[{"data":1,"prerenderedAt":96},["ShallowReactive",2],{"categories-init":3,"subcategory-ai-model-aggregators":4,"category-meta-apis-infrastructure":56,"score-types":60,"pricing-models":82},true,{"subcategory_id":5,"name":6,"slug":7,"description":8,"category_id":9,"display_order":9,"tool_count":10,"tools":11},63,"AI Model Aggregators","ai-model-aggregators","Unified API layers that route requests across many underlying model providers rather than hosting models themselves — used for provider fallback, price arbitrage, and a single integration point across many LLMs.",11,2,[12],{"tool_id":13,"name":14,"slug":15,"tooltip_description":16,"logo_url":17,"logo_bg":18,"pricing_model":19,"learning_curve_score":23,"popularity_score":24,"hosting_assignment_type":25,"hosting_provider_restriction":26,"hosting_target_restriction":26,"hosting_compatible_tool_ids":25,"parent_tool_id":25,"category":27,"subcategory":30,"categories":31,"subcategories":34,"flexibility_score":24,"performance_score":24,"portability_score":36,"is_featured":37,"tags":38,"score_reasonings":49,"published_date":55,"last_updated_date":25},218,"OpenRouter","openrouter","Unified, OpenAI-compatible API to 500+ models across 80+ providers, with automatic provider fallback and one credits-based bill: the hosted, nothing-to-deploy counterpart to a self-hosted gateway like LiteLLM.","https:\u002F\u002Fassets.tekyous.dev\u002Flogos\u002Ftools\u002Fopenrouter.svg","dark",{"slug":20,"display_name":21,"description":22},"usage_based","Usage-Based","Pricing scales with consumption: API calls, data volume, compute time, or similar metered units.",5,4,null,"open",{"category_id":9,"name":28,"slug":29},"APIs & Infrastructure","apis-infrastructure",{"subcategory_id":5,"name":6,"slug":7},[32],{"category_id":9,"name":28,"slug":29,"is_primary":3,"display_order":33},0,[35],{"subcategory_id":5,"name":6,"slug":7,"category_id":9,"is_primary":3,"display_order":33},3,false,[39,44],{"tag_id":40,"name":41,"slug":42,"tag_type":43},25,"Machine Learning","machine-learning","use_case",{"tag_id":45,"name":46,"slug":47,"tag_type":48},40,"Web","web","platform",{"learning_curve":50,"flexibility":51,"performance":52,"portability":53,"popularity":54},"A single OpenAI-compatible API key and endpoint gives instant access to hundreds of models, no infrastructure setup or provider-specific integration work required.","500+ models across 80+ providers, custom data policies, and a Bring-Your-Own-Key mode cover most routing needs, though there's no control over the underlying routing logic the way a self-hosted gateway offers.","Edge-deployed routing and automatic provider fallback keep added latency low and reliability high, backed by real scale (200+ trillion tokens\u002Fmonth).","Closed-source, hosted-only SaaS with no self-hosting option, credits and API keys are OpenRouter-specific and don't transfer if switching to a self-hosted gateway.","Aggregates 400+ models from 60+ providers behind one OpenAI-style API and is usually the first stop for developers who want to try many models without juggling separate provider keys. A fixture of the LLM-app-building corner of AI development specifically, not a name outside that corner.","2026-09-27",{"category_id":9,"name":28,"slug":29,"description":57,"icon_url":58,"display_order":9,"tool_count":59},"API gateways, CDNs, and infrastructure tools.","https:\u002F\u002Fassets.tekyous.dev\u002Ficons\u002Fcategories\u002Fapis-infrastructure.svg",18,[61,66,70,74,78],{"slug":62,"name":63,"description":64,"display_order":65},"popularity","Popularity","How widely adopted the tool is in the developer community. 1 = niche; 5 = mainstream and widely used.",1,{"slug":67,"name":68,"description":69,"display_order":10},"learning_curve","Learning Curve","How quickly a developer can become productive with this tool. 1 = beginner-accessible; 5 = steep, requires significant prior experience.",{"slug":71,"name":72,"description":73,"display_order":36},"flexibility","Flexibility","How much you can customise or extend the tool for your specific needs. 1 = highly opinionated with few escape hatches; 5 = highly flexible.",{"slug":75,"name":76,"description":77,"display_order":24},"performance","Performance","How well the tool performs its primary function. For runtimes: execution speed. For services: throughput and latency. For editors: responsiveness. 1 = slow or resource-heavy; 5 = fast and efficient.",{"slug":79,"name":80,"description":81,"display_order":23},"portability","Portability","How easy it is to migrate away from this tool once you are invested in it. Based on: data\u002Fcode exportability, skills transferability to other tools, and adherence to open standards. 1 = high lock-in; 5 = fully open, skills transfer universally.",[83,87,91,95],{"slug":84,"display_name":85,"description":86,"display_order":65},"open_source","Open Source","Source code is publicly available and free to use, modify, and distribute. No paid plans from the project itself.",{"slug":88,"display_name":89,"description":90,"display_order":10},"freemium","Freemium","A free tier is available; additional features, usage limits, or managed hosting require a paid plan.",{"slug":92,"display_name":93,"description":94,"display_order":36},"paid","Paid","No meaningful free tier — a subscription or one-time purchase is required to use the tool.",{"slug":20,"display_name":21,"description":22,"display_order":24},1790518754781]