Verify a model
For when you pay for one model and suspect you get another.
Model Fingerprint Lab
Every model is bad at picking random numbers in its own way. Send it three short number prompts, paste the replies, and the lab ranks the closest matches in a reference bank. Run it against the official API and against a reseller or relay that claims the same model, then compare. Only the numbers leave your browser, and nothing is stored.
Fingerprint a modelWrite like yourself
For drafts that came out of a chatbot and sound like it.
AI Humanizer
Paste a draft. It marks the phrases that read as machine-made, rewrites them without changing what you said, and lists where a detail only you know would help. Pick work email, cover letter or LinkedIn post and the rewrite follows that format. Checks and rewrites use an AI model; 5 free rewrites a day.
Humanize textCheck before you ship
Find out if a file will work before anyone else does.
llms.txt Checker
Paste a URL or the file. You get 10 checks against the llmstxt.org spec, a score out of 10, and a Markdown report to paste into an issue.
Check a fileClaude Skill Validator
Paste a SKILL.md or upload the skill folder as a .zip. It checks the frontmatter, the name rules, and the description Claude reads to decide when your skill runs.
Validate a skillversion: fails the upload. Put it under metadata.Generate
Start from a working file instead of a blank page.
llms.txt Generator
Fill in your site name, a one-line summary and your key pages. It writes an llms.txt that follows the spec, ready to save at your site root.
Generate llms.txtDecisions API Request Builder
Choose yes/no, pick-one or score, fill in the fields, and copy a request body for OpenAI's POST /v1/decisions. Then slide the estimator to see the monthly cost.
Guides & research
- LLM API pricing comparison · 17 models per 1M tokens: input, cached, output, cost calculatortool: Cost Calculator
- Which model is behind an API? · six ways to check an API reseller or proxy, weakest to strongesttool: Fingerprint Lab
- Did OpenRouter serve the model you asked for? · provider routing, quantized endpoints, fallbacks: see it, pin it, verify ittool: Fingerprint Lab
- Model fingerprints, explained · why LLMs can't pick random numbers, with referencestool: Fingerprint Lab
- llms.txt State 2026 · adoption and errors across the Tranco Top 500, with CSVtool: llms.txt Checker
- OpenAI Decisions API, explained · question types, pricing, when to use ittool: Request Builder
- GPT-6 Luna pricing, explained · $0.10 per 1M input: cost calculator, 272K rule, caching mathtool: Cost Calculator
- textGrain, explained · OpenAI's invisible text watermark and what it can proveguide
Model notes
- MiniMax M3.1 Flash, explained · MiniMax's agent model (ex-Space Bunny): $0.15/$0.60 per 1M tokens, $0.22 per tasktool: Cost Calculator
- Claude Fable 5.2, explained · Anthropic’s flagship model: $8/$40 pricing, fast mode, AA Index 64.6, access checkertool: Cost Calculator
- GPT-6 Cyber, explained · OpenAI's cybersecurity model: gated Daybreak Red access, $20/$100 pricing, ExploitGym 48.5%tool: Access Checker
- Mistral Large 4, explained · Mistral's 1T open-weight model: GPU run checker, $0.70/$2.10 pricing, labeled benchmarkstool: GPU Checker
- LongCat 2.5, explained · Meituan's 1.6T agent model: discounted $0.30/$1.20 pricing, labeled benchmarks, weights not releasedtool: Cost Calculator
- Tencent Hy4, explained · Tencent's flagship model: vision and computer use, $0.834/$2.501 pricing, weights promised not publishedtool: Cost Calculator
- Inkling 2 Small, explained · Thinking Machines Lab's 594B model: AA Index 31, $0.30/$1.00 pricing, weights promised next weektool: Access Checker
- FLUX 3 Image Klein, explained · BFL's 5.6B open-weight image model: VRAM checker, pricing, licensetool: VRAM Checker
- FLUX 3 Max, explained · fal's AI video model (Oct 19, 2026): 12-second clips, price calculatortool: Cost Calculator
- Pele Mermaid renderer, explained · Obsidian's open-source Mermaid-to-SVG renderer: live speed test vs Mermaid.js, installtool: Render Test
Developer tools
- UUID v7 Generator · bulk time-ordered IDs, up to 10,000 at once, timestamp decodertool: Bulk Generator
- ULID Generator · 26-character sortable IDs: batch, monotonic and fixed-time modes, decoder, list order checktool: ULID Generator
- JWT Decoder · read any token in your browser, expiry check, HS signature checktool: Decoder
- Robots.txt Generator · build valid crawler rules, AI crawler presets, path testertool: Generator + Tester
- Markdown Table Generator · grid editor, CSV and JSON import, per-column alignment, HTML exporttool: Table Generator
- Chmod Calculator · octal, symbolic and ls forms, umask defaults, safe recursive commandstool: Calculator
- Cron Expression Generator · build five-field schedules, plain English explanations, next 10 runs, Quartz and AWS formstool: Schedule Builder
- Unix Timestamp Converter · epoch to date and back: seconds to nanoseconds, any timezone, batch mode for log linestool: Timestamp Converter
- SQL Formatter · messy SQL in, readable SQL out: dialect, keyword case, indent, minify, structural checkstool: SQL Formatter
- JSON Formatter · messy JSON in, readable JSON out: 2 or 4 spaces, tab, minify, validation with line numbers, JSONPath, YAML and CSVtool: JSON Formatter
- YAML Formatter · messy YAML in, readable YAML out: 2 or 4 spaces, validation with line numbers, the on: boolean trap, YAML to JSONtool: YAML Formatter
- TOML Formatter · messy TOML in, readable TOML out: 2 or 4 spaces, validation with line numbers, TOML to JSONtool: TOML Formatter
- XML Formatter · messy XML in, readable XML out: indent, minify, validation with line numbers, XML to JSONtool: XML Formatter
- HTML Formatter · messy HTML in, readable HTML out: 2 or 4 spaces, tab, minify, structure checks, tag outlinetool: HTML Formatter
- JavaScript Formatter · messy JS in, readable JS out: 2 or 4 spaces, tab, minify, syntax check with line numbers, ASI warningstool: JavaScript Formatter
- LLM API Tester · one prompt to any OpenAI-compatible API or relay: TTFT, tokens/s, returned model, up to 3 side by sidetool: API Tester
- Document to Markdown · PDF, Word, HTML or pasted rich text to clean Markdown for LLMs, in your browsertool: Converter
- Team Name Generator · cool and funny team names for sports, gaming, work, school or trivia: 7 team types, 3 tones, your own word, favorites shortlisttool: Team Name Generator
- 镜像站是不是真 GPT、Claude? · 没有 API Key:把指纹提示词粘进网页版,再把回复粘回来测tool: 模型指纹