OCR: extract and recognize text from images via chat completions
1 operation12 models3 revisions
Changes
Full historySource
View schema- Spec
- OpenAPI 3.0.3
- Document
- raw.githubusercontent.com, JSON, 23 KB
- Commit
- 58b05e9 Update API reference for voice, OCR, video, image, chat, vision, docs.json, and favicon.svg
- Published
- Apr 13, 2026, 18:29 UTC
- Retrieved
- Nov 6, 2026, 22:05 UTC
- Digest
- cc5d51dc7845
For agents
Every page here has a markdown twin. The overview is one fetch; the llms.txt lists every operation with a link to its own markdown.
curl https://skmtc.dev/qubrid/apis/qubrid-ocr-api.mdcurl https://skmtc.dev/qubrid/apis/qubrid-ocr-api/llms.txt