built pages (checked 2026-11-15)](https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20%27Foundry%20Tools%27%20and%20productName%20eq%20%27Azure%20Document%20Intelligence%27%20and%20armRegionName%20eq%20%27eastus%27)
-   [Azure Document Intelligence pricing page: free tier of 500 pages a month (checked 2026-11-15)](https://azure.microsoft.com/en-us/pricing/details/ai-document-intelligence/)
-   [Amazon Textract FAQs: printed text in 40+ languages including Arabic; handwriting English only (checked 2026-11-15)](https://aws.amazon.com/textract/faqs/)
-   [Amazon Textract pricing: Detect Document Text examples, US West (Oregon) (checked 2026-11-15)](https://aws.amazon.com/textract/pricing/)
-   [Mistral docs, OCR processor: output fields and inputs (checked 2026-11-15)](https://docs.mistral.ai/capabilities/document_ai/basic_ocr/)
-   [Mistral docs, supported languages: OCR lists Arabic (checked 2026-11-15)](https://docs.mistral.ai/resources/languages)
-   [Mistral pricing: OCR priced per 1,000 pages (checked 2026-11-15)](https://mistral.ai/pricing)
-   [BroadNet Inference API reference: image input, vision models, tools and structured output (checked 2026-11-15)](https://inference.broadnet.ai/docs?utm_source=broadrouter&utm_medium=referral&utm_campaign=blog-arabic-ocr-api-comparison&utm_content=sources)
-   [BroadNet Inference machine-readable prices, pricing.json (checked 2026-11-15)](https://inference.broadnet.ai/pricing.json?utm_source=broadrouter&utm_medium=referral&utm_campaign=blog-arabic-ocr-api-comparison&utm_content=sources)
-   [Google Gemma docs, vision: image token budgets of 70 to 1,120 tokens (checked 2026-11-15)](https://ai.google.dev/gemma/docs/capabilities/vision)
