GOT-OCR v2

Free.ai · ocr · ~500 tokens per page

Fi àwòrán pamọ́

Ti fáìlì síbẹ̀ tàbí tẹ̀ láti ṣàfihàn

~500 tokens per page

N ṣiṣẹ́ ọ̀fẹ̀ nípa GPUs wa. Àwọn ìṣàfihàn fún GOT-OCR v2 →

GOT-OCR v2 ni an Àwọn ìṣàmúlò-ètò OCR. A ti ṣetó nípa àwọn àwọn àwòrán inú — ~500 tokè Àwọn ojú-ìwé (50% tí a fi pamọ́ lọ́wọ́lú).

Lò nípa API

OpenAI-compatible REST API. Generate a key and call this model in seconds.

curl -X POST https://api.free.ai/v1/ocr/ \
  -H "Authorization: Bearer sk-free-..." \
  -H "Content-Type: application/json" \
  -d '{"model":"premium/got-ocr/v2","prompt":"your prompt here"}'

Àwọn Àkọsílẹ̀ Gba àwọn àwọn àmì-ìwé API

Àwọn Àtòjọ-ẹ̀yàn

GOT-OCR v2 extracts text from images and PDFs. Upload a scanned page, a screenshot, or a photo of a document and GOT-OCR v2 returns the text — preserving line breaks and (on capable engines) tables, formulas, and structure.

GOT-OCR v2 n ṣakoso àwọn ìrísí-lẹ́tà kọ́ọ̀kan - Latin, Cyrillic, CJK, Arabic, Devanagari, àti àwọn mìíràn. Ààyè /ocr/ ní àtòjọ ìtàn ìtàn fún ìpéwọ̀n fún ìpéwọ̀n.

Yes for clean printed-style handwriting; cursive and shorthand are harder. TrOCR and modern transformer-based engines are noticeably better than legacy Tesseract on handwriting.

Àwọn inú ìṣàmúlò-ètò-ìmọ̀ (GOT-OCR, Marker, Florence-2) ń fi àwọn táàbù Markdown/HTML pamọ́ láti fi àwọn ìṣàmúlò-ètò pamọ́. Àwọn inú àkọlé ìṣàmúlò-ètò ìṣàmúlò-ètò láti fi àwọn àkọlé pamọ́ láti fi àwọn ìṣàmúlò-ètò láti fi àwọn ìṣàmúlò-ètò pamọ́.

GOT-OCR v2 ní ìṣẹ̀dá OCR. Àwọn tókènì 500-1,500 nínú ojú-ìwé kan. $1 = tókènì 750,000.

PNG, JPG, WebP, HEIC, BMP, plus-ọ̀kan atí àwọn ojú-ìwé àìpẹ̀là-àwọn PDFs lọ́wọ́lọ́wọ́ sí 50 MB. Àwọn ojú-ìwé tí a kọ̀ọ̀kan tàbí a tí a kọ̀ọ̀kan nípa ìṣàfarawé àwọn àwọn ojú-ìwé tí a kọ̀ọ̀kan nípa ìṣàfilọ́lẹ̀.

Àwọn àwọn àmì-àṣírí tí a fi pamọ́ ní >98% nínú àwọn ojú-ìwé àìṣàfilọ́lẹ̀, àwọn àwòrán àìfàn, àwọn ìṣàmúlò-ètò àìdálẹ̀, àti àwọn ìrísí-lẹ́tà àìdálẹ̀. Àwọn ìṣàfilọ́lẹ̀ àwọn inú ìrísí-lẹ́tà nínú /ocr/compare/ tí àwọn àwọn àmì-àṣírí bá jẹ́ pataki.

Yes — /batch/ accepts a folder of images/PDFs. Each extraction lands in /account/?tab=history. For folder-tree preservation use the API.

Yes — POST your file to /v1/ocr/ with model="GOT-OCR v2". Returns JSON with text + (when supported) layout + word-level bounding boxes. /api/ has the full reference.

Self-hosted models keep your file on our GPUs; premium pass through with a DPA. Documents are deleted after the share-window. We do not train on your inputs.

Ya — Free.ai gba ìlòòrò àwọn àkọlé tí a yá. Ò nì àwọn ìwọ̀n láti lò nípa àkọlé orílẹ̀ẹ̀dà.

1–5 seconds per page typically. Layout-aware engines (tables, math) take longer. Multi-page PDFs scale roughly linearly.

GOT-OCR v2

Lò nípa API

Àwọn Àtòjọ-ẹ̀yàn

Àwọn àṣẹ GOT-OCR v2 wo ní?

Àwọn ìtàn wo ní GOT-OCR v2 ǹfà?

Àwọn àwọn àkọlé àwọn àwọn àkọlé

Does GOT-OCR v2 preserve table structure or math formulas?

Ìgbà wo ní GOT-OCR v2 ń kùnà nínú ojú-ìwé kan?

Àwọn ìṣàmúlò-ètò ìpamọ́ wo ni GOT-OCR v2 gbà?

Ìyàn wo ní GOT-OCR v2?

Ń lè fi OCR pamọ́ láti GOT-OCR v2?

Is there an API for GOT-OCR v2?

Kini nipa ìdàjọ́ nígbà tí mò bá kọ́kọ́ àwọn àkọsílẹ̀ àìdálẹ̀ OCR pẹ̀lú GOT-OCR v2?

Àwọn àtòjọ-ẹ̀yàn GOT-OCR v2 ní ìdáràn fún ìlò àwọn iṣẹ́ ọ̀fẹ́?

Ìgbà wo ní GOT-OCR v2 náà?

Gba 10,000 Free Tokens

Wá - Gba 10K Free Tokens!

Tí o fẹ́ láti mú diẹ̀ sii?