{"type":"models","count":33,"schema_url":"/api/v1/schema.json","item_api_pattern":"/api/v1/models/{slug}.json","items":[{"slug":"claude-haiku-4.5","id":"claude-haiku-4.5","type":"model","title":"Claude Haiku 4.5","description":"Anthropic's fastest and most cost-efficient model. Matches Claude Sonnet 4's performance on coding and agent tasks while being dramatically faster and cheaper.","last_updated":"2026-04-10","last_verified":null,"verification_status":"unverified","markdown_url":"/content/models/claude-haiku-4.5.md","html_url":"/models/claude-haiku-4.5","api_url":"/api/v1/models/claude-haiku-4.5.json","content_hash":"d3cca87c491bc7fd29b2c8a90ab87448891b116b24de29dee3b54580fc78885c","sha256":"d3cca87c491bc7fd29b2c8a90ab87448891b116b24de29dee3b54580fc78885c","provider":"Anthropic","pricing":{"input":"$1.00 / 1M tokens","output":"$5.00 / 1M tokens"},"benchmarks":{"reasoning":82,"coding":84,"math":80,"writing":83,"multilingual":80,"speed":95},"tags":["anthropic","proprietary","text","image"],"website":"https://anthropic.com","release_date":"2025-11","relationships":{"links":[],"related":[{"id":"claude-opus-4.6","title":"Claude Opus 4.6","type":"model","html_url":"/models/claude-opus-4.6","markdown_url":"/content/models/claude-opus-4.6.md","shared_tags":["anthropic","proprietary","text","image"],"score":8},{"id":"claude-sonnet-4.6","title":"Claude Sonnet 4.6","type":"model","html_url":"/models/claude-sonnet-4.6","markdown_url":"/content/models/claude-sonnet-4.6.md","shared_tags":["anthropic","proprietary","text","image"],"score":8},{"id":"gemini-3-flash","title":"Gemini 3 Flash","type":"model","html_url":"/models/gemini-3-flash","markdown_url":"/content/models/gemini-3-flash.md","shared_tags":["proprietary","text","image"],"score":5},{"id":"gemini-3.1-pro","title":"Gemini 3.1 Pro","type":"model","html_url":"/models/gemini-3.1-pro","markdown_url":"/content/models/gemini-3.1-pro.md","shared_tags":["proprietary","text","image"],"score":5},{"id":"gpt-5.4","title":"GPT-5.4","type":"model","html_url":"/models/gpt-5.4","markdown_url":"/content/models/gpt-5.4.md","shared_tags":["proprietary","text","image"],"score":5},{"id":"gpt-5.4-thinking","title":"GPT-5.4 Thinking","type":"model","html_url":"/models/gpt-5.4-thinking","markdown_url":"/content/models/gpt-5.4-thinking.md","shared_tags":["proprietary","text","image"],"score":5}],"explicit":{}}},{"slug":"claude-opus-4.6","id":"claude-opus-4.6","type":"model","title":"Claude Opus 4.6","description":"Anthropic's most capable model and the first Opus-class model with a 1M token context window. Leads on coding benchmarks with 80.8% SWE-bench. Internal codename \"Fennec.\"","last_updated":"2026-04-10","last_verified":null,"verification_status":"unverified","markdown_url":"/content/models/claude-opus-4.6.md","html_url":"/models/claude-opus-4.6","api_url":"/api/v1/models/claude-opus-4.6.json","content_hash":"51a0a4c31212a32a86a8e6d0d5a3a7844bb7bcf4454e0237f9693476e284df48","sha256":"51a0a4c31212a32a86a8e6d0d5a3a7844bb7bcf4454e0237f9693476e284df48","provider":"Anthropic","pricing":{"input":"$5.00 / 1M tokens","output":"$25.00 / 1M tokens","note":"Significantly cheaper than Opus 4.5"},"benchmarks":{"reasoning":96,"coding":97,"math":93,"writing":95,"multilingual":88,"speed":62},"tags":["anthropic","proprietary","text","image"],"website":"https://anthropic.com","release_date":"2026-02","relationships":{"links":[],"related":[{"id":"claude-haiku-4.5","title":"Claude Haiku 4.5","type":"model","html_url":"/models/claude-haiku-4.5","markdown_url":"/content/models/claude-haiku-4.5.md","shared_tags":["anthropic","proprietary","text","image"],"score":8},{"id":"claude-sonnet-4.6","title":"Claude Sonnet 4.6","type":"model","html_url":"/models/claude-sonnet-4.6","markdown_url":"/content/models/claude-sonnet-4.6.md","shared_tags":["anthropic","proprietary","text","image"],"score":8},{"id":"gemini-3-flash","title":"Gemini 3 Flash","type":"model","html_url":"/models/gemini-3-flash","markdown_url":"/content/models/gemini-3-flash.md","shared_tags":["proprietary","text","image"],"score":5},{"id":"gemini-3.1-pro","title":"Gemini 3.1 Pro","type":"model","html_url":"/models/gemini-3.1-pro","markdown_url":"/content/models/gemini-3.1-pro.md","shared_tags":["proprietary","text","image"],"score":5},{"id":"gpt-5.4","title":"GPT-5.4","type":"model","html_url":"/models/gpt-5.4","markdown_url":"/content/models/gpt-5.4.md","shared_tags":["proprietary","text","image"],"score":5},{"id":"gpt-5.4-thinking","title":"GPT-5.4 Thinking","type":"model","html_url":"/models/gpt-5.4-thinking","markdown_url":"/content/models/gpt-5.4-thinking.md","shared_tags":["proprietary","text","image"],"score":5}],"explicit":{}}},{"slug":"claude-sonnet-4.6","id":"claude-sonnet-4.6","type":"model","title":"Claude Sonnet 4.6","description":"The first Sonnet model preferred over a previous Opus in coding evaluations. Excellent balance of speed, quality, and cost with a full 1M token context window.","last_updated":"2026-04-10","last_verified":null,"verification_status":"unverified","markdown_url":"/content/models/claude-sonnet-4.6.md","html_url":"/models/claude-sonnet-4.6","api_url":"/api/v1/models/claude-sonnet-4.6.json","content_hash":"6561095974ae8db00e5211cd16382bd27503cc9420dc9bb29e05f157c643ab14","sha256":"6561095974ae8db00e5211cd16382bd27503cc9420dc9bb29e05f157c643ab14","provider":"Anthropic","pricing":{"input":"$3.00 / 1M tokens","output":"$15.00 / 1M tokens"},"benchmarks":{"reasoning":91,"coding":93,"math":89,"writing":92,"multilingual":87,"speed":82},"tags":["anthropic","proprietary","text","image"],"website":"https://anthropic.com","release_date":"2026-02","relationships":{"links":[],"related":[{"id":"claude-haiku-4.5","title":"Claude Haiku 4.5","type":"model","html_url":"/models/claude-haiku-4.5","markdown_url":"/content/models/claude-haiku-4.5.md","shared_tags":["anthropic","proprietary","text","image"],"score":8},{"id":"claude-opus-4.6","title":"Claude Opus 4.6","type":"model","html_url":"/models/claude-opus-4.6","markdown_url":"/content/models/claude-opus-4.6.md","shared_tags":["anthropic","proprietary","text","image"],"score":8},{"id":"gemini-3-flash","title":"Gemini 3 Flash","type":"model","html_url":"/models/gemini-3-flash","markdown_url":"/content/models/gemini-3-flash.md","shared_tags":["proprietary","text","image"],"score":5},{"id":"gemini-3.1-pro","title":"Gemini 3.1 Pro","type":"model","html_url":"/models/gemini-3.1-pro","markdown_url":"/content/models/gemini-3.1-pro.md","shared_tags":["proprietary","text","image"],"score":5},{"id":"gpt-5.4","title":"GPT-5.4","type":"model","html_url":"/models/gpt-5.4","markdown_url":"/content/models/gpt-5.4.md","shared_tags":["proprietary","text","image"],"score":5},{"id":"gpt-5.4-thinking","title":"GPT-5.4 Thinking","type":"model","html_url":"/models/gpt-5.4-thinking","markdown_url":"/content/models/gpt-5.4-thinking.md","shared_tags":["proprietary","text","image"],"score":5}],"explicit":{}}},{"slug":"cohere-tiny-aya","id":"cohere-tiny-aya","type":"model","title":"Cohere Tiny Aya 3.35B","description":"Multilingual specialist supporting 70+ languages at only 3.35B parameters. Designed for laptop and edge deployment. CC-BY-NC license.","last_updated":"2026-04-10","last_verified":null,"verification_status":"unverified","markdown_url":"/content/models/cohere-tiny-aya.md","html_url":"/models/cohere-tiny-aya","api_url":"/api/v1/models/cohere-tiny-aya.json","content_hash":"087f1f51b6a22266b8f31fa4633500a13965ab77d919f8f314724e9fe2b177e3","sha256":"087f1f51b6a22266b8f31fa4633500a13965ab77d919f8f314724e9fe2b177e3","provider":"Cohere","pricing":{"input":"Free (CC-BY-NC)","output":"Free (CC-BY-NC)","free":true},"benchmarks":{"reasoning":65,"coding":62,"math":60,"writing":68,"multilingual":85,"speed":96},"tags":["cohere","open-source","text"],"website":"https://cohere.com","release_date":"2026-02","relationships":{"links":[],"related":[{"id":"command-r-plus","title":"Command R+","type":"model","html_url":"/models/command-r-plus","markdown_url":"/content/models/command-r-plus.md","shared_tags":["cohere","open-source","text"],"score":7},{"id":"deepseek-r1","title":"DeepSeek R1","type":"model","html_url":"/models/deepseek-r1","markdown_url":"/content/models/deepseek-r1.md","shared_tags":["open-source","text"],"score":4},{"id":"deepseek-v3.2","title":"DeepSeek V3.2","type":"model","html_url":"/models/deepseek-v3.2","markdown_url":"/content/models/deepseek-v3.2.md","shared_tags":["open-source","text"],"score":4},{"id":"falcon-3","title":"Falcon 3","type":"model","html_url":"/models/falcon-3","markdown_url":"/content/models/falcon-3.md","shared_tags":["open-source","text"],"score":4},{"id":"gemma-3","title":"Gemma 3","type":"model","html_url":"/models/gemma-3","markdown_url":"/content/models/gemma-3.md","shared_tags":["open-source","text"],"score":4},{"id":"gemma-4","title":"Gemma 4","type":"model","html_url":"/models/gemma-4","markdown_url":"/content/models/gemma-4.md","shared_tags":["open-source","text"],"score":4}],"explicit":{}}},{"slug":"command-r-plus","id":"command-r-plus","type":"model","title":"Command R+","description":"Cohere's flagship model purpose-built for enterprise RAG (Retrieval-Augmented Generation). Excels at grounded generation with citations, multi-step tool use, and structured outputs. Strong bilingual English/French support.","last_updated":"2026-04-10","last_verified":null,"verification_status":"unverified","markdown_url":"/content/models/command-r-plus.md","html_url":"/models/command-r-plus","api_url":"/api/v1/models/command-r-plus.json","content_hash":"faa41ff7cbfc7b98daf2b8d3c80294e1042295580e41b2387502559ef2e258c1","sha256":"faa41ff7cbfc7b98daf2b8d3c80294e1042295580e41b2387502559ef2e258c1","provider":"Cohere","pricing":{"input":"$2.50 / 1M tokens","output":"$10.00 / 1M tokens","note":"Also available as open weights (CC-BY-NC)"},"benchmarks":{"reasoning":82,"coding":78,"math":76,"writing":85,"multilingual":88,"speed":78},"tags":["cohere","open-source","text"],"website":"https://cohere.com","release_date":"2025-08","relationships":{"links":[],"related":[{"id":"cohere-tiny-aya","title":"Cohere Tiny Aya 3.35B","type":"model","html_url":"/models/cohere-tiny-aya","markdown_url":"/content/models/cohere-tiny-aya.md","shared_tags":["cohere","open-source","text"],"score":7},{"id":"deepseek-r1","title":"DeepSeek R1","type":"model","html_url":"/models/deepseek-r1","markdown_url":"/content/models/deepseek-r1.md","shared_tags":["open-source","text"],"score":4},{"id":"deepseek-v3.2","title":"DeepSeek V3.2","type":"model","html_url":"/models/deepseek-v3.2","markdown_url":"/content/models/deepseek-v3.2.md","shared_tags":["open-source","text"],"score":4},{"id":"falcon-3","title":"Falcon 3","type":"model","html_url":"/models/falcon-3","markdown_url":"/content/models/falcon-3.md","shared_tags":["open-source","text"],"score":4},{"id":"gemma-3","title":"Gemma 3","type":"model","html_url":"/models/gemma-3","markdown_url":"/content/models/gemma-3.md","shared_tags":["open-source","text"],"score":4},{"id":"gemma-4","title":"Gemma 4","type":"model","html_url":"/models/gemma-4","markdown_url":"/content/models/gemma-4.md","shared_tags":["open-source","text"],"score":4}],"explicit":{}}},{"slug":"deepseek-r1","id":"deepseek-r1","type":"model","title":"DeepSeek R1","description":"Powerful open-source reasoning model that exceeds OpenAI o1 on AIME and MATH benchmarks. Transparent chain-of-thought reasoning at extremely low cost. MIT license. Updated with R1-0528 in May 2025.","last_updated":"2026-04-10","last_verified":null,"verification_status":"unverified","markdown_url":"/content/models/deepseek-r1.md","html_url":"/models/deepseek-r1","api_url":"/api/v1/models/deepseek-r1.json","content_hash":"82337e0cad76f5697b684824360eb063620b86b838f2550c40857a2257cc90f2","sha256":"82337e0cad76f5697b684824360eb063620b86b838f2550c40857a2257cc90f2","provider":"DeepSeek","pricing":{"input":"$0.55 / 1M tokens","output":"$2.19 / 1M tokens","note":"Also available open-source (MIT)"},"benchmarks":{"reasoning":92,"coding":88,"math":94,"writing":72,"multilingual":70,"speed":55},"tags":["deepseek","open-source","text"],"website":"https://deepseek.com","release_date":"2025-01","relationships":{"links":[],"related":[{"id":"deepseek-v3.2","title":"DeepSeek V3.2","type":"model","html_url":"/models/deepseek-v3.2","markdown_url":"/content/models/deepseek-v3.2.md","shared_tags":["deepseek","open-source","text"],"score":7},{"id":"cohere-tiny-aya","title":"Cohere Tiny Aya 3.35B","type":"model","html_url":"/models/cohere-tiny-aya","markdown_url":"/content/models/cohere-tiny-aya.md","shared_tags":["open-source","text"],"score":4},{"id":"command-r-plus","title":"Command R+","type":"model","html_url":"/models/command-r-plus","markdown_url":"/content/models/command-r-plus.md","shared_tags":["open-source","text"],"score":4},{"id":"provider-deepseek","title":"DeepSeek Provider Profile","type":"provider","html_url":"/providers/deepseek","markdown_url":"/content/providers/deepseek.md","shared_tags":["deepseek","open-source"],"score":4},{"id":"falcon-3","title":"Falcon 3","type":"model","html_url":"/models/falcon-3","markdown_url":"/content/models/falcon-3.md","shared_tags":["open-source","text"],"score":4},{"id":"gemma-3","title":"Gemma 3","type":"model","html_url":"/models/gemma-3","markdown_url":"/content/models/gemma-3.md","shared_tags":["open-source","text"],"score":4}],"explicit":{}}},{"slug":"deepseek-v3.2","id":"deepseek-v3.2","type":"model","title":"DeepSeek V3.2","description":"On par with GPT-5.1 and Gemini 3.0 Pro on benchmarks. Uses sparse attention for efficiency. MIT license. Dramatically cheaper than Western alternatives.","last_updated":"2026-04-10","last_verified":null,"verification_status":"unverified","markdown_url":"/content/models/deepseek-v3.2.md","html_url":"/models/deepseek-v3.2","api_url":"/api/v1/models/deepseek-v3.2.json","content_hash":"0c21502ecf4fd597605f77df8b6087ee795fa28cd4042faeaf81191400a3f0b8","sha256":"0c21502ecf4fd597605f77df8b6087ee795fa28cd4042faeaf81191400a3f0b8","provider":"DeepSeek","pricing":{"input":"$0.27 / 1M tokens","output":"$1.10 / 1M tokens","free":true,"note":"MIT license for self-hosting"},"benchmarks":{"reasoning":88,"coding":88,"math":87,"writing":84,"multilingual":80,"speed":82},"tags":["deepseek","open-source","text"],"website":"https://deepseek.com","release_date":"2025-09","relationships":{"links":[],"related":[{"id":"deepseek-r1","title":"DeepSeek R1","type":"model","html_url":"/models/deepseek-r1","markdown_url":"/content/models/deepseek-r1.md","shared_tags":["deepseek","open-source","text"],"score":7},{"id":"cohere-tiny-aya","title":"Cohere Tiny Aya 3.35B","type":"model","html_url":"/models/cohere-tiny-aya","markdown_url":"/content/models/cohere-tiny-aya.md","shared_tags":["open-source","text"],"score":4},{"id":"command-r-plus","title":"Command R+","type":"model","html_url":"/models/command-r-plus","markdown_url":"/content/models/command-r-plus.md","shared_tags":["open-source","text"],"score":4},{"id":"provider-deepseek","title":"DeepSeek Provider Profile","type":"provider","html_url":"/providers/deepseek","markdown_url":"/content/providers/deepseek.md","shared_tags":["deepseek","open-source"],"score":4},{"id":"falcon-3","title":"Falcon 3","type":"model","html_url":"/models/falcon-3","markdown_url":"/content/models/falcon-3.md","shared_tags":["open-source","text"],"score":4},{"id":"gemma-3","title":"Gemma 3","type":"model","html_url":"/models/gemma-3","markdown_url":"/content/models/gemma-3.md","shared_tags":["open-source","text"],"score":4}],"explicit":{}}},{"slug":"falcon-3","id":"falcon-3","type":"model","title":"Falcon 3","description":"Runs on regular (non-gaming) laptops. Designed for accessibility and low-resource deployment. From UAE-based Technology Innovation Institute.","last_updated":"2026-04-10","last_verified":null,"verification_status":"unverified","markdown_url":"/content/models/falcon-3.md","html_url":"/models/falcon-3","api_url":"/api/v1/models/falcon-3.json","content_hash":"8e07fbaca612cc5122f0ba87d422f70dd56becb5b7b63789399f5cd63749b2f6","sha256":"8e07fbaca612cc5122f0ba87d422f70dd56becb5b7b63789399f5cd63749b2f6","provider":"Technology Innovation Institute","pricing":{"input":"Free (Apache 2.0)","output":"Free (Apache 2.0)","free":true},"benchmarks":{"reasoning":70,"coding":68,"math":67,"writing":72,"multilingual":70,"speed":94},"tags":["technology innovation institute","open-source","text"],"website":"https://falconllm.tii.ae","release_date":"2025","relationships":{"links":[],"related":[{"id":"cohere-tiny-aya","title":"Cohere Tiny Aya 3.35B","type":"model","html_url":"/models/cohere-tiny-aya","markdown_url":"/content/models/cohere-tiny-aya.md","shared_tags":["open-source","text"],"score":4},{"id":"command-r-plus","title":"Command R+","type":"model","html_url":"/models/command-r-plus","markdown_url":"/content/models/command-r-plus.md","shared_tags":["open-source","text"],"score":4},{"id":"deepseek-r1","title":"DeepSeek R1","type":"model","html_url":"/models/deepseek-r1","markdown_url":"/content/models/deepseek-r1.md","shared_tags":["open-source","text"],"score":4},{"id":"deepseek-v3.2","title":"DeepSeek V3.2","type":"model","html_url":"/models/deepseek-v3.2","markdown_url":"/content/models/deepseek-v3.2.md","shared_tags":["open-source","text"],"score":4},{"id":"gemma-3","title":"Gemma 3","type":"model","html_url":"/models/gemma-3","markdown_url":"/content/models/gemma-3.md","shared_tags":["open-source","text"],"score":4},{"id":"gemma-4","title":"Gemma 4","type":"model","html_url":"/models/gemma-4","markdown_url":"/content/models/gemma-4.md","shared_tags":["open-source","text"],"score":4}],"explicit":{}}},{"slug":"gemini-3-flash","id":"gemini-3-flash","type":"model","title":"Gemini 3 Flash","description":"Google's fast, cost-efficient model replacing Gemini 2.5 Flash. Designed for high-throughput applications with up to 1M token context at an extremely low price.","last_updated":"2026-04-10","last_verified":null,"verification_status":"unverified","markdown_url":"/content/models/gemini-3-flash.md","html_url":"/models/gemini-3-flash","api_url":"/api/v1/models/gemini-3-flash.json","content_hash":"fcac5c432f135a29ea7f4fe0a637295106eb4caffd1cf3c8753a1964900b7f12","sha256":"fcac5c432f135a29ea7f4fe0a637295106eb4caffd1cf3c8753a1964900b7f12","provider":"Google","pricing":{"input":"$0.15 / 1M tokens","output":"$0.60 / 1M tokens","note":"Free tier available"},"benchmarks":{"reasoning":82,"coding":80,"math":79,"writing":83,"multilingual":85,"speed":95},"tags":["google","proprietary","text","image","video","audio"],"website":"https://deepmind.google","release_date":"2025-12","relationships":{"links":[],"related":[{"id":"gemini-3.1-pro","title":"Gemini 3.1 Pro","type":"model","html_url":"/models/gemini-3.1-pro","markdown_url":"/content/models/gemini-3.1-pro.md","shared_tags":["google","proprietary","text","image","video","audio"],"score":10},{"id":"gemma-4","title":"Gemma 4","type":"model","html_url":"/models/gemma-4","markdown_url":"/content/models/gemma-4.md","shared_tags":["google","text","image","video","audio"],"score":9},{"id":"gemma-3","title":"Gemma 3","type":"model","html_url":"/models/gemma-3","markdown_url":"/content/models/gemma-3.md","shared_tags":["google","text","image"],"score":7},{"id":"gpt-5.4","title":"GPT-5.4","type":"model","html_url":"/models/gpt-5.4","markdown_url":"/content/models/gpt-5.4.md","shared_tags":["proprietary","text","image","audio"],"score":6},{"id":"gpt-5.4-thinking","title":"GPT-5.4 Thinking","type":"model","html_url":"/models/gpt-5.4-thinking","markdown_url":"/content/models/gpt-5.4-thinking.md","shared_tags":["proprietary","text","image","audio"],"score":6},{"id":"claude-haiku-4.5","title":"Claude Haiku 4.5","type":"model","html_url":"/models/claude-haiku-4.5","markdown_url":"/content/models/claude-haiku-4.5.md","shared_tags":["proprietary","text","image"],"score":5}],"explicit":{}}},{"slug":"gemini-3.1-pro","id":"gemini-3.1-pro","type":"model","title":"Gemini 3.1 Pro","description":"Google's most capable model, building on the Gemini 3 series with improved reasoning, multimodal, and agentic capabilities. Native multimodal across text, images, video, and audio.","last_updated":"2026-04-10","last_verified":null,"verification_status":"unverified","markdown_url":"/content/models/gemini-3.1-pro.md","html_url":"/models/gemini-3.1-pro","api_url":"/api/v1/models/gemini-3.1-pro.json","content_hash":"95504fb958957b344c2ed8ffcf4e5545aafb3eb285acf694668ec13cd38b7bfe","sha256":"95504fb958957b344c2ed8ffcf4e5545aafb3eb285acf694668ec13cd38b7bfe","provider":"Google","pricing":{"input":"$2.00 / 1M tokens","output":"$12.00 / 1M tokens","note":"Free tier via Google AI Studio"},"benchmarks":{"reasoning":93,"coding":91,"math":92,"writing":89,"multilingual":93,"speed":78},"tags":["google","proprietary","text","image","video","audio"],"website":"https://deepmind.google","release_date":"2026-02","relationships":{"links":[],"related":[{"id":"gemini-3-flash","title":"Gemini 3 Flash","type":"model","html_url":"/models/gemini-3-flash","markdown_url":"/content/models/gemini-3-flash.md","shared_tags":["google","proprietary","text","image","video","audio"],"score":10},{"id":"gemma-4","title":"Gemma 4","type":"model","html_url":"/models/gemma-4","markdown_url":"/content/models/gemma-4.md","shared_tags":["google","text","image","video","audio"],"score":9},{"id":"gemma-3","title":"Gemma 3","type":"model","html_url":"/models/gemma-3","markdown_url":"/content/models/gemma-3.md","shared_tags":["google","text","image"],"score":7},{"id":"gpt-5.4","title":"GPT-5.4","type":"model","html_url":"/models/gpt-5.4","markdown_url":"/content/models/gpt-5.4.md","shared_tags":["proprietary","text","image","audio"],"score":6},{"id":"gpt-5.4-thinking","title":"GPT-5.4 Thinking","type":"model","html_url":"/models/gpt-5.4-thinking","markdown_url":"/content/models/gpt-5.4-thinking.md","shared_tags":["proprietary","text","image","audio"],"score":6},{"id":"claude-haiku-4.5","title":"Claude Haiku 4.5","type":"model","html_url":"/models/claude-haiku-4.5","markdown_url":"/content/models/claude-haiku-4.5.md","shared_tags":["proprietary","text","image"],"score":5}],"explicit":{}}},{"slug":"gemma-3","id":"gemma-3","type":"model","title":"Gemma 3","description":"Google's open model family optimized for on-device and edge deployment. Multimodal from 4B parameters. Sizes from 1B to 27B.","last_updated":"2026-04-10","last_verified":null,"verification_status":"unverified","markdown_url":"/content/models/gemma-3.md","html_url":"/models/gemma-3","api_url":"/api/v1/models/gemma-3.json","content_hash":"9b8c41f767f8ab3f20fb6a19336914199798ee25d1904f377f75061cfd00fb3f","sha256":"9b8c41f767f8ab3f20fb6a19336914199798ee25d1904f377f75061cfd00fb3f","provider":"Google","pricing":{"input":"Free (open weights)","output":"Free (open weights)","free":true},"benchmarks":{"reasoning":75,"coding":73,"math":72,"writing":76,"multilingual":78,"speed":93},"tags":["google","open-source","text","image"],"website":"https://ai.google.dev/gemma","release_date":"2025","relationships":{"links":[],"related":[{"id":"gemma-4","title":"Gemma 4","type":"model","html_url":"/models/gemma-4","markdown_url":"/content/models/gemma-4.md","shared_tags":["google","open-source","text","image"],"score":8},{"id":"gemini-3-flash","title":"Gemini 3 Flash","type":"model","html_url":"/models/gemini-3-flash","markdown_url":"/content/models/gemini-3-flash.md","shared_tags":["google","text","image"],"score":7},{"id":"gemini-3.1-pro","title":"Gemini 3.1 Pro","type":"model","html_url":"/models/gemini-3.1-pro","markdown_url":"/content/models/gemini-3.1-pro.md","shared_tags":["google","text","image"],"score":7},{"id":"llama-4-maverick","title":"Llama 4 Maverick","type":"model","html_url":"/models/llama-4-maverick","markdown_url":"/content/models/llama-4-maverick.md","shared_tags":["open-source","text","image"],"score":5},{"id":"llama-4-scout","title":"Llama 4 Scout","type":"model","html_url":"/models/llama-4-scout","markdown_url":"/content/models/llama-4-scout.md","shared_tags":["open-source","text","image"],"score":5},{"id":"mistral-small-4","title":"Mistral Small 4","type":"model","html_url":"/models/mistral-small-4","markdown_url":"/content/models/mistral-small-4.md","shared_tags":["open-source","text","image"],"score":5}],"explicit":{}}},{"slug":"gemma-4","id":"gemma-4","type":"model","title":"Gemma 4","description":"Google's most capable open model, built from the same research as Gemini 3. The 31B dense variant ranks #3 on Arena AI (1,452 Elo). First Gemma release under Apache 2.0. Four variants from edge (E2B) to workstation (31B). Natively multimodal with 140+ language support.","last_updated":"2026-04-10","last_verified":null,"verification_status":"unverified","markdown_url":"/content/models/gemma-4.md","html_url":"/models/gemma-4","api_url":"/api/v1/models/gemma-4.json","content_hash":"b9666dc638f0f664c0183da1974bdc48349c21c055d683e7b43ccb8652db7f83","sha256":"b9666dc638f0f664c0183da1974bdc48349c21c055d683e7b43ccb8652db7f83","provider":"Google","pricing":{"input":"Free (Apache 2.0)","output":"Free (Apache 2.0)","free":true},"benchmarks":{"reasoning":84,"coding":83,"math":89,"writing":83,"multilingual":90,"speed":85},"tags":["google","open-source","text","image","video","audio"],"website":"https://ai.google.dev/gemma","release_date":"2026-04","relationships":{"links":[],"related":[{"id":"gemini-3-flash","title":"Gemini 3 Flash","type":"model","html_url":"/models/gemini-3-flash","markdown_url":"/content/models/gemini-3-flash.md","shared_tags":["google","text","image","video","audio"],"score":9},{"id":"gemini-3.1-pro","title":"Gemini 3.1 Pro","type":"model","html_url":"/models/gemini-3.1-pro","markdown_url":"/content/models/gemini-3.1-pro.md","shared_tags":["google","text","image","video","audio"],"score":9},{"id":"gemma-3","title":"Gemma 3","type":"model","html_url":"/models/gemma-3","markdown_url":"/content/models/gemma-3.md","shared_tags":["google","open-source","text","image"],"score":8},{"id":"gpt-5.4","title":"GPT-5.4","type":"model","html_url":"/models/gpt-5.4","markdown_url":"/content/models/gpt-5.4.md","shared_tags":["text","image","audio"],"score":5},{"id":"gpt-5.4-thinking","title":"GPT-5.4 Thinking","type":"model","html_url":"/models/gpt-5.4-thinking","markdown_url":"/content/models/gpt-5.4-thinking.md","shared_tags":["text","image","audio"],"score":5},{"id":"llama-4-maverick","title":"Llama 4 Maverick","type":"model","html_url":"/models/llama-4-maverick","markdown_url":"/content/models/llama-4-maverick.md","shared_tags":["open-source","text","image"],"score":5}],"explicit":{}}},{"slug":"glm-5","id":"glm-5","type":"model","title":"GLM-5","description":"Large MoE model with strongest coding benchmark among open models (77.8% SWE-bench). 50.4% on Humanity's Last Exam. MIT license with no usage restrictions.","last_updated":"2026-04-10","last_verified":null,"verification_status":"unverified","markdown_url":"/content/models/glm-5.md","html_url":"/models/glm-5","api_url":"/api/v1/models/glm-5.json","content_hash":"a76745362d5dfd180eaf3a17bf8ca609a5de1b9e08f6c03d6f60d79b7c16184a","sha256":"a76745362d5dfd180eaf3a17bf8ca609a5de1b9e08f6c03d6f60d79b7c16184a","provider":"Zhipu AI","pricing":{"input":"Free (self-hosted)","output":"Free (self-hosted)","free":true,"note":"Also via Zhipu API"},"benchmarks":{"reasoning":90,"coding":93,"math":88,"writing":82,"multilingual":83,"speed":70},"tags":["zhipu ai","open-source","text"],"website":"https://www.zhipuai.cn","release_date":"2026-02","relationships":{"links":[],"related":[{"id":"cohere-tiny-aya","title":"Cohere Tiny Aya 3.35B","type":"model","html_url":"/models/cohere-tiny-aya","markdown_url":"/content/models/cohere-tiny-aya.md","shared_tags":["open-source","text"],"score":4},{"id":"command-r-plus","title":"Command R+","type":"model","html_url":"/models/command-r-plus","markdown_url":"/content/models/command-r-plus.md","shared_tags":["open-source","text"],"score":4},{"id":"deepseek-r1","title":"DeepSeek R1","type":"model","html_url":"/models/deepseek-r1","markdown_url":"/content/models/deepseek-r1.md","shared_tags":["open-source","text"],"score":4},{"id":"deepseek-v3.2","title":"DeepSeek V3.2","type":"model","html_url":"/models/deepseek-v3.2","markdown_url":"/content/models/deepseek-v3.2.md","shared_tags":["open-source","text"],"score":4},{"id":"falcon-3","title":"Falcon 3","type":"model","html_url":"/models/falcon-3","markdown_url":"/content/models/falcon-3.md","shared_tags":["open-source","text"],"score":4},{"id":"gemma-3","title":"Gemma 3","type":"model","html_url":"/models/gemma-3","markdown_url":"/content/models/gemma-3.md","shared_tags":["open-source","text"],"score":4}],"explicit":{}}},{"slug":"gpt-5.4","id":"gpt-5.4","type":"model","title":"GPT-5.4","description":"OpenAI's flagship model combining frontier reasoning, coding, and agentic capabilities. Unifies the best of GPT-5.3-Codex into a single model with 45% fewer hallucinations than GPT-4o.","last_updated":"2026-04-10","last_verified":null,"verification_status":"unverified","markdown_url":"/content/models/gpt-5.4.md","html_url":"/models/gpt-5.4","api_url":"/api/v1/models/gpt-5.4.json","content_hash":"dae20b16e893dcd5b0f2baeb4f785195b83ba98a1b799126bceab3845e9d7d7e","sha256":"dae20b16e893dcd5b0f2baeb4f785195b83ba98a1b799126bceab3845e9d7d7e","provider":"OpenAI","pricing":{"input":"$5.00 / 1M tokens","output":"$15.00 / 1M tokens","note":"Pricing varies by variant"},"benchmarks":{"reasoning":95,"coding":92,"math":95,"writing":93,"multilingual":90,"speed":80},"tags":["openai","proprietary","text","image","audio"],"website":"https://openai.com","release_date":"2026-03","relationships":{"links":[],"related":[{"id":"gpt-5.4-thinking","title":"GPT-5.4 Thinking","type":"model","html_url":"/models/gpt-5.4-thinking","markdown_url":"/content/models/gpt-5.4-thinking.md","shared_tags":["openai","proprietary","text","image","audio"],"score":9},{"id":"gemini-3-flash","title":"Gemini 3 Flash","type":"model","html_url":"/models/gemini-3-flash","markdown_url":"/content/models/gemini-3-flash.md","shared_tags":["proprietary","text","image","audio"],"score":6},{"id":"gemini-3.1-pro","title":"Gemini 3.1 Pro","type":"model","html_url":"/models/gemini-3.1-pro","markdown_url":"/content/models/gemini-3.1-pro.md","shared_tags":["proprietary","text","image","audio"],"score":6},{"id":"gpt-oss-120b","title":"GPT-OSS-120B","type":"model","html_url":"/models/gpt-oss-120b","markdown_url":"/content/models/gpt-oss-120b.md","shared_tags":["openai","text"],"score":6},{"id":"claude-haiku-4.5","title":"Claude Haiku 4.5","type":"model","html_url":"/models/claude-haiku-4.5","markdown_url":"/content/models/claude-haiku-4.5.md","shared_tags":["proprietary","text","image"],"score":5},{"id":"claude-opus-4.6","title":"Claude Opus 4.6","type":"model","html_url":"/models/claude-opus-4.6","markdown_url":"/content/models/claude-opus-4.6.md","shared_tags":["proprietary","text","image"],"score":5}],"explicit":{}}},{"slug":"gpt-5.4-thinking","id":"gpt-5.4-thinking","type":"model","title":"GPT-5.4 Thinking","description":"Extended thinking mode of GPT-5.4 for the hardest problems. Uses chain-of-thought reasoning for math, science, and complex analysis. Successor to the o1/o3 reasoning line.","last_updated":"2026-04-10","last_verified":null,"verification_status":"unverified","markdown_url":"/content/models/gpt-5.4-thinking.md","html_url":"/models/gpt-5.4-thinking","api_url":"/api/v1/models/gpt-5.4-thinking.json","content_hash":"40bd1ae425c863f5a20a5c11e5419f0f4f6d6f915e22a707e194f6b018c1f2cf","sha256":"40bd1ae425c863f5a20a5c11e5419f0f4f6d6f915e22a707e194f6b018c1f2cf","provider":"OpenAI","pricing":{"input":"$10.00 / 1M tokens","output":"$40.00 / 1M tokens"},"benchmarks":{"reasoning":98,"coding":93,"math":97,"writing":85,"multilingual":88,"speed":45},"tags":["openai","proprietary","text","image","audio"],"website":"https://openai.com","release_date":"2026-03","relationships":{"links":[],"related":[{"id":"gpt-5.4","title":"GPT-5.4","type":"model","html_url":"/models/gpt-5.4","markdown_url":"/content/models/gpt-5.4.md","shared_tags":["openai","proprietary","text","image","audio"],"score":9},{"id":"gemini-3-flash","title":"Gemini 3 Flash","type":"model","html_url":"/models/gemini-3-flash","markdown_url":"/content/models/gemini-3-flash.md","shared_tags":["proprietary","text","image","audio"],"score":6},{"id":"gemini-3.1-pro","title":"Gemini 3.1 Pro","type":"model","html_url":"/models/gemini-3.1-pro","markdown_url":"/content/models/gemini-3.1-pro.md","shared_tags":["proprietary","text","image","audio"],"score":6},{"id":"gpt-oss-120b","title":"GPT-OSS-120B","type":"model","html_url":"/models/gpt-oss-120b","markdown_url":"/content/models/gpt-oss-120b.md","shared_tags":["openai","text"],"score":6},{"id":"claude-haiku-4.5","title":"Claude Haiku 4.5","type":"model","html_url":"/models/claude-haiku-4.5","markdown_url":"/content/models/claude-haiku-4.5.md","shared_tags":["proprietary","text","image"],"score":5},{"id":"claude-opus-4.6","title":"Claude Opus 4.6","type":"model","html_url":"/models/claude-opus-4.6","markdown_url":"/content/models/claude-opus-4.6.md","shared_tags":["proprietary","text","image"],"score":5}],"explicit":{}}},{"slug":"gpt-oss-120b","id":"gpt-oss-120b","type":"model","title":"GPT-OSS-120B","description":"OpenAI's first fully open-weight LLMs since GPT-2. Matches or surpasses o4-mini on core benchmarks. Can run on a single 80GB GPU. Optimized for vLLM, llama.cpp, and Ollama.","last_updated":"2026-04-10","last_verified":null,"verification_status":"unverified","markdown_url":"/content/models/gpt-oss-120b.md","html_url":"/models/gpt-oss-120b","api_url":"/api/v1/models/gpt-oss-120b.json","content_hash":"392ce26b17261a4f104b5aaff63173cd5bb4a68d71efe808331632dfbc3b7cc6","sha256":"392ce26b17261a4f104b5aaff63173cd5bb4a68d71efe808331632dfbc3b7cc6","provider":"OpenAI","pricing":{"input":"Free (open weights)","output":"Free (open weights)","free":true},"benchmarks":{"reasoning":85,"coding":86,"math":85,"writing":87,"multilingual":86,"speed":75},"tags":["openai","open-source","text"],"website":"https://openai.com","release_date":"2026","relationships":{"links":[],"related":[{"id":"gpt-5.4","title":"GPT-5.4","type":"model","html_url":"/models/gpt-5.4","markdown_url":"/content/models/gpt-5.4.md","shared_tags":["openai","text"],"score":6},{"id":"gpt-5.4-thinking","title":"GPT-5.4 Thinking","type":"model","html_url":"/models/gpt-5.4-thinking","markdown_url":"/content/models/gpt-5.4-thinking.md","shared_tags":["openai","text"],"score":6},{"id":"cohere-tiny-aya","title":"Cohere Tiny Aya 3.35B","type":"model","html_url":"/models/cohere-tiny-aya","markdown_url":"/content/models/cohere-tiny-aya.md","shared_tags":["open-source","text"],"score":4},{"id":"command-r-plus","title":"Command R+","type":"model","html_url":"/models/command-r-plus","markdown_url":"/content/models/command-r-plus.md","shared_tags":["open-source","text"],"score":4},{"id":"deepseek-r1","title":"DeepSeek R1","type":"model","html_url":"/models/deepseek-r1","markdown_url":"/content/models/deepseek-r1.md","shared_tags":["open-source","text"],"score":4},{"id":"deepseek-v3.2","title":"DeepSeek V3.2","type":"model","html_url":"/models/deepseek-v3.2","markdown_url":"/content/models/deepseek-v3.2.md","shared_tags":["open-source","text"],"score":4}],"explicit":{}}},{"slug":"grok-4.1","id":"grok-4.1","type":"model","title":"Grok 4.1","description":"xAI's flagship model with 65% fewer hallucinations than its predecessor (down to 4.22%). Available in both Thinking and Non-thinking configurations.","last_updated":"2026-04-10","last_verified":null,"verification_status":"unverified","markdown_url":"/content/models/grok-4.1.md","html_url":"/models/grok-4.1","api_url":"/api/v1/models/grok-4.1.json","content_hash":"efb07266f1333573c72d3df8eb5e5155bb143f0a9a1b14428f8264de48e9394c","sha256":"efb07266f1333573c72d3df8eb5e5155bb143f0a9a1b14428f8264de48e9394c","provider":"xAI","pricing":{"input":"$3.00 / 1M tokens","output":"$15.00 / 1M tokens","note":"Available via xAI API"},"benchmarks":{"reasoning":91,"coding":90,"math":91,"writing":87,"multilingual":80,"speed":76},"tags":["xai","proprietary","text","image"],"website":"https://x.ai","release_date":"2025-11","relationships":{"links":[],"related":[{"id":"grok-4.20","title":"Grok 4.20","type":"model","html_url":"/models/grok-4.20","markdown_url":"/content/models/grok-4.20.md","shared_tags":["xai","proprietary","text","image"],"score":8},{"id":"claude-haiku-4.5","title":"Claude Haiku 4.5","type":"model","html_url":"/models/claude-haiku-4.5","markdown_url":"/content/models/claude-haiku-4.5.md","shared_tags":["proprietary","text","image"],"score":5},{"id":"claude-opus-4.6","title":"Claude Opus 4.6","type":"model","html_url":"/models/claude-opus-4.6","markdown_url":"/content/models/claude-opus-4.6.md","shared_tags":["proprietary","text","image"],"score":5},{"id":"claude-sonnet-4.6","title":"Claude Sonnet 4.6","type":"model","html_url":"/models/claude-sonnet-4.6","markdown_url":"/content/models/claude-sonnet-4.6.md","shared_tags":["proprietary","text","image"],"score":5},{"id":"gemini-3-flash","title":"Gemini 3 Flash","type":"model","html_url":"/models/gemini-3-flash","markdown_url":"/content/models/gemini-3-flash.md","shared_tags":["proprietary","text","image"],"score":5},{"id":"gemini-3.1-pro","title":"Gemini 3.1 Pro","type":"model","html_url":"/models/gemini-3.1-pro","markdown_url":"/content/models/gemini-3.1-pro.md","shared_tags":["proprietary","text","image"],"score":5}],"explicit":{}}},{"slug":"grok-4.20","id":"grok-4.20","type":"model","title":"Grok 4.20","description":"xAI's latest flagship with the lowest hallucination rate of any model (78% Omniscience) and #1 instruction following (83% IFBench). Features a novel multi-agent architecture and 2M token context window. 248 tokens/second output speed.","last_updated":"2026-04-10","last_verified":null,"verification_status":"unverified","markdown_url":"/content/models/grok-4.20.md","html_url":"/models/grok-4.20","api_url":"/api/v1/models/grok-4.20.json","content_hash":"8ec7488ed7e26660d72a71da074ea8f705627f699f9945487d0830489501458e","sha256":"8ec7488ed7e26660d72a71da074ea8f705627f699f9945487d0830489501458e","provider":"xAI","pricing":{"input":"$2.00 / 1M tokens","output":"$6.00 / 1M tokens","note":"Fast tier; Standard tier $20/$60"},"benchmarks":{"reasoning":85,"coding":88,"math":83,"writing":87,"multilingual":82,"speed":90},"tags":["xai","proprietary","text","image"],"website":"https://x.ai","release_date":"2026-03","relationships":{"links":[],"related":[{"id":"grok-4.1","title":"Grok 4.1","type":"model","html_url":"/models/grok-4.1","markdown_url":"/content/models/grok-4.1.md","shared_tags":["xai","proprietary","text","image"],"score":8},{"id":"claude-haiku-4.5","title":"Claude Haiku 4.5","type":"model","html_url":"/models/claude-haiku-4.5","markdown_url":"/content/models/claude-haiku-4.5.md","shared_tags":["proprietary","text","image"],"score":5},{"id":"claude-opus-4.6","title":"Claude Opus 4.6","type":"model","html_url":"/models/claude-opus-4.6","markdown_url":"/content/models/claude-opus-4.6.md","shared_tags":["proprietary","text","image"],"score":5},{"id":"claude-sonnet-4.6","title":"Claude Sonnet 4.6","type":"model","html_url":"/models/claude-sonnet-4.6","markdown_url":"/content/models/claude-sonnet-4.6.md","shared_tags":["proprietary","text","image"],"score":5},{"id":"gemini-3-flash","title":"Gemini 3 Flash","type":"model","html_url":"/models/gemini-3-flash","markdown_url":"/content/models/gemini-3-flash.md","shared_tags":["proprietary","text","image"],"score":5},{"id":"gemini-3.1-pro","title":"Gemini 3.1 Pro","type":"model","html_url":"/models/gemini-3.1-pro","markdown_url":"/content/models/gemini-3.1-pro.md","shared_tags":["proprietary","text","image"],"score":5}],"explicit":{}}},{"slug":"hermes-4-405b","id":"hermes-4-405b","type":"model","title":"Hermes 4 405B","description":"Nous Research's flagship open-weight model with hybrid reasoning (toggle between standard and explicit chain-of-thought with think tags). Based on Llama 3.1, trained with rejection sampling via 1,000+ task verifiers. Known for minimal content restrictions and user-directed behavior.","last_updated":"2026-04-10","last_verified":null,"verification_status":"unverified","markdown_url":"/content/models/hermes-4-405b.md","html_url":"/models/hermes-4-405b","api_url":"/api/v1/models/hermes-4-405b.json","content_hash":"faba518cd7a696af5fb5455cefb68fe5c879d8df7eeb18cf4777d03b1088f819","sha256":"faba518cd7a696af5fb5455cefb68fe5c879d8df7eeb18cf4777d03b1088f819","provider":"Nous Research","pricing":{"input":"Free (self-hosted)","output":"Free (self-hosted)","free":true,"note":"Or via Nous Portal / OpenRouter"},"benchmarks":{"reasoning":88,"coding":84,"math":90,"writing":85,"multilingual":78,"speed":55},"tags":["nous research","open-source","text"],"website":"https://nousresearch.com","release_date":"2025-08","relationships":{"links":[],"related":[{"id":"cohere-tiny-aya","title":"Cohere Tiny Aya 3.35B","type":"model","html_url":"/models/cohere-tiny-aya","markdown_url":"/content/models/cohere-tiny-aya.md","shared_tags":["open-source","text"],"score":4},{"id":"command-r-plus","title":"Command R+","type":"model","html_url":"/models/command-r-plus","markdown_url":"/content/models/command-r-plus.md","shared_tags":["open-source","text"],"score":4},{"id":"deepseek-r1","title":"DeepSeek R1","type":"model","html_url":"/models/deepseek-r1","markdown_url":"/content/models/deepseek-r1.md","shared_tags":["open-source","text"],"score":4},{"id":"deepseek-v3.2","title":"DeepSeek V3.2","type":"model","html_url":"/models/deepseek-v3.2","markdown_url":"/content/models/deepseek-v3.2.md","shared_tags":["open-source","text"],"score":4},{"id":"falcon-3","title":"Falcon 3","type":"model","html_url":"/models/falcon-3","markdown_url":"/content/models/falcon-3.md","shared_tags":["open-source","text"],"score":4},{"id":"gemma-3","title":"Gemma 3","type":"model","html_url":"/models/gemma-3","markdown_url":"/content/models/gemma-3.md","shared_tags":["open-source","text"],"score":4}],"explicit":{}}},{"slug":"kimi-k2.5","id":"kimi-k2.5","type":"model","title":"Kimi K2.5","description":"Chinese AI model achieving 96% on AIME 2025, outperforming most proprietary models on math. Strong reasoning and mathematical capabilities.","last_updated":"2026-04-10","last_verified":null,"verification_status":"unverified","markdown_url":"/content/models/kimi-k2.5.md","html_url":"/models/kimi-k2.5","api_url":"/api/v1/models/kimi-k2.5.json","content_hash":"ab881ce9ca6e96be96c32c086c7b32453d9d521fa73913418d93fa7acd5e1520","sha256":"ab881ce9ca6e96be96c32c086c7b32453d9d521fa73913418d93fa7acd5e1520","provider":"Moonshot AI","pricing":{"input":"Free (self-hosted)","output":"Free (self-hosted)","free":true,"note":"Kimi API available"},"benchmarks":{"reasoning":93,"coding":85,"math":97,"writing":78,"multilingual":80,"speed":72},"tags":["moonshot ai","open-source","text"],"website":"https://www.moonshot.cn","release_date":"2025","relationships":{"links":[],"related":[{"id":"cohere-tiny-aya","title":"Cohere Tiny Aya 3.35B","type":"model","html_url":"/models/cohere-tiny-aya","markdown_url":"/content/models/cohere-tiny-aya.md","shared_tags":["open-source","text"],"score":4},{"id":"command-r-plus","title":"Command R+","type":"model","html_url":"/models/command-r-plus","markdown_url":"/content/models/command-r-plus.md","shared_tags":["open-source","text"],"score":4},{"id":"deepseek-r1","title":"DeepSeek R1","type":"model","html_url":"/models/deepseek-r1","markdown_url":"/content/models/deepseek-r1.md","shared_tags":["open-source","text"],"score":4},{"id":"deepseek-v3.2","title":"DeepSeek V3.2","type":"model","html_url":"/models/deepseek-v3.2","markdown_url":"/content/models/deepseek-v3.2.md","shared_tags":["open-source","text"],"score":4},{"id":"falcon-3","title":"Falcon 3","type":"model","html_url":"/models/falcon-3","markdown_url":"/content/models/falcon-3.md","shared_tags":["open-source","text"],"score":4},{"id":"gemma-3","title":"Gemma 3","type":"model","html_url":"/models/gemma-3","markdown_url":"/content/models/gemma-3.md","shared_tags":["open-source","text"],"score":4}],"explicit":{}}},{"slug":"llama-4-maverick","id":"llama-4-maverick","type":"model","title":"Llama 4 Maverick","description":"Meta's flagship open-source MoE model with 400B total parameters (17B active). Scored #2 on LMArena leaderboard (ELO 1,417). Native multimodal capabilities.","last_updated":"2026-04-10","last_verified":null,"verification_status":"unverified","markdown_url":"/content/models/llama-4-maverick.md","html_url":"/models/llama-4-maverick","api_url":"/api/v1/models/llama-4-maverick.json","content_hash":"676662087b7879291e437f5765c1cb309db3bb0227f69c8e23f32f3e584a5ba1","sha256":"676662087b7879291e437f5765c1cb309db3bb0227f69c8e23f32f3e584a5ba1","provider":"Meta","pricing":{"input":"Free (self-hosted)","output":"Free (self-hosted)","free":true,"note":"Or use via third-party APIs"},"benchmarks":{"reasoning":87,"coding":82,"math":84,"writing":86,"multilingual":84,"speed":80},"tags":["meta","open-source","text","image"],"website":"https://llama.meta.com","release_date":"2025-04","relationships":{"links":[],"related":[{"id":"llama-4-scout","title":"Llama 4 Scout","type":"model","html_url":"/models/llama-4-scout","markdown_url":"/content/models/llama-4-scout.md","shared_tags":["meta","open-source","text","image"],"score":8},{"id":"gemma-3","title":"Gemma 3","type":"model","html_url":"/models/gemma-3","markdown_url":"/content/models/gemma-3.md","shared_tags":["open-source","text","image"],"score":5},{"id":"gemma-4","title":"Gemma 4","type":"model","html_url":"/models/gemma-4","markdown_url":"/content/models/gemma-4.md","shared_tags":["open-source","text","image"],"score":5},{"id":"mistral-small-4","title":"Mistral Small 4","type":"model","html_url":"/models/mistral-small-4","markdown_url":"/content/models/mistral-small-4.md","shared_tags":["open-source","text","image"],"score":5},{"id":"qwen-3.5","title":"Qwen 3.5 397B-A17B","type":"model","html_url":"/models/qwen-3.5","markdown_url":"/content/models/qwen-3.5.md","shared_tags":["open-source","text","image"],"score":5},{"id":"claude-haiku-4.5","title":"Claude Haiku 4.5","type":"model","html_url":"/models/claude-haiku-4.5","markdown_url":"/content/models/claude-haiku-4.5.md","shared_tags":["text","image"],"score":4}],"explicit":{}}},{"slug":"llama-4-scout","id":"llama-4-scout","type":"model","title":"Llama 4 Scout","description":"Meta's efficient open-source MoE model with 109B total parameters (17B active). Features the largest context window of any model at 10M tokens.","last_updated":"2026-04-10","last_verified":null,"verification_status":"unverified","markdown_url":"/content/models/llama-4-scout.md","html_url":"/models/llama-4-scout","api_url":"/api/v1/models/llama-4-scout.json","content_hash":"bd39ae1c5f0d58eac4f04ca023b65a63d4b1957f7f373f2f2c49d159eec1b42c","sha256":"bd39ae1c5f0d58eac4f04ca023b65a63d4b1957f7f373f2f2c49d159eec1b42c","provider":"Meta","pricing":{"input":"Free (self-hosted)","output":"Free (self-hosted)","free":true},"benchmarks":{"reasoning":80,"coding":79,"math":77,"writing":81,"multilingual":79,"speed":88},"tags":["meta","open-source","text","image"],"website":"https://llama.meta.com","release_date":"2025-04","relationships":{"links":[],"related":[{"id":"llama-4-maverick","title":"Llama 4 Maverick","type":"model","html_url":"/models/llama-4-maverick","markdown_url":"/content/models/llama-4-maverick.md","shared_tags":["meta","open-source","text","image"],"score":8},{"id":"gemma-3","title":"Gemma 3","type":"model","html_url":"/models/gemma-3","markdown_url":"/content/models/gemma-3.md","shared_tags":["open-source","text","image"],"score":5},{"id":"gemma-4","title":"Gemma 4","type":"model","html_url":"/models/gemma-4","markdown_url":"/content/models/gemma-4.md","shared_tags":["open-source","text","image"],"score":5},{"id":"mistral-small-4","title":"Mistral Small 4","type":"model","html_url":"/models/mistral-small-4","markdown_url":"/content/models/mistral-small-4.md","shared_tags":["open-source","text","image"],"score":5},{"id":"qwen-3.5","title":"Qwen 3.5 397B-A17B","type":"model","html_url":"/models/qwen-3.5","markdown_url":"/content/models/qwen-3.5.md","shared_tags":["open-source","text","image"],"score":5},{"id":"claude-haiku-4.5","title":"Claude Haiku 4.5","type":"model","html_url":"/models/claude-haiku-4.5","markdown_url":"/content/models/claude-haiku-4.5.md","shared_tags":["text","image"],"score":4}],"explicit":{}}},{"slug":"minimax-m2.7","id":"minimax-m2.7","type":"model","title":"MiniMax M2.7","description":"Third iteration of MiniMax's M2 line with tighter factual accuracy and lower cost. Intelligence index of 49.62 places it near frontier models at a fraction of the price. Open weights.","last_updated":"2026-04-10","last_verified":null,"verification_status":"unverified","markdown_url":"/content/models/minimax-m2.7.md","html_url":"/models/minimax-m2.7","api_url":"/api/v1/models/minimax-m2.7.json","content_hash":"25266587c54fa84bcbbee4e33f0d7e84175ba9ddc84f54ed0c3dc102e8e9fdb7","sha256":"25266587c54fa84bcbbee4e33f0d7e84175ba9ddc84f54ed0c3dc102e8e9fdb7","provider":"MiniMax","pricing":{"input":"$0.53 / 1M tokens","output":"$0.53 / 1M tokens","free":true,"note":"Also free self-hosted"},"benchmarks":{"reasoning":90,"coding":95,"math":88,"writing":82,"multilingual":83,"speed":85},"tags":["minimax","open-source","text"],"website":"https://minimax.io","release_date":"2026-03","relationships":{"links":[],"related":[{"id":"cohere-tiny-aya","title":"Cohere Tiny Aya 3.35B","type":"model","html_url":"/models/cohere-tiny-aya","markdown_url":"/content/models/cohere-tiny-aya.md","shared_tags":["open-source","text"],"score":4},{"id":"command-r-plus","title":"Command R+","type":"model","html_url":"/models/command-r-plus","markdown_url":"/content/models/command-r-plus.md","shared_tags":["open-source","text"],"score":4},{"id":"deepseek-r1","title":"DeepSeek R1","type":"model","html_url":"/models/deepseek-r1","markdown_url":"/content/models/deepseek-r1.md","shared_tags":["open-source","text"],"score":4},{"id":"deepseek-v3.2","title":"DeepSeek V3.2","type":"model","html_url":"/models/deepseek-v3.2","markdown_url":"/content/models/deepseek-v3.2.md","shared_tags":["open-source","text"],"score":4},{"id":"falcon-3","title":"Falcon 3","type":"model","html_url":"/models/falcon-3","markdown_url":"/content/models/falcon-3.md","shared_tags":["open-source","text"],"score":4},{"id":"gemma-3","title":"Gemma 3","type":"model","html_url":"/models/gemma-3","markdown_url":"/content/models/gemma-3.md","shared_tags":["open-source","text"],"score":4}],"explicit":{}}},{"slug":"mistral-3","id":"mistral-3","type":"model","title":"Mistral 3","description":"Mistral's flagship model suite with Apache 2.0 license. A European alternative focused on enterprise compliance, adopting a DeepSeek-style MoE architecture for efficiency.","last_updated":"2026-04-10","last_verified":null,"verification_status":"unverified","markdown_url":"/content/models/mistral-3.md","html_url":"/models/mistral-3","api_url":"/api/v1/models/mistral-3.json","content_hash":"ff6095b4ec1c7eb3786e0468c5e41035ecad16e788a1f82dae1a3aca488ec94b","sha256":"ff6095b4ec1c7eb3786e0468c5e41035ecad16e788a1f82dae1a3aca488ec94b","provider":"Mistral AI","pricing":{"input":"$2.00 / 1M tokens","output":"$6.00 / 1M tokens"},"benchmarks":{"reasoning":86,"coding":87,"math":84,"writing":86,"multilingual":92,"speed":78},"tags":["mistral ai","open-source","text"],"website":"https://mistral.ai","release_date":"2025-12","relationships":{"links":[],"related":[{"id":"mistral-small-3","title":"Mistral Small 3 24B","type":"model","html_url":"/models/mistral-small-3","markdown_url":"/content/models/mistral-small-3.md","shared_tags":["mistral ai","open-source","text"],"score":7},{"id":"mistral-small-4","title":"Mistral Small 4","type":"model","html_url":"/models/mistral-small-4","markdown_url":"/content/models/mistral-small-4.md","shared_tags":["mistral ai","open-source","text"],"score":7},{"id":"cohere-tiny-aya","title":"Cohere Tiny Aya 3.35B","type":"model","html_url":"/models/cohere-tiny-aya","markdown_url":"/content/models/cohere-tiny-aya.md","shared_tags":["open-source","text"],"score":4},{"id":"command-r-plus","title":"Command R+","type":"model","html_url":"/models/command-r-plus","markdown_url":"/content/models/command-r-plus.md","shared_tags":["open-source","text"],"score":4},{"id":"deepseek-r1","title":"DeepSeek R1","type":"model","html_url":"/models/deepseek-r1","markdown_url":"/content/models/deepseek-r1.md","shared_tags":["open-source","text"],"score":4},{"id":"deepseek-v3.2","title":"DeepSeek V3.2","type":"model","html_url":"/models/deepseek-v3.2","markdown_url":"/content/models/deepseek-v3.2.md","shared_tags":["open-source","text"],"score":4}],"explicit":{}}},{"slug":"mistral-small-3","id":"mistral-small-3","type":"model","title":"Mistral Small 3 24B","description":"Efficient 24B model that competes with models 2-3x its size. Apache 2.0 license. Strong for real-time applications.","last_updated":"2026-04-10","last_verified":null,"verification_status":"unverified","markdown_url":"/content/models/mistral-small-3.md","html_url":"/models/mistral-small-3","api_url":"/api/v1/models/mistral-small-3.json","content_hash":"403f149992bfa3f3b9099a284593215e35db4500620e3d2963b5fd1ea14ee462","sha256":"403f149992bfa3f3b9099a284593215e35db4500620e3d2963b5fd1ea14ee462","provider":"Mistral AI","pricing":{"input":"Free (Apache 2.0)","output":"Free (Apache 2.0)","free":true},"benchmarks":{"reasoning":79,"coding":80,"math":77,"writing":80,"multilingual":85,"speed":90},"tags":["mistral ai","open-source","text"],"website":"https://mistral.ai","release_date":"2025","relationships":{"links":[],"related":[{"id":"mistral-3","title":"Mistral 3","type":"model","html_url":"/models/mistral-3","markdown_url":"/content/models/mistral-3.md","shared_tags":["mistral ai","open-source","text"],"score":7},{"id":"mistral-small-4","title":"Mistral Small 4","type":"model","html_url":"/models/mistral-small-4","markdown_url":"/content/models/mistral-small-4.md","shared_tags":["mistral ai","open-source","text"],"score":7},{"id":"cohere-tiny-aya","title":"Cohere Tiny Aya 3.35B","type":"model","html_url":"/models/cohere-tiny-aya","markdown_url":"/content/models/cohere-tiny-aya.md","shared_tags":["open-source","text"],"score":4},{"id":"command-r-plus","title":"Command R+","type":"model","html_url":"/models/command-r-plus","markdown_url":"/content/models/command-r-plus.md","shared_tags":["open-source","text"],"score":4},{"id":"deepseek-r1","title":"DeepSeek R1","type":"model","html_url":"/models/deepseek-r1","markdown_url":"/content/models/deepseek-r1.md","shared_tags":["open-source","text"],"score":4},{"id":"deepseek-v3.2","title":"DeepSeek V3.2","type":"model","html_url":"/models/deepseek-v3.2","markdown_url":"/content/models/deepseek-v3.2.md","shared_tags":["open-source","text"],"score":4}],"explicit":{}}},{"slug":"mistral-small-4","id":"mistral-small-4","type":"model","title":"Mistral Small 4","description":"Efficient MoE model with 119B total parameters but only 6.5B active — the knowledge capacity of a large model at the inference cost of a small one. Multimodal with hybrid reasoning. Apache 2.0 license.","last_updated":"2026-04-10","last_verified":null,"verification_status":"unverified","markdown_url":"/content/models/mistral-small-4.md","html_url":"/models/mistral-small-4","api_url":"/api/v1/models/mistral-small-4.json","content_hash":"3ec89fad7278bcd586405b60839c515f76204baab026f59598cb67ff34a8939f","sha256":"3ec89fad7278bcd586405b60839c515f76204baab026f59598cb67ff34a8939f","provider":"Mistral AI","pricing":{"input":"Free (Apache 2.0)","output":"Free (Apache 2.0)","free":true,"note":"Also via Mistral API"},"benchmarks":{"reasoning":76,"coding":78,"math":74,"writing":78,"multilingual":86,"speed":92},"tags":["mistral ai","open-source","text","image"],"website":"https://mistral.ai","release_date":"2026-03","relationships":{"links":[],"related":[{"id":"mistral-3","title":"Mistral 3","type":"model","html_url":"/models/mistral-3","markdown_url":"/content/models/mistral-3.md","shared_tags":["mistral ai","open-source","text"],"score":7},{"id":"mistral-small-3","title":"Mistral Small 3 24B","type":"model","html_url":"/models/mistral-small-3","markdown_url":"/content/models/mistral-small-3.md","shared_tags":["mistral ai","open-source","text"],"score":7},{"id":"gemma-3","title":"Gemma 3","type":"model","html_url":"/models/gemma-3","markdown_url":"/content/models/gemma-3.md","shared_tags":["open-source","text","image"],"score":5},{"id":"gemma-4","title":"Gemma 4","type":"model","html_url":"/models/gemma-4","markdown_url":"/content/models/gemma-4.md","shared_tags":["open-source","text","image"],"score":5},{"id":"llama-4-maverick","title":"Llama 4 Maverick","type":"model","html_url":"/models/llama-4-maverick","markdown_url":"/content/models/llama-4-maverick.md","shared_tags":["open-source","text","image"],"score":5},{"id":"llama-4-scout","title":"Llama 4 Scout","type":"model","html_url":"/models/llama-4-scout","markdown_url":"/content/models/llama-4-scout.md","shared_tags":["open-source","text","image"],"score":5}],"explicit":{}}},{"slug":"nemotron-3-super","id":"nemotron-3-super","type":"model","title":"Nemotron 3 Super","description":"NVIDIA's open-weight MoE model with 120B total parameters and 12B active. Designed to fit on hardware most companies already own. Serves as the anchor for NVIDIA's agent toolkit strategy, optimized for TensorRT-LLM and NIM.","last_updated":"2026-04-10","last_verified":null,"verification_status":"unverified","markdown_url":"/content/models/nemotron-3-super.md","html_url":"/models/nemotron-3-super","api_url":"/api/v1/models/nemotron-3-super.json","content_hash":"3eda34659011749da47fc3f1d62569591d4bc5bfc540d53f717ecdfcdacc795b","sha256":"3eda34659011749da47fc3f1d62569591d4bc5bfc540d53f717ecdfcdacc795b","provider":"NVIDIA","pricing":{"input":"Free (open weights)","output":"Free (open weights)","free":true,"note":"Also via NVIDIA NIM API"},"benchmarks":{"reasoning":80,"coding":82,"math":78,"writing":79,"multilingual":78,"speed":88},"tags":["nvidia","open-source","text"],"website":"https://build.nvidia.com","release_date":"2026-03","relationships":{"links":[],"related":[{"id":"nemotron-cascade-2","title":"Nemotron-Cascade 2","type":"model","html_url":"/models/nemotron-cascade-2","markdown_url":"/content/models/nemotron-cascade-2.md","shared_tags":["nvidia","open-source","text"],"score":7},{"id":"cohere-tiny-aya","title":"Cohere Tiny Aya 3.35B","type":"model","html_url":"/models/cohere-tiny-aya","markdown_url":"/content/models/cohere-tiny-aya.md","shared_tags":["open-source","text"],"score":4},{"id":"command-r-plus","title":"Command R+","type":"model","html_url":"/models/command-r-plus","markdown_url":"/content/models/command-r-plus.md","shared_tags":["open-source","text"],"score":4},{"id":"deepseek-r1","title":"DeepSeek R1","type":"model","html_url":"/models/deepseek-r1","markdown_url":"/content/models/deepseek-r1.md","shared_tags":["open-source","text"],"score":4},{"id":"deepseek-v3.2","title":"DeepSeek V3.2","type":"model","html_url":"/models/deepseek-v3.2","markdown_url":"/content/models/deepseek-v3.2.md","shared_tags":["open-source","text"],"score":4},{"id":"falcon-3","title":"Falcon 3","type":"model","html_url":"/models/falcon-3","markdown_url":"/content/models/falcon-3.md","shared_tags":["open-source","text"],"score":4}],"explicit":{}}},{"slug":"nemotron-cascade-2","id":"nemotron-cascade-2","type":"model","title":"Nemotron-Cascade 2","description":"NVIDIA's 30B MoE with only 3B active parameters that achieves gold-medal performance on IMO, IOI, and ICPC. Beats the larger Nemotron 3 Super 120B on coding and instruction following. Fits on a single RTX 4090 (24GB VRAM with Q4). Hybrid Mamba-2 + Transformer architecture enables a 1M token context window.","last_updated":"2026-04-10","last_verified":null,"verification_status":"unverified","markdown_url":"/content/models/nemotron-cascade-2.md","html_url":"/models/nemotron-cascade-2","api_url":"/api/v1/models/nemotron-cascade-2.json","content_hash":"e2169ac59e26102777a47d9984fd843bd6a7a7d460ac6de4c9cc8b3e67661f94","sha256":"e2169ac59e26102777a47d9984fd843bd6a7a7d460ac6de4c9cc8b3e67661f94","provider":"NVIDIA","pricing":{"input":"Free (open weights)","output":"Free (open weights)","free":true,"note":"Also via Ollama, NVIDIA NIM"},"benchmarks":{"reasoning":88,"coding":90,"math":92,"writing":78,"multilingual":75,"speed":92},"tags":["nvidia","open-source","text"],"website":"https://build.nvidia.com","release_date":"2026-03","relationships":{"links":[],"related":[{"id":"nemotron-3-super","title":"Nemotron 3 Super","type":"model","html_url":"/models/nemotron-3-super","markdown_url":"/content/models/nemotron-3-super.md","shared_tags":["nvidia","open-source","text"],"score":7},{"id":"cohere-tiny-aya","title":"Cohere Tiny Aya 3.35B","type":"model","html_url":"/models/cohere-tiny-aya","markdown_url":"/content/models/cohere-tiny-aya.md","shared_tags":["open-source","text"],"score":4},{"id":"command-r-plus","title":"Command R+","type":"model","html_url":"/models/command-r-plus","markdown_url":"/content/models/command-r-plus.md","shared_tags":["open-source","text"],"score":4},{"id":"deepseek-r1","title":"DeepSeek R1","type":"model","html_url":"/models/deepseek-r1","markdown_url":"/content/models/deepseek-r1.md","shared_tags":["open-source","text"],"score":4},{"id":"deepseek-v3.2","title":"DeepSeek V3.2","type":"model","html_url":"/models/deepseek-v3.2","markdown_url":"/content/models/deepseek-v3.2.md","shared_tags":["open-source","text"],"score":4},{"id":"falcon-3","title":"Falcon 3","type":"model","html_url":"/models/falcon-3","markdown_url":"/content/models/falcon-3.md","shared_tags":["open-source","text"],"score":4}],"explicit":{}}},{"slug":"phi-4","id":"phi-4","type":"model","title":"Phi-4","description":"Microsoft's small-but-capable model using state-of-the-art training techniques and high-quality data. Punches well above its weight class despite small parameter count.","last_updated":"2026-04-10","last_verified":null,"verification_status":"unverified","markdown_url":"/content/models/phi-4.md","html_url":"/models/phi-4","api_url":"/api/v1/models/phi-4.json","content_hash":"61b985ed0b24781209146be778fbb08bdbbf287cf1bfe01c24d0cb7e81d8123c","sha256":"61b985ed0b24781209146be778fbb08bdbbf287cf1bfe01c24d0cb7e81d8123c","provider":"Microsoft","pricing":{"input":"Free (open weights)","output":"Free (open weights)","free":true,"note":"MIT license"},"benchmarks":{"reasoning":78,"coding":80,"math":79,"writing":77,"multilingual":72,"speed":92},"tags":["microsoft","open-source","text"],"website":"https://azure.microsoft.com/en-us/products/phi","release_date":"2025","relationships":{"links":[],"related":[{"id":"cohere-tiny-aya","title":"Cohere Tiny Aya 3.35B","type":"model","html_url":"/models/cohere-tiny-aya","markdown_url":"/content/models/cohere-tiny-aya.md","shared_tags":["open-source","text"],"score":4},{"id":"command-r-plus","title":"Command R+","type":"model","html_url":"/models/command-r-plus","markdown_url":"/content/models/command-r-plus.md","shared_tags":["open-source","text"],"score":4},{"id":"deepseek-r1","title":"DeepSeek R1","type":"model","html_url":"/models/deepseek-r1","markdown_url":"/content/models/deepseek-r1.md","shared_tags":["open-source","text"],"score":4},{"id":"deepseek-v3.2","title":"DeepSeek V3.2","type":"model","html_url":"/models/deepseek-v3.2","markdown_url":"/content/models/deepseek-v3.2.md","shared_tags":["open-source","text"],"score":4},{"id":"falcon-3","title":"Falcon 3","type":"model","html_url":"/models/falcon-3","markdown_url":"/content/models/falcon-3.md","shared_tags":["open-source","text"],"score":4},{"id":"gemma-3","title":"Gemma 3","type":"model","html_url":"/models/gemma-3","markdown_url":"/content/models/gemma-3.md","shared_tags":["open-source","text"],"score":4}],"explicit":{}}},{"slug":"qwen-3","id":"qwen-3","type":"model","title":"Qwen 3","description":"Alibaba's flagship open model family. Overtook Llama as the most-downloaded model family on HuggingFace in late 2025. Hybrid reasoning with think/non-think modes. 119 languages supported.","last_updated":"2026-04-10","last_verified":null,"verification_status":"unverified","markdown_url":"/content/models/qwen-3.md","html_url":"/models/qwen-3","api_url":"/api/v1/models/qwen-3.json","content_hash":"101bb63231ffecd8f44c24f0e7373fcab02cf3fb0e7c30b74225e3f3e106509b","sha256":"101bb63231ffecd8f44c24f0e7373fcab02cf3fb0e7c30b74225e3f3e106509b","provider":"Alibaba","pricing":{"input":"Free (self-hosted)","output":"Free (self-hosted)","free":true,"note":"Also via Alibaba Cloud API"},"benchmarks":{"reasoning":88,"coding":90,"math":92,"writing":82,"multilingual":95,"speed":80},"tags":["alibaba","open-source","text"],"website":"https://qwenlm.github.io","release_date":"2025-06","relationships":{"links":[],"related":[{"id":"qwen-3.5","title":"Qwen 3.5 397B-A17B","type":"model","html_url":"/models/qwen-3.5","markdown_url":"/content/models/qwen-3.5.md","shared_tags":["alibaba","open-source","text"],"score":7},{"id":"provider-qwen","title":"Alibaba Qwen Provider Profile","type":"provider","html_url":"/providers/qwen","markdown_url":"/content/providers/qwen.md","shared_tags":["alibaba","open-source"],"score":4},{"id":"cohere-tiny-aya","title":"Cohere Tiny Aya 3.35B","type":"model","html_url":"/models/cohere-tiny-aya","markdown_url":"/content/models/cohere-tiny-aya.md","shared_tags":["open-source","text"],"score":4},{"id":"command-r-plus","title":"Command R+","type":"model","html_url":"/models/command-r-plus","markdown_url":"/content/models/command-r-plus.md","shared_tags":["open-source","text"],"score":4},{"id":"deepseek-r1","title":"DeepSeek R1","type":"model","html_url":"/models/deepseek-r1","markdown_url":"/content/models/deepseek-r1.md","shared_tags":["open-source","text"],"score":4},{"id":"deepseek-v3.2","title":"DeepSeek V3.2","type":"model","html_url":"/models/deepseek-v3.2","markdown_url":"/content/models/deepseek-v3.2.md","shared_tags":["open-source","text"],"score":4}],"explicit":{}}},{"slug":"qwen-3.5","id":"qwen-3.5","type":"model","title":"Qwen 3.5 397B-A17B","description":"Alibaba's generational leap. Natively multimodal, 256K context, 201 languages. The flagship 397B-A17B MoE model activates only 17B parameters per token. Apache 2.0. Most downloaded model family on HuggingFace.","last_updated":"2026-04-10","last_verified":null,"verification_status":"unverified","markdown_url":"/content/models/qwen-3.5.md","html_url":"/models/qwen-3.5","api_url":"/api/v1/models/qwen-3.5.json","content_hash":"e6f1fe3693f685475bfb8c819995c27a29bee4321a03ed12249578b68fb6198f","sha256":"e6f1fe3693f685475bfb8c819995c27a29bee4321a03ed12249578b68fb6198f","provider":"Alibaba","pricing":{"input":"Free (self-hosted)","output":"Free (self-hosted)","free":true,"note":"Alibaba Cloud API available"},"benchmarks":{"reasoning":91,"coding":92,"math":94,"writing":84,"multilingual":97,"speed":82},"tags":["alibaba","open-source","text","image"],"website":"https://qwenlm.github.io","release_date":"2026-02","relationships":{"links":[],"related":[{"id":"qwen-3","title":"Qwen 3","type":"model","html_url":"/models/qwen-3","markdown_url":"/content/models/qwen-3.md","shared_tags":["alibaba","open-source","text"],"score":7},{"id":"gemma-3","title":"Gemma 3","type":"model","html_url":"/models/gemma-3","markdown_url":"/content/models/gemma-3.md","shared_tags":["open-source","text","image"],"score":5},{"id":"gemma-4","title":"Gemma 4","type":"model","html_url":"/models/gemma-4","markdown_url":"/content/models/gemma-4.md","shared_tags":["open-source","text","image"],"score":5},{"id":"llama-4-maverick","title":"Llama 4 Maverick","type":"model","html_url":"/models/llama-4-maverick","markdown_url":"/content/models/llama-4-maverick.md","shared_tags":["open-source","text","image"],"score":5},{"id":"llama-4-scout","title":"Llama 4 Scout","type":"model","html_url":"/models/llama-4-scout","markdown_url":"/content/models/llama-4-scout.md","shared_tags":["open-source","text","image"],"score":5},{"id":"mistral-small-4","title":"Mistral Small 4","type":"model","html_url":"/models/mistral-small-4","markdown_url":"/content/models/mistral-small-4.md","shared_tags":["open-source","text","image"],"score":5}],"explicit":{}}},{"slug":"smollm3-3b","id":"smollm3-3b","type":"model","title":"SmolLM3 3B","description":"Fully open instruct and reasoning model with unprecedented transparency — Hugging Face published the complete engineering blueprint. Outperforms Llama-3.2-3B and Qwen2.5-3B at the 3B scale.","last_updated":"2026-04-10","last_verified":null,"verification_status":"unverified","markdown_url":"/content/models/smollm3-3b.md","html_url":"/models/smollm3-3b","api_url":"/api/v1/models/smollm3-3b.json","content_hash":"6872d71c66e72321804ed4e3d60798a018517d03fa5ddebb51679042be9a6b12","sha256":"6872d71c66e72321804ed4e3d60798a018517d03fa5ddebb51679042be9a6b12","provider":"Hugging Face","pricing":{"input":"Free (Apache 2.0)","output":"Free (Apache 2.0)","free":true},"benchmarks":{"reasoning":68,"coding":70,"math":66,"writing":70,"multilingual":65,"speed":96},"tags":["hugging face","open-source","text"],"website":"https://huggingface.co/HuggingFaceTB/SmolLM3-3B","release_date":"2026","relationships":{"links":[],"related":[{"id":"cohere-tiny-aya","title":"Cohere Tiny Aya 3.35B","type":"model","html_url":"/models/cohere-tiny-aya","markdown_url":"/content/models/cohere-tiny-aya.md","shared_tags":["open-source","text"],"score":4},{"id":"command-r-plus","title":"Command R+","type":"model","html_url":"/models/command-r-plus","markdown_url":"/content/models/command-r-plus.md","shared_tags":["open-source","text"],"score":4},{"id":"deepseek-r1","title":"DeepSeek R1","type":"model","html_url":"/models/deepseek-r1","markdown_url":"/content/models/deepseek-r1.md","shared_tags":["open-source","text"],"score":4},{"id":"deepseek-v3.2","title":"DeepSeek V3.2","type":"model","html_url":"/models/deepseek-v3.2","markdown_url":"/content/models/deepseek-v3.2.md","shared_tags":["open-source","text"],"score":4},{"id":"falcon-3","title":"Falcon 3","type":"model","html_url":"/models/falcon-3","markdown_url":"/content/models/falcon-3.md","shared_tags":["open-source","text"],"score":4},{"id":"gemma-3","title":"Gemma 3","type":"model","html_url":"/models/gemma-3","markdown_url":"/content/models/gemma-3.md","shared_tags":["open-source","text"],"score":4}],"explicit":{}}},{"slug":"yi-1.5-34b","id":"yi-1.5-34b","type":"model","title":"Yi-1.5 34B","description":"Strong bilingual (English/Chinese) model from 01.AI that competes with much larger models on benchmarks. Excellent reasoning and code generation at a deployable 34B size. Apache 2.0 license.","last_updated":"2026-04-10","last_verified":null,"verification_status":"unverified","markdown_url":"/content/models/yi-1.5-34b.md","html_url":"/models/yi-1.5-34b","api_url":"/api/v1/models/yi-1.5-34b.json","content_hash":"f36c16df029a54e4c586ea6a91a93956de84f9eefcacf6db13e6fed78881c3f8","sha256":"f36c16df029a54e4c586ea6a91a93956de84f9eefcacf6db13e6fed78881c3f8","provider":"01.AI","pricing":{"input":"Free (Apache 2.0)","output":"Free (Apache 2.0)","free":true},"benchmarks":{"reasoning":80,"coding":79,"math":78,"writing":80,"multilingual":82,"speed":85},"tags":["01.ai","open-source","text"],"website":"https://01.ai","release_date":"2025","relationships":{"links":[],"related":[{"id":"cohere-tiny-aya","title":"Cohere Tiny Aya 3.35B","type":"model","html_url":"/models/cohere-tiny-aya","markdown_url":"/content/models/cohere-tiny-aya.md","shared_tags":["open-source","text"],"score":4},{"id":"command-r-plus","title":"Command R+","type":"model","html_url":"/models/command-r-plus","markdown_url":"/content/models/command-r-plus.md","shared_tags":["open-source","text"],"score":4},{"id":"deepseek-r1","title":"DeepSeek R1","type":"model","html_url":"/models/deepseek-r1","markdown_url":"/content/models/deepseek-r1.md","shared_tags":["open-source","text"],"score":4},{"id":"deepseek-v3.2","title":"DeepSeek V3.2","type":"model","html_url":"/models/deepseek-v3.2","markdown_url":"/content/models/deepseek-v3.2.md","shared_tags":["open-source","text"],"score":4},{"id":"falcon-3","title":"Falcon 3","type":"model","html_url":"/models/falcon-3","markdown_url":"/content/models/falcon-3.md","shared_tags":["open-source","text"],"score":4},{"id":"gemma-3","title":"Gemma 3","type":"model","html_url":"/models/gemma-3","markdown_url":"/content/models/gemma-3.md","shared_tags":["open-source","text"],"score":4}],"explicit":{}}}]}