Documents & files

Scanned PDF Page OCR: Render and OCR one selected page of a supplied PDF locally, using English, French, German or Spanish. Up to 600 KB and 50 total pages. Returns page text and the rendered PNG. Encrypted or malformed PDFs can be rejected; OCR can be wrong. 0.01 USDC includes one bounded document-data report.

Blender: Convert Stl: Export triangulated STL geometry for downstream fabrication workflows; printability is not guaranteed. Accepts mesh JSON, small GLB or OBJ; without input uses an explicitly labelled demo mesh. Runs locally in Blender. Bounded small-model processing, normally under 60 seconds; a busy worker returns an error before payment settlement.

CRM JSON to CSV converter: Convert an array of JSON objects into CSV text. Tailored for crm workflows.

CRM CSV to JSON converter: Convert simple comma-separated rows into JSON records. Tailored for crm workflows.

Tile coordinate converter: Convert world coordinates into tile coordinates for a grid.

Events Time-zone converter: Convert a timestamp between IANA time zones. Tailored for events workflows.

Classroom Time-zone converter: Convert a timestamp between IANA time zones. Tailored for classroom workflows.

File type and MIME/media type inspector — identify bounded content by magic bytes and return SHA-256, size, and extension consistency without unpacking, malware scanning, or safety claims.

+2 more from Artifact Inspector

Create a temporary public HTTPS download URL for an artifact generated by an agent or tool when the sending and receiving systems do not share storage. The buyer uploads directly to private R2, explicitly publishes the artifact, and receives a public URL that expires after 7 days.

Resize, crop, compress, convert (WebP/AVIF/JPEG/PNG/GIF), optimize, and transform images from a natural-language instruction. Remove backgrounds, make thumbnails, srcset variants, icon sets, watermarks, GIF edits, Shopify-ready product images. Up to 12 named variants per request as a ZIP, or base64 data URI output. Every constraint is verified against the real output bytes before payment settles; failures are never charged.

Convert between 30+ currencies at the European Central Bank's daily reference rate, for today or any past date. Returns the converted amount, the per-unit rate and the date the rate is actually from — the ECB publishes on business days only, so a weekend date answers with the previous business day and says so instead of pretending. Reference rates for accounting and reporting, not tradable quotes.

Access and edit your Craft documents.

Send Markdown (or HTML) and get back a URL that renders as a real page — headings, tables, code blocks, mobile-readable, no scripts and no external requests. The other half of an agent's output problem: file-slot is for bytes it will fetch back, this is for the report somebody has to read. Retention 1-30 days. Published on the storage origin, never on 402.com.tr.

Parse a bank CSV (comma/semicolon/tab, quoted fields) and map common headers (date/amount/debit/credit/balance/description, TR aliases) into one schema. Up to 500 rows. Best-effort.

Heuristic extraction from invoice/receipt text: totals, amounts, VAT hints, IBANs, dates, emails, invoice numbers. Not OCR — convert a scan to text first, then send it here.

Convert an amount between wei, kwei, mwei, gwei, szabo, finney and ether — or between any token decimals (pass a number like 6 for USDC). Integer-exact, no precision loss. Pass amount, from, to. Pure compute, sub-cent — the unit-conversion commodity agents call constantly when building transactions. Not financial advice.

Parse a DKIM public-key DNS TXT record ("v=DKIM1; k=rsa; p=…") into its key type, public key, hash algorithms, service types and flags. An empty `p` is reported as a revoked key. A missing `p` tag is a clean 400.

Parse a DMARC TXT record ("v=DMARC1; p=…") into its policy, alignment, sampling and reporting tags. Missing or invalid policy/alignment/pct values are clean 400s.

Parse an SPF TXT record ("v=spf1 …") into its qualified mechanisms and modifiers. Records that do not start with v=spf1 or use unknown mechanisms are clean 400s.

Break a braille string into its cells and the raised-dot numbers (1–8) of each cell.

Parse dice notation such as "3d6+2", "4d6kh3" (keep highest 3) or "2d20dl1" (drop lowest 1) into structured terms. Malformed notation is a clean 400.

Given a reaction and a known amount (moles or grams) of one species, compute the amount of a target species. The equation is balanced automatically.

Convert a decimal string to an exact reduced fraction. For a repeating decimal, set repeat to the number of trailing fractional digits that repeat (e.g. value='0.1666', repeat=1 → 1/6; value='0.3', repeat=1 → 1/3). A non-numeric value is a clean 400.

Parse a document (in any format) and re-emit it in the RFC 8785 JSON Canonicalization Scheme form — sorted keys, canonical number/string formatting — plus the SHA-256 of the canonical bytes for stable hashing, signing and dedup.

Parse a document (json, json5, jsonc, yaml, xml, csv, tsv, toml, ndjson, ini, env, properties, plist or querystring) and validate it against a JSON Schema. Returns whether it is valid and a list of precise, path-tagged errors. Malformed input or an invalid schema is rejected before payment.

Convert between the shapes data actually arrives in: CSV or TSV to JSON, JSON to CSV or TSV, CSV to a Markdown table, Markdown to HTML. Proper RFC 4180 parsing — quoted fields, embedded commas and newlines, doubled quotes — so a spreadsheet exported by a human does not silently come apart. Numbers and booleans get real types (turn it off with typed=false). No model call and no upstream: local parsing only.

Time-zone conversion on the IANA database: convert a time between zones with offsets, abbreviations and DST flags, describe zones at an instant, or compute the shared business-hours window across several zones for meeting scheduling.

Document Retrieval Evidence Pack: Compare semantic embedding similarity with cross-encoder relevance, then combine their ranks for up to 5 passages. Returns source indices, both scores and a reproducible evidence report. 0.01 USDC includes up to 5 passages.

Japanese address parser and component extraction. Keywords: Japanese address parser, address components, chome, block, lot, house, 丁目, 番地, 号. Parse a Japanese address into components without returning postal validation or geocoding; local postal prefix evidence may safely recover a unique town or report ambiguity. / 日本住所を構造化します。郵便番号の検証結果・ジオコーディングは返しませんが、町域の一意な前方一致による補完・曖昧性判定のためローカル郵便データを内部参照する場合があります。

Automated data-pipeline integrity gate for ETL regression detection and breaking CSV/schema changes. Compares profiles, data-quality deltas, and data contracts, then returns an evidence-backed PASS/WARN/FAIL pipeline action.