Upload any image. Get every readable word back as plain text. Tesseract OCR. $0.01 per image. Instant results.
# Extract text from a screenshot
curl -X POST https://api.image2text.dev/api/v1/extract \
-H "X-API-Key: i2t_live_YOUR_KEY" \
-F "file=@screenshot.jpg"
POST /api/v1/auth/register with your email. You'll get a 6-digit verification code.
POST /api/v1/auth/verify with the code, then POST /api/v1/auth/api-key. You get 5 free credits.
POST /api/v1/extract with an image file. Supports JPEG, PNG, WebP, TIFF, BMP. Results are instant.
No async polling. Upload an image, get text back in the same response. Typical response time under 500ms.
$0.01 per image analyzed. If extraction fails, the credit is automatically refunded. You only pay for text we return.
JPEG, PNG, WebP, TIFF, BMP. Up to 20MB per image. Optimized for screenshots with rendered text.
Every readable word extracted and returned as plain text. Character count and line count included. No markup, no interpretation.
Simple. No tiers. No subscriptions. Buy credits, use them whenever.
$0.01 each
$0.01 each
$0.01 each
5 free credits on signup. Failed extractions are automatically refunded.
| Method | Endpoint | Cost | Description |
|---|---|---|---|
| POST | /api/v1/extract | 1 credit | Extract text from an image |
| Method | Endpoint | Cost | Description |
|---|---|---|---|
| POST | /api/v1/auth/register | Free | Create account |
| POST | /api/v1/auth/verify | Free | Verify email |
| POST | /api/v1/auth/api-key | Free | Generate API key |
| Method | Endpoint | Cost | Description |
|---|---|---|---|
| GET | /api/v1/account | Free | View balance and usage |
| GET | /api/v1/credits/packs | Free | List credit packs |
| POST | /api/v1/credits/purchase | Free | Buy credits via Stripe |
| Method | Endpoint | Cost | Description |
|---|---|---|---|
| GET | /api/v1/health | Free | Health check and Tesseract status |
Full API reference: llms-full.txt · OpenAPI spec
This site is designed for machine consumption. AI agents can discover and integrate with this API using these files: