# Models.dev vs Zeli Models.dev records 200,451 monthly visits with -3.9% month-over-month growth and Free pricing. Zeli records 56,147 monthly visits with -46.8% growth and Free pricing. | Metric | [Models.dev](https://openaitools.app/tool/models-dev) | [Zeli](https://openaitools.app/tool/zeli) | | :--- | :--- | :--- | | Website URL | https://models.dev | https://zeli.app | | Categories | AI Models, AI API, Open Source AI Models, AI Tools Directory | AI Article Summarizer, AI Papers, AI News, AI Research Papers | | Pricing Model | Free | Free | | Monthly Visits | 200,451 | 56,147 | | MoM Growth Rate | -3.9% | -46.8% | | Primary Market | China | China | | Direct Visits | 136,316 | 39,950 | | Review Score | 4.4 | 4.3 | | Saved Count | 0 | 0 | | Supported Platforms | Website | Website | ## Models.dev Models.dev exists to answer a very practical developer question: which model should I use, and what will it cost? The site organises every entry under a canonical identifier in the form provider/model, so the same model served by several providers can be compared directly rather than guessed at. Columns cover context window, maximum output, whether input and output are supported, reasoning, tool calling, structured output, temperature control, open versus closed weights, price per million tokens, and release and update dates. Because model releases move fast, the catalogue is built to stay current, with sortable and searchable tables that let you scan by lab or provider and filter down to what matters. Entries include both closed flagship models and open-weight alternatives, making it useful for cost planning as well as capability research. The project is open source and free to use, and it is intended to be consumed programmatically. Developers can pull the catalogue into their own tooling through a JSON API or a type-safe SDK, which makes it a practical backend for dashboards, routing logic, or internal cost calculators rather than just a reference page to browse. **Pricing & Plans:** Models.dev is free and open source. It is a reference database, so the prices it lists are the per-million-token rates charged by the model providers themselves, not a fee for using the site. - **Canonical model identifiers:** Every model uses a consistent provider/model format so the same model across providers can be compared directly. - **Specification comparison:** Side-by-side context window, output limit, reasoning, tool calling, structured output, and temperature support. - **Pricing transparency:** Input and output prices per million tokens listed alongside release and update dates. - **Open and closed models:** Covers closed flagship APIs and open-weight models from many labs in one sortable catalogue. - **Developer access:** Consume the catalogue through a JSON API or a type-safe SDK for your own tools and dashboards. **Strengths:** Free and open source with no account required; Consistent canonical identifiers make cross-provider comparison reliable; Covers pricing, limits, and capabilities in one sortable table; Available as a JSON API and type-safe SDK for programmatic use **Limitations:** It is a reference catalogue, not an inference or hosting service; Data quality depends on community and maintainer updates keeping pace with releases; Interface is aimed at developers and offers little guidance for non-technical users [Profile (Markdown)](https://openaitools.app/tool/models-dev.md) ## Zeli Zeli solves the oldest problem with Hacker News: the front page is a list of headlines, and deciding which of the thirty stories deserves your attention means opening all of them. Zeli mirrors that front page, attaches an AI-written summary and a representative key quote to each story, and translates everything into seven languages. The ranking tracks news.ycombinator.com and refreshes every fifteen minutes, so the feed stays current without you checking the orange site directly. The structure is built around permanent, citable pages. Every story gets a URL keyed to its Hacker News item id — zeli.app/story/{id} in English, or zeli.app/{lang}/story/{id} for the other languages — carrying the translated title, the original title, a summary, a key quote and translated highlights from the discussion. Every day also gets a permanent archive of the complete front page, so a digest can be retrieved after that day has scrolled away. Alongside the news feed, Zeli digests HuggingFace's daily AI papers with translated titles and summaries, which makes it useful for keeping up with research as well as with developer chatter. Content languages are English, Chinese, Japanese, Korean, German, Spanish and Russian, with English served at the root and no language prefix. There is no account, no API key and no cost; an RSS feed bundles one item per day instead of flooding your reader, and the site can be installed as a PWA. For programmatic use, Zeli also publishes plain-markdown daily digests, JSON endpoints and an RSS feed aimed at feeds and AI agents. It requires no JavaScript and is served from an edge cache, so it is unusually light to read. **Pricing & Plans:** Free. No account, no API key and no payment; the full site, the RSS feed and the machine-readable digests are all available at no cost. - **AI summaries on every Hacker News story:** Each story carries a short summary generated from the linked article plus a standout key quote, so you can judge relevance before clicking through. - **Seven-language translation:** The whole feed — titles, summaries and top comment highlights — is available in English, Chinese, Japanese, Korean, German, Spanish and Russian. - **Daily front-page archive:** Every day gets a permanent page containing every story that hit the front page, retrievable long after the feed has moved on. - **HuggingFace AI paper digests:** Daily AI papers are surfaced with translated titles and AI summaries, making Zeli a research reader as well as a news reader. - **Machine-readable outputs:** One-item-per-day RSS feeds, plain-markdown digests, JSON endpoints and a sitemap make Zeli easy to pipe into readers or AI agents. **Strengths:** Turns the Hacker News front page into a fast, scannable daily brief; Seven languages with genuinely translated titles, summaries and comment highlights; Permanent, citable story and daily archive pages that never expire; Free, no signup, no API key, installable as a PWA **Limitations:** Summaries are machine-generated and are not fact-checked by a human; Real summaries exist only in seven languages — other locales fall back to English; It covers Hacker News and HuggingFace papers only, not your own reading list or arbitrary URLs; Keys off Hacker News ranking, so niche topics that never hit the front page are not included [Profile (Markdown)](https://openaitools.app/tool/zeli.md) ## Frequently Asked Questions ### How do Models.dev and Zeli compare in monthly traffic? Models.dev has 200,451 monthly visits, while Zeli has 56,147. Traffic estimates describe audience size, not product quality. ### How do their growth rates compare? Models.dev has a month-over-month growth rate of -3.9%; Zeli has -46.8%. ### How does pricing compare? Models.dev: Free. Models.dev is free and open source. It is a reference database, so the prices it lists are the per-million-token rates charged by the model providers themselves, not a fee for using the site. Zeli: Free. Free. No account, no API key and no payment; the full site, the RSS feed and the machine-readable digests are all available at no cost. ## Alternatives | # | Tool Name | Monthly Visits | MoM Growth Rate | Pricing Model | Summary | Profile (Markdown) | | :--- | :--- | :--- | :--- | :--- | :--- | :--- | | 1 | [Readray (formerly Lilys AI)](https://openaitools.app/tool/lilys-ai) | 967,113 | -9.7% | Freemium | A proactive AI reading lens for papers, videos, and web pages | [.md](https://openaitools.app/tool/lilys-ai.md) | | 2 | [Summarizer.org](https://openaitools.app/tool/summarizer-org) | 398,509 | +1.3% | Freemium | Free AI Summarizer for text, articles, URLs and images | [.md](https://openaitools.app/tool/summarizer-org.md) | | 3 | [Stork](https://openaitools.app/tool/stork) | 201,544 | +2.3% | Free | Includes model pricing trackers and developer news alongside tools directories, but less focused on raw API specs. | [.md](https://openaitools.app/tool/stork.md) | | 4 | [Paper Digest](https://openaitools.app/tool/paper-digest) | 97,202 | -7.1% | Freemium | AI-powered platform to read, write, and stay current with research | [.md](https://openaitools.app/tool/paper-digest.md) | | 5 | [TLDR This](https://openaitools.app/tool/tldr-this) | 82,609 | -20.5% | Free | Turn any long article or webpage into a clean, clickable summary in one click | [.md](https://openaitools.app/tool/tldr-this.md) | | 6 | [InfraBase.ai](https://openaitools.app/tool/infrabase-ai) | 39,072 | -13.6% | Free | Catalogues and compares AI infrastructure tools and services across categories, but lacks deep per-token pricing tables. | [.md](https://openaitools.app/tool/infrabase-ai.md) | | 7 | [SciSummary](https://openaitools.app/tool/scisummary) | 38,871 | -37.7% | Freemium, Free Trial, Paid | AI summaries and study guides for scientific papers | [.md](https://openaitools.app/tool/scisummary.md) | | 8 | [OpenRead](https://openaitools.app/tool/openread) | 27,098 | -51.6% | Freemium, Paid, Contact for Pricing | AI research workspace for searching, reading and connecting papers | [.md](https://openaitools.app/tool/openread.md) | | 9 | [ExplainPaper](https://openaitools.app/tool/explainpaper) | 26,016 | -39.3% | Freemium | Highlight dense research text and get plain-language explanations instantly | [.md](https://openaitools.app/tool/explainpaper.md) | | 10 | [Particle](https://openaitools.app/tool/particle) | 15,561 | -11.9% | Free | Personalized news, summarized from many sources | [.md](https://openaitools.app/tool/particle.md) | --- Source: https://openaitools.app/compare/models-dev-vs-zeli More Markdown: [Categories](https://openaitools.app/categories.md) · [Traffic rankings](https://openaitools.app/rankings.md) · [llms.txt](https://openaitools.app/llms.txt)