An RChilli alternative for AI agents
Choose VerbatimCV when an AI agent reads the result and needs each value traceable to the CV, with prompt injection already removed. Choose RChilli for a very wide field set (200+), more input formats and high-volume production use. Facts below come from RChilli's own pages, read on 17 November 2026.
| VerbatimCV | RChilli | |
|---|---|---|
| Free start | 50 parses a month, no card | 100 free credits |
| Paid entry | Paid plans not yet published | Standard plan from $75 |
| Fields | A focused, versioned schema built around agent decisions | "200+ data fields" |
| Languages | Text-layer CVs in most languages; OCR for 9 scripts | "40+ languages" |
| Inputs | PDF, DOCX (scans OCR'd) | DOC, DOCX, PDF, RTF, TXT, ODT, HTML and more |
| Quote for each extracted preference | Yes (evidence) | Not mentioned |
| Hidden text and prompt-injection handling | Removed and reported | Not mentioned |
| MCP server | Yes | Not mentioned |
| Stores parsed data | Not by VerbatimCV; Anthropic, which runs the extraction model, deletes API data within 30 days | "never stores the data" |
Where RChilli is stronger
Breadth of fields, input formats, a claimed 4.1 billion documents parsed a year, and redaction features.
Sources
- RChilli pricing (read 2026-11-17)
- RChilli resume parser (read 2026-11-17)
"Not mentioned" means not stated on those pages on that date; the feature may exist elsewhere.
Try it
Get a free API key (50 parses a month, no card), then:
curl https://api.verbatimcv.com/v1/parse \
-H "Authorization: Bearer $VERBATIMCV_API_KEY" \
-F file=@cv.pdf
Agents can use the parse_resume tool instead: uvx verbatimcv-mcp. See the
quickstart for Python, JavaScript and MCP setup.