Scale with OCRWell.
Start on the generous free tier — 200 OCR pages and 50 extraction pages every month, no credit card, no overage surprises. Upgrade when you outgrow it.
For weekend experiments and proof-of-concepts.
- 200 OCR pages / month
- 50 Extraction pages / month
- Hard cap — no overage
- Community support
Indie builders shipping to first customers.
- 15,000 OCR pages / month
- 750 Extraction pages / month
- OCR overage: $0.004 / page
- Extraction overage: $0.05 / page
- Email support
Growing teams with predictable volume.
- 50,000 OCR pages / month
- 2,500 Extraction pages / month
- OCR overage: $0.003 / page
- Extraction overage: $0.04 / page
- Priority support
- 99.9% uptime SLA
Mission-critical document pipelines.
- 200,000 OCR pages / month
- 10,000 Extraction pages / month
- OCR overage: $0.002 / page
- Extraction overage: $0.025 / page
High-throughput deployments with dedicated solution architect.
- 750,000 OCR pages / month
- 40,000 Extraction pages / month
- OCR overage: $0.0015 / page
- Extraction overage: $0.02 / page
- Dedicated solution architect
- Integration pipeline review
Custom throughput and white-glove SLA.
- Custom page limits
- Negotiated overage rates
- White-glove SLA
- Custom legal terms
Save with OCRWell
Using our dedicated OCR processing leads to better accuracy and big savings vs using in-built image processing.
| Per A4 page | OCRWell Scale + Opus 4.7 text | Raw 200 DPI image → Opus 4.7 |
|---|---|---|
| OCR cost | $0.0008 ($600 ÷ 750,000 pages) | — |
| Input to Claude | ~700 text tokens | ~4,784 image tokens |
| Opus 4.7 input ($5 / MTok) | $0.0035 | $0.0239 |
| Total per page | $0.0043 | $0.0239 |
Opus 4.7 API pricing from Anthropic; image token count uses the
published width × height ÷ 750 formula, capped at Opus 4.7's
4,784-token native resolution limit. Output tokens are identical in both
paths and excluded. Scale Plan per-page OCR cost assumes 100%
utilisation of the 750,000 included pages and no overage.
Questions, answered precisely.
How are overages handled?
Overages are billed at the fractional per-page rate on your plan and applied to the next billing cycle. Higher tiers carry better rates automatically — you never need to call support to renegotiate. The Free tier is a hard cap: once you hit the limit, requests return 429 until the next month.
What security and compliance do you support?
Data is encrypted at rest with AWS KMS (AES-256), with keys managed in a FIPS 140-2 validated HSM, and in transit with TLS 1.3. Uploaded files are deleted immediately after processing; results are deleted five minutes after first retrieval. The full set of controls — access, network, logging, vulnerability disclosure — is documented on the security page.
How long is my data retained?
Uploaded documents are stored only for the duration of processing and are deleted as soon as their result is produced. Results are deleted 300 seconds after they are retrieved. As a safeguard, any document whose result is never retrieved — or on which processing errors occur — is deleted automatically after 24 hours.
Can I change plans mid-cycle?
Yes. Upgrades take effect immediately and are prorated against your current cycle. Downgrades apply at the end of the cycle. Annual credits are prorated back to the card on file.
Will my documents be used to train AI models?
No. We never retain your data for any reason, including model training. All documents are deleted automatically after processing. See our privacy policy for the full commitments.
What is the difference between OCR and Extraction?
OCR is reading — turning pixels into characters. Extraction is understanding — mapping those characters into a typed schema (invoices, contracts, clinical notes) using language models with document context.