Skip to main content
Image utility fal.ai

GOT-OCR V2 (Text Extract)

GOT-OCR V2 (Text Extract) costs $0.060/image on FairStack — a utility model for Text extraction from photos, Document digitization, Sign and label reading. No subscription required. Pay per generation with full REST API access. FairStack applies a transparent 20% margin on infrastructure cost so you always see the real price.

FairStack price
$0.060/image

What is GOT-OCR V2 (Text Extract)?

GOT-OCR V2 (General OCR Theory V2) is an AI-powered text extraction model that reads text from any image at $0.05 per extraction. It handles printed text, handwriting, documents, signs, labels, and text in natural scenes, returning structured text output from visual input. The model goes beyond traditional OCR by understanding text in context, handling varied fonts, sizes, orientations, and lighting conditions. It processes documents, photographs of signs, product labels, handwritten notes, and text embedded in complex scenes. Output is returned as structured text suitable for downstream processing. Compared to traditional OCR engines which work best on clean, high-contrast document scans, GOT-OCR V2 handles the messier reality of text in natural photographs, angled perspectives, and varied lighting. Against multimodal language models used for text extraction, GOT-OCR V2 is specifically optimized for OCR accuracy rather than general image understanding. Best suited for extracting text from photographs, digitizing documents from camera captures, reading signs and labels in scene photos, and any workflow requiring accurate text extraction from images in varied conditions. Available on FairStack at infrastructure cost plus a 20% platform fee.

Key Features

Text extraction from any image
Handles printed and handwritten text
Natural scene text recognition
Structured output

What are GOT-OCR V2 (Text Extract)'s strengths?

Good accuracy on diverse text types
Handles natural scenes
Structured output format

What are GOT-OCR V2 (Text Extract)'s limitations?

$0.05 per extraction
Very messy handwriting may fail
Not a document parser — text extraction only

What is GOT-OCR V2 (Text Extract) best for?

Text extraction from photos Document digitization Sign and label reading Scene text capture

How much does GOT-OCR V2 (Text Extract) cost?

Metric
FairStack
Details
Price per generation
$0.060
Includes 20% margin
Subscription
None
Pay per generation only

How does GOT-OCR V2 (Text Extract) perform across capabilities?

GOT-OCR V2 — text extraction from images, not generation. Scores reflect text recognition ability.

photorealism
30%
layout precision
65%
text rendering
92%
identity consistency
20%
style adherence
30%
editing
40%
fine detail
55%
multi subject
35%
lighting complexity
25%
storytelling
20%

How do I use the GOT-OCR V2 (Text Extract) API?

curl
curl -X POST https://api.fairstack.ai/v1/generations/image \
  -H "Authorization: Bearer $FAIRSTACK_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "got-ocr-v2",
    "prompt": "Your prompt here"
  }'
Python
import requests

response = requests.post(
    "https://api.fairstack.ai/v1/generations/image",
    headers={
        "Authorization": f"Bearer {FAIRSTACK_API_KEY}",
        "Content-Type": "application/json",
    },
    json={
        "model": "got-ocr-v2",
        "prompt": "Your prompt here",
    },
)

result = response.json()
print(result["url"])
Node.js
const response = await fetch(
  "https://api.fairstack.ai/v1/generations/image",
  {
    method: "POST",
    headers: {
      Authorization: `Bearer ${process.env.FAIRSTACK_API_KEY}`,
      "Content-Type": "application/json",
    },
    body: JSON.stringify({
      model: "got-ocr-v2",
      prompt: "Your prompt here",
    }),
  }
);

const result = await response.json();
console.log(result.url);

What parameters does GOT-OCR V2 (Text Extract) support?

Parameter
Type
Default
Details
seed
integer (optional)
guidance_scale
float (optional)
num_inference_steps
integer (optional)

Frequently Asked Questions

How much does GOT-OCR V2 (Text Extract) cost?

GOT-OCR V2 (Text Extract) costs $0.060/image on FairStack as of 2026-05-13. This price includes FairStack's transparent 20% margin on infrastructure cost. No subscription or monthly fee — you pay per generation only. Minimum deposit is $1.

What is GOT-OCR V2 (Text Extract) and what is it best for?

GOT-OCR V2 (General OCR Theory V2) is an AI-powered text extraction model that reads text from any image at $0.05 per extraction. It handles printed text, handwriting, documents, signs, labels, and text in natural scenes, returning structured text output from visual input. The model goes beyond traditional OCR by understanding text in context, handling varied fonts, sizes, orientations, and lighting conditions. It processes documents, photographs of signs, product labels, handwritten notes, and text embedded in complex scenes. Output is returned as structured text suitable for downstream processing. Compared to traditional OCR engines which work best on clean, high-contrast document scans, GOT-OCR V2 handles the messier reality of text in natural photographs, angled perspectives, and varied lighting. Against multimodal language models used for text extraction, GOT-OCR V2 is specifically optimized for OCR accuracy rather than general image understanding. Best suited for extracting text from photographs, digitizing documents from camera captures, reading signs and labels in scene photos, and any workflow requiring accurate text extraction from images in varied conditions. Available on FairStack at infrastructure cost plus a 20% platform fee. GOT-OCR V2 (Text Extract) is best for Text extraction from photos, Document digitization, Sign and label reading. Available via FairStack's REST API with curl, Python, and Node.js SDKs.

Does GOT-OCR V2 (Text Extract) have an API?

Yes. GOT-OCR V2 (Text Extract) is available via FairStack's REST API at api.fairstack.ai. Send a POST request to /v1/generations/image with your API key and prompt. Works with curl, Python requests, Node.js fetch, and any HTTP client. No SDK installation required.

How does GOT-OCR V2 (Text Extract) compare to other image models?

GOT-OCR V2 (Text Extract) excels at Text extraction from photos, Document digitization, Sign and label reading. It is a utility model priced at $0.060/image on FairStack. Key strengths: Good accuracy on diverse text types, Handles natural scenes. Compare all image models at fairstack.ai/models.

What makes GOT-OCR V2 (Text Extract) stand out from other image generators?

GOT-OCR V2 (Text Extract) stands out with good accuracy on diverse text types and handles natural scenes. Generation typically completes in under 5 seconds.

What are the known limitations of GOT-OCR V2 (Text Extract)?

Key limitations include: $0.05 per extraction; very messy handwriting may fail; not a document parser — text extraction only. FairStack documents these transparently so you can choose the right model for your workflow.

How fast is GOT-OCR V2 (Text Extract)?

GOT-OCR V2 (Text Extract) typically completes in under 5 seconds. This makes it suitable for real-time applications, interactive workflows, and high-volume batch processing.

What features does GOT-OCR V2 (Text Extract) support?

GOT-OCR V2 (Text Extract) offers: text extraction from any image; handles printed and handwritten text; natural scene text recognition; structured output. All capabilities are accessible through both the FairStack web interface and REST API.

Start using GOT-OCR V2 (Text Extract) today

$0.060/image. Full API access. No subscription.

Start Creating