Development x402 offerings

MIME type for .xml files: application/xml. Returns the Content-Type to send, the category, whether browsers render it inline, whether it is compressible, common magic bytes and related extensions. Set headers and validate uploads for .xml correctly. $0.01 per call.

MIME type for .xsl files: application/xslt+xml. Returns the Content-Type to send, the category, whether browsers render it inline, whether it is compressible, common magic bytes and related extensions. Set headers and validate uploads for .xsl correctly. $0.01 per call.

MIME type for .xz files: application/x-xz. Returns the Content-Type to send, the category, whether browsers render it inline, whether it is compressible, common magic bytes and related extensions. Set headers and validate uploads for .xz correctly. $0.01 per call.

MIME type for .yaml files: application/yaml. Returns the Content-Type to send, the category, whether browsers render it inline, whether it is compressible, common magic bytes and related extensions. Set headers and validate uploads for .yaml correctly. $0.01 per call.

MIME type for .yml files: application/yaml. Returns the Content-Type to send, the category, whether browsers render it inline, whether it is compressible, common magic bytes and related extensions. Set headers and validate uploads for .yml correctly. $0.01 per call.

MIME type for .zip files: application/zip. Returns the Content-Type to send, the category, whether browsers render it inline, whether it is compressible, common magic bytes and related extensions. Set headers and validate uploads for .zip correctly. $0.01 per call.

MIME type for .zst files: application/zstd. Returns the Content-Type to send, the category, whether browsers render it inline, whether it is compressible, common magic bytes and related extensions. Set headers and validate uploads for .zst correctly. $0.01 per call.

Checks XML tag nesting and reports mismatched or unclosed tags 🆓 5 free trial calls per signed wallet

Sorts an array of numeric values ascending with a quicksort partition scan 🆓 5 free trial calls per signed wallet

Converts an integer value into its Gray code by XORing it with itself shifted right one bit 🆓 5 free trial calls per signed wallet

Runs a full technical SEO audit on a single web page. Verify redirects, headers, meta tags, indexability, JSON-LD, missing or conflicting canonicals and more. No black-box scoring; just deterministic, composable signal you can act on. Every threshold is documented at https://minifetch.com/skills/seo-page-audit/SKILL.md Obeys robots.txt. Supports GET & POST

Chat completions via Telnyx Inference (MiniMaxAI/MiniMax-M3-MXFP8). OpenAI-compatible. $0.011974 USDC per call.

Generate deterministic fake test rows from a field->type spec plus a seed (names, emails, phones, addresses, dates, ints, bools). Output JSON, CSV, or NDJSON. Same seed always yields the same data -- reproducible fixtures.

Deterministic synthetic JSON or WireMock fixtures for ten commercial and four government APIs. Selected operations and realistic success/error scenarios, with source provenance.

Compare two to five models side by side. Give a comma separated list of names or aliases and get each model normalized on price, context, capabilities, knowledge cutoff and coding benchmark, plus flags for the cheapest, the best benchmark and the largest context. Fused from open keyless catalogs with a citation on every model.

Look up one normalized model record by name or short alias such as sonnet or 4o. Returns per-million input and output prices, context and output limits, capability tags, modalities, knowledge cutoff, release date, provider and coding benchmark, each fused from open keyless catalogs LiteLLM, models dev and Aider with a source citation. Unknown names return found false, never an error.

Pick the cheapest LLM that passes your task and constraints. Give a task class and optional constraints such as minimum context, required tool-use, vision or reasoning, maximum input and output price per million tokens, a minimum coding benchmark and a provider filter, and get a ranked cheapest-first list of models that pass, plus a recommended pick and a deterministic rationale. Fused from open keyless catalogs LiteLLM, models dev and Aider with a citation on every model.

Two checks in one. First the arguments are validated against the tool input schema and every violation is reported with its path and a sentence saying what to change. Second, values that satisfy the schema but look wrong are flagged: an unset required field filled with a placeholder like "string" or "TODO", a number at a suspicious order of magnitude, an address that fails its checksum shape, a destructive flag set to true, an empty string where content was expected.

A comparison table of language models: input, output and cache prices per million tokens, context window, maximum output length, batch discount and a short note on what each is suited to. Filter by vendor, by a maximum price, by the context window you need, or by capability tag. Every row carries the date its prices were last checked, so a stale figure is visible rather than silently wrong.

Single-model capability lookup: context window size, max output tokens, and vision/audio/function-calling/reasoning support for one AI model by id. Answers 'can this model handle my task?' in one $0.003 call.

Cheapest tool-use LLM leaderboard: the 50 lowest-cost AI models that support function calling / tool use, ranked by token price across 70+ providers. Input, output and cache USD per 1M tokens with context window and modality flags joined in. The cheapest way to pick a model for an agent loop that needs reliable structured tool calls. Refreshed hourly.

MV3 Declared Access Diff 1.0.0. An offline Python tool for Chrome extension maintainers reviewing a release. Compare required and optional API permissions, host patterns and complete static First approved purchase: 0.01 USDC total where maker terms permit; later 1 USDC plus tax. Stored ZIP download; commercial use, no redistribution. Verified by Speedbot for this version. Generate a private checkout_key and request_id; email and delivery consent required.

Multilingual text embeddings (384-dim) served in-house, no OpenAI dependency, no API key. NetIntel's cheapest embeddings at $0.001/call, batches up to 256 texts. Supports query/passage input types for retrieval (e5). Pairs with /text/chunk for a full chunk→embed RAG pipeline on one provider.

Repair malformed JSON into valid JSON — fixes code fences, trailing commas, single quotes, unquoted keys, bad escapes, duplicate keys, truncation, and JSON buried in prose. A deterministic tokenizer runs first (no LLM cost), with an optional Haiku fallback, plus optional schema validation and type coercion — so agents can rescue broken model output or dirty data in one call.