Razi Tools

Previous value: -"The page to read, e.g. https://stripe.com/pricing. A bare domain is accepted and assumed to be https."New value: +"The page to read, e.g. https://stripe.com/pricing. A bare domain is accepted and assumed to be https. It is the cache key verbatim, so two spellings of the same page are fetched twice."

Previous value: -"Copy the top candidates to razi.pro's CDN and expose them as `rehostedUrl` (default true). Prefer these for downloading or embedding: many origins block hotlinking or omit CORS headers, so the original URL can fail in a browser. Set false to skip the copy and get origin URLs only."New value: +"Copy the top 3 fetchable candidates to razi.pro's CDN and expose them as `rehostedUrl` (default true). Prefer these for downloading or embedding: many origins block hotlinking or omit CORS headers, so the original URL can fail in a browser. Set false to skip the copy and get origin URLs only. A copy that fails is dropped silently, leaving that candidate with its origin URL only, and the two settings are cached separately."

Previous value: -"The website to inspect, e.g. https://stripe.com. A bare domain is accepted and assumed to be https."New value: +"The website to inspect, e.g. https://stripe.com. A bare domain is accepted and assumed to be https. Up to 3 redirects are followed; more is refused with 400."

Previous value: -"Render with prefers-color-scheme: dark. Has no effect on sites that do not implement a dark theme."New value: +"Render with prefers-color-scheme: dark. Default false. Has no effect on sites that do not implement a dark theme."

Previous value: -"Extra wait after load, in milliseconds (max 5000). Use for pages with entrance animations or slow client-side rendering."New value: +"Extra wait after load, in milliseconds. Default 0, clamped to 0-5000. Use for pages with entrance animations or slow client-side rendering; it comes out of the same 50-second render budget."

Previous value: -"Image format (default webp)"New value: +"Image format. Default webp; an unrecognised value also falls back to webp."

Previous value: -"Capture the entire scrollable page rather than just the viewport. Pages taller than 12000px are truncated at 12000px, which is a browser encoding limit, so a very long article returns only its top portion."New value: +"Capture the entire scrollable page rather than just the viewport. Default false. Pages taller than 12000px are truncated at 12000px, which is a browser encoding limit, so a very long article returns only its top portion."

Previous value: -"Viewport height in pixels (200-4320, default 800). Ignored when fullPage is true."New value: +"Viewport height in pixels. Default 800; values outside 200-4320 are clamped. Ignored when fullPage is true, where the returned height is null."

Previous value: -"The page to capture. Must be publicly reachable over http(s)."New value: +"The page to capture. Must be publicly reachable over http or https; the scheme is required. Part of the cache key, so two spellings of the same page render twice."

Previous value: -"Viewport width in pixels (200-3840, default 1280)"New value: +"Viewport width in pixels. Default 1280; values outside 200-3840 are clamped into that range and fractions are truncated."

Previous value: -"Vanity code to use as the last path segment, e.g. 'launch' for razi.pro/launch. 3-32 characters, letters, digits, hyphen and underscore only. Fails with 409 if already taken and 400 if it collides with a reserved site path such as 'api', 'blog' or 'tools'. Omit to get a random 8-character code."New value: +"Vanity code to use as the last path segment, e.g. 'launch' for razi.pro/launch. 3-32 characters, letters, digits, hyphen and underscore only. Fails with 409 if already taken and 400 if it is malformed or collides with a reserved site path such as 'api', 'blog' or 'tools'. Omit to get a random 8-character code drawn from an alphabet with no 0, O, 1 or l."

Previous value: -"The absolute destination URL to redirect to, including the scheme. Only http:// and https:// are accepted; anything else is rejected with 400."New value: +"The absolute destination URL to redirect to, including the scheme. Only http:// and https:// are accepted; anything that is not an absolute URL in one of those schemes is rejected with 400. It is normalised by the URL parser before being stored, so the redirect target may differ cosmetically from what you sent."

Previous value: -"Calculation type"New value: +"Which calculation to run. 'of' = value1 percent OF value2. 'increase' = value1 raised BY value2 percent. 'decrease' = value1 reduced BY value2 percent. 'change' = the percentage change going FROM value1 TO value2, which errors when value1 is 0. Required; any other value is rejected."

Previous value: -"First value"New value: +"For 'of', the percentage itself (25 means 25%). For 'increase' and 'decrease', the base amount being adjusted. For 'change', the original value. Must be a finite number."

Previous value: -"Second value"New value: +"For 'of', the amount the percentage is taken from. For 'increase' and 'decrease', the percentage to apply (10 means 10%). For 'change', the new value. Must be a finite number."

Previous value: -"First text"New value: +"The baseline text, reported as `before` in each change."

Previous value: -"Second text"New value: +"The revised text, reported as `after` in each change."

Previous value: -"Output format"New value: +"Output container/codec. Default webp; an unrecognised value also falls back to webp. Transparency survives in webp, png and avif but not jpeg."

Previous value: -"Convert image to grayscale"New value: +"Drop colour before encoding. Default false."

Previous value: -"Target height in pixels (optional)"New value: +"Target height in pixels. Give only one of width/height to scale the other proportionally. Omit both to keep the original dimensions."

Previous value: -"Maintain aspect ratio when resizing. Set false for square crop."New value: +"Only has an effect when BOTH width and height are given. Default false, which centre-crops the image to fill the box exactly. Set true to fit the whole image inside the box instead, so the result may be smaller than the box in one dimension."

Previous value: -"Quality from 0.1 to 1.0, default 0.9"New value: +"Encoder quality as a fraction from 0.1 to 1.0, scaled to the encoder's 0-100 range. Default 0.9. Higher means larger and closer to the original."

Previous value: -"Target width in pixels (optional)"New value: +"Target width in pixels. Give only one of width/height to scale the other proportionally. Omit both to keep the original dimensions. Enlarging is allowed."

Previous value: -"Base64 encoded text"New value: +"Standard Base64 text. Surrounding whitespace and missing '=' padding are tolerated; the URL-safe alphabet (- and _) is not."

Previous value: -"JWT token to decode"New value: +"The full JWT: three base64url segments separated by dots (header.payload.signature). Surrounding whitespace is trimmed; a 'Bearer ' prefix is not stripped and will fail. Anything without exactly three segments is rejected."

Previous value: -"URL encoded string"New value: +"A percent-encoded string, such as one query-string value taken from a URL. Every %XX sequence must be well formed UTF-8 or the call fails."

Previous value: -"Email purpose or content description"New value: +"What the email needs to say: purpose, recipient context, and any facts to include. A sentence or two is enough. Required and must not be blank."

Previous value: -"Email tone"New value: +"Register of the writing. Default formal. Passed to the model as an instruction, so it shapes wording rather than enforcing a fixed template."

Previous value: -"Text to encode"New value: +"The plain text to encode, interpreted as UTF-8. Must be a string; raw binary cannot be passed through this parameter."

Previous value: -"URL to encode"New value: +"The value to percent-encode, typically one query-string value or path segment. Everything outside A-Z a-z 0-9 - _ . ! ~ * ' ( ) is escaped, including slashes and colons."

Previous value: -"Language of the text (default: eng)"New value: +"ISO 639-2 style code for the language the recogniser should expect: eng English, ara Arabic, chi_sim Simplified Chinese, fra French, deu German, spa Spanish, jpn Japanese, kor Korean. Default eng. One language per call; naming the wrong one badly degrades accuracy."

Previous value: -"Indentation spaces (default 2)"New value: +"Spaces per indent level in `formatted`, 0 to 10. Default 2; a value outside that range or a non-number silently falls back to 2. Use 0 for newlines with no indentation, or read `minified` for no whitespace at all."

Previous value: -"JSON string to format"New value: +"The JSON document as a string. Must be strict JSON — comments and trailing commas are parse errors."

Previous value: -"Number of sections (default 5)"New value: +"How many main sections to plan between the introduction and the conclusion. Default 5; a non-numeric or zero value also falls back to 5."

Previous value: -"Blog topic or keywords"New value: +"The subject of the post, or a comma-free keyword phrase to build it around. The first thing supplied is treated as the primary keyword and the rest as secondary keywords to work in."

Previous value: -"Number of records (default 1)"New value: +"How many records to return. Default 1, clamped to the range 1-100, and truncated to a whole number. Records are always the same sequence, so count 10 is the first 5 of count 5 plus 5 more."

Previous value: -"Data type"New value: +"Shape of each record. 'name', 'email', 'address' and 'phone' each return a plain string; 'user' returns an object with all four fields. Required; any other value is rejected."

Previous value: -"What to avoid in the image (optional)"New value: +"What to keep out of the image, e.g. 'text, watermark, blurry'. Maximum 2,000 characters. Only the Replicate fallback provider honours it, so on the usual path it has no effect."

Previous value: -"Text description of the image to generate"New value: +"What the image should show. Subject, style and composition all help. Required, non-blank, maximum 2,000 characters."

Previous value: -"Error correction level"New value: +"Declared for compatibility but currently ignored — the code is always generated at the library default, level M (about 15% damage tolerance)."

Previous value: -"QR code size in pixels (default 256)"New value: +"Width and height of the output PNG in pixels; the code is always square. Default 300. Only applied when given as a number."

Previous value: -"Text or URL to encode"New value: +"The exact payload to encode. A URL must include its scheme to be actionable when scanned. Very long values force a denser code that is harder to scan."

Previous value: -"Natural language query description"New value: +"What the query should do, in plain language. Include the table and column names you want used, otherwise the model invents plausible ones. Required and must not be blank."

Previous value: -"SQL dialect"New value: +"Intended SQL dialect. Accepted for forward compatibility but NOT currently passed to the model, so the generated SQL is generic and may need adjusting for your engine."

Previous value: -"Number of text blocks to generate (default 1)"New value: +"How many separate blocks to return. Default 1. Large values are bounded in practice by the ~1,500 token output cap."

Previous value: -"Length of text in characters (default 100)"New value: +"Rough size of each block in characters. Default 100. Requested in the prompt, so treat it as a target, not a limit."

Previous value: -"Type of text to generate"New value: +"Flavour of filler to ask for: classic latin lorem ipsum, arbitrary English copy, or standalone sentences. Default lorem. Used as a prompt hint, so it steers the style rather than guaranteeing it."

Previous value: -"Humanization level"New value: +"How far the rewrite may drift from the original voice. 'light' strips AI tells but stays professional, 'medium' (the default, also used for any unrecognised value) turns it conversational with contractions, 'strong' rewrites it casually with short punchy sentences."

Previous value: -"Text to humanize"New value: +"The passage to rewrite. Plain text. Maximum 10,000 characters; longer input is rejected with 413."

Previous value: -"Optional custom short code"New value: +"Vanity code to use as the last path segment, e.g. 'launch' for razi.pro/launch. 3-32 characters, letters, digits, hyphen and underscore only. Fails with 409 if already taken and 400 if it collides with a reserved site path such as 'api', 'blog' or 'tools'. Omit to get a random 8-character code."

Previous value: -"The URL to shorten"New value: +"The absolute destination URL to redirect to, including the scheme. Only http:// and https:// are accepted; anything else is rejected with 400."

Previous value: -"Number of columns (optional, auto-detected if not provided)"New value: +"Number of equal-width columns in the grid. Only takes effect when rows is also given. Omit both rows and cols to have the panels detected automatically."

Previous value: -"Output image format (default: png)"New value: +"Encoding for each extracted panel and its file extension inside the ZIP. Default png, which is lossless; jpeg and webp are written at quality 90."

Previous value: -"Number of rows (optional, auto-detected if not provided)"New value: +"Number of equal-height rows in the grid. Only takes effect when cols is also given; supplying both switches off vision detection and divides the image evenly, ignoring any borders or gaps."

Previous value: -"Array of page ranges (e.g., '1-2', '3-5')"New value: +"Page ranges to extract, 1-based and inclusive, one output file per entry. Use 'first-last' for a span ('1-2', '3-5'), a bare number for one page ('7'), or a comma-separated combination in one entry ('1-3,7'). Spans are clamped to the document length and pages that do not exist are dropped; an entry that selects no page produces no output file."

Previous value: -"Render with prefers-color-scheme: dark"New value: +"Render with prefers-color-scheme: dark. Has no effect on sites that do not implement a dark theme."

Previous value: -"Extra wait after load, in milliseconds (max 5000)"New value: +"Extra wait after load, in milliseconds (max 5000). Use for pages with entrance animations or slow client-side rendering."

Previous value: -"Capture the entire scrollable page rather than just the viewport"New value: +"Capture the entire scrollable page rather than just the viewport. Pages taller than 12000px are truncated at 12000px, which is a browser encoding limit, so a very long article returns only its top portion."

Previous value: -"Viewport height in pixels (200-4320, default 800)"New value: +"Viewport height in pixels (200-4320, default 800). Ignored when fullPage is true."

Previous value: -"The page to capture"New value: +"The page to capture. Must be publicly reachable over http(s)."