--- title: APIs.io On-Premise, And Why I Am Looking For Design Partners description: APIs.io, a public API catalog launched in 2014, is expanding into an on-premise appliance for companies that want a private inventory of their own APIs without... canonical: https://daily.dev/posts/apis-io-on-premise-and-why-i-am-looking-for-design-partners-a55sh5idj twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: APIs.io On-Premise, And Why I Am Looking For Design Partners | daily.dev og:description: APIs.io, a public API catalog launched in 2014, is expanding into an on-premise appliance for companies that want a private inventory of their own APIs without... og:url: https://daily.dev/posts/apis-io-on-premise-and-why-i-am-looking-for-design-partners-a55sh5idj og:image: https://api.daily.dev/og/posts/a55Sh5IDj.png og:image:alt: APIs.io On-Premise, And Why I Am Looking For Design Partners og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # APIs.io On-Premise, And Why I Am Looking For Design Partners **[API Evangelist](https://daily.dev/sources/apievangelist)** · 5 min read · 0 upvotes · 0 comments ## Summary APIs.io, a public API catalog launched in 2014, is expanding into an on-premise appliance for companies that want a private inventory of their own APIs without sending source code to a hosted AI provider. The system now runs the profiling and scoring pipeline on gpt-oss-120b, OpenAI's open-weight model, quantized to a 59GB GGUF file served locally via llama-server, eliminating per-token costs and keeping data on-premises. Testing against Claude on six well-documented providers showed the local model landed within 1-10 points of Claude's output, in about half the time and for $0 versus $55.25. The appliance spiders Git repos, Confluence, and portals for API definitions, aggregates them into a Git-based system of record, scores them with a reconfigurable Kin Score, and publishes a static site. The author is seeking small and medium-sized company design partners to shape the product before a general release. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### How does the gpt-oss-120b open-weight model compare to Claude for automated API documentation profiling? Running the same profiling pipeline on six well-documented API providers, gpt-oss-120b landed within about one to ten points of Claude's Kin Score results, tying on one provider. It completed the work in roughly half the wall-clock time and cost $0, compared to $55.25 for the equivalent Claude runs, since it runs locally with no per-token billing. _Anyone weighing local versus hosted models for internal tooling can compare real cost and accuracy tradeoffs on daily.dev._ ### What model and quantization does APIs.io On-Premise use to run locally without sending data to a hosted AI provider? It uses gpt-oss-120b, OpenAI's open-weight model, in MXFP4 quantization as a 59 GB GGUF file, served locally through llama-server. This lets the API profiling and scoring pipeline run entirely on hardware the operator owns, starting on a Mac mini, with no tokens leaving the machine and no per-token billing. _Teams evaluating self-hosted LLM inference for sensitive internal data can track setups like this on daily.dev._ ## Similar posts on daily.dev - [I stopped paying for multiple AI coding tools and built one setup that can use Claude, GPT, Gemini, and local models](https://daily.dev/posts/i-stopped-paying-for-multiple-ai-coding-tools-and-built-one-setup-that-can-use-claude-gpt-gemini--4a44dlugk) · XDA Developers · 0 upvotes · 0 comments - [Open-source coding agents like OpenCode, Cline, and Aider are solving a huge headache for developers](https://daily.dev/posts/open-source-coding-agents-like-opencode-cline-and-aider-are-solving-a-huge-headache-for-developers-77xyw8rmy) · The New Stack · 4 upvotes · 0 comments - [Local vs Cloud AI Coding: Latency, Privacy & Performance Guide](https://daily.dev/posts/local-vs-cloud-ai-coding-latency-privacy-performance-guide-ce3vygmeo) · SitePoint · 0 upvotes · 0 comments --- Tags: [#openapi](https://daily.dev/tags/openapi) [View this post on daily.dev](https://daily.dev/posts/apis-io-on-premise-and-why-i-am-looking-for-design-partners-a55sh5idj) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"APIs.io On-Premise, And Why I Am Looking For Design Partners","url":"https://daily.dev/posts/apis-io-on-premise-and-why-i-am-looking-for-design-partners-a55sh5idj","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/apis-io-on-premise-and-why-i-am-looking-for-design-partners-a55sh5idj"},"datePublished":"2026-09-29T12:42:58.749Z","dateModified":"2026-09-29T12:43:22.980Z","description":"APIs.io, a public API catalog launched in 2014, is expanding into an on-premise appliance for companies that want a private inventory of their own APIs without...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/b6996e75a64c2780f0fc45896884e787?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/b6996e75a64c2780f0fc45896884e787?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"API Evangelist","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"API Evangelist","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/a36244ae67bc4f41a605f780267ecb5f","url":"https://daily.dev/sources/apievangelist"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/apis-io-on-premise-and-why-i-am-looking-for-design-partners-a55sh5idj","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"openapi","timeRequired":"PT5M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"API Evangelist","item":"https://daily.dev/sources/apievangelist"},{"@type":"ListItem","position":3,"name":"APIs.io On-Premise, And Why I Am Looking For Design Partners"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/apis-io-on-premise-and-why-i-am-looking-for-design-partners-a55sh5idj#faq","mainEntity":[{"@type":"Question","name":"How does the gpt-oss-120b open-weight model compare to Claude for automated API documentation profiling?","acceptedAnswer":{"@type":"Answer","text":"Running the same profiling pipeline on six well-documented API providers, gpt-oss-120b landed within about one to ten points of Claude's Kin Score results, tying on one provider. It completed the work in roughly half the wall-clock time and cost $0, compared to $55.25 for the equivalent Claude runs, since it runs locally with no per-token billing. Anyone weighing local versus hosted models for internal tooling can compare real cost and accuracy tradeoffs on daily.dev."}},{"@type":"Question","name":"What model and quantization does APIs.io On-Premise use to run locally without sending data to a hosted AI provider?","acceptedAnswer":{"@type":"Answer","text":"It uses gpt-oss-120b, OpenAI's open-weight model, in MXFP4 quantization as a 59 GB GGUF file, served locally through llama-server. This lets the API profiling and scoring pipeline run entirely on hardware the operator owns, starting on a Mac mini, with no tokens leaving the machine and no per-token billing. Teams evaluating self-hosted LLM inference for sensitive internal data can track setups like this on daily.dev."}}]} ```