Loading
90 days of the enterprise, pro and team plans free, no card needed. See the plans
Rankings
Published listings ranked per kind: the most installed, the best rated (a Bayesian average that a single five-star review cannot top) and the newest. Every row links to the listing; publishers appear by name.
| # | Listing | Publisher | Installs | Rating | Version | Updated |
|---|
Raw numbers: /api/v1/rankings/listings and the kinds at /api/v1/rankings/listings/kinds. Browse everything on the marketplace.
Photo: RDNE Stock project
| 1 | Ternary Bonsai 2 9B is PrismML’s compact, open-weight language model for conversational AI, reasoning, and tool use. Built on Qwen3.5, it uses ternary weights packed into 2 bits for efficient... | Prism Ml | 0 | (0) | 1.0.0 | Oct 28, 2026 |
| 2 | GPT-6.1 Terra Pro is the same underlying model as GPT-6.1 Terra, served with reasoning.mode set to pro for higher-quality responses on complex tasks. Cost note: pro mode spends far more... | OpenAI | 0 | (0) | 1.0.0 | Oct 27, 2026 |
| 3 | GPT-6.1 Terra Pro is the same underlying model as GPT-6.1 Terra, served with reasoning.mode set to pro for higher-quality responses on complex tasks. Cost note: pro mode spends far more... | OpenAI | 0 | (0) | 1.0.0 | Oct 27, 2026 |
| 4 | GPT-6.1 Terra is the mid-tier model in OpenAI's GPT-6.1 series, priced below GPT-6.1 Sol. It is suited for everyday agentic, coding, and writing work, is particularly strong at understanding… | OpenAI | 0 | (0) | 1.0.0 | Oct 27, 2026 |
| 5 | GPT-6.1 Terra is the mid-tier model in OpenAI's GPT-6.1 series, priced below GPT-6.1 Sol. It is suited for everyday agentic, coding, and writing work, is particularly strong at understanding… | OpenAI | 0 | (0) | 1.0.0 | Oct 27, 2026 |
| 6 | LFM2.5-2.6B is a compact reasoning model from Liquid AI. It is suited for agent workflows, data extraction, RAG, and long-context processing. Liquid advises against using it for agentic coding or... | Liquid AI | 0 | (0) | 1.0.0 | Oct 25, 2026 |
| 7 | Kimi K3.1 Pro is Moonshot AI's flagship open-weight multimodal reasoning model and a post-trained successor to Kimi K3, with a 1M-token context window. It is built for long-horizon coding, 3D... | Moonshot AI | 0 | (0) | 1.0.0 | Oct 24, 2026 |
| 8 | MiniMax-M3.1-Flash is a multimodal model from MiniMax. Compared with M3, it delivers significant improvements across multiple benchmarks, particularly in complex agentic tasks, coding, and… | MiniMax | 0 | (0) | 1.0.0 | Oct 23, 2026 |
| 9 | Flint is an open-weight mixture-of-experts model from Recursive, with about 2.5B active parameters out of 40B total, built by Recursive's autoresearch system Eureka Machine for coding agents. | Recursive | 0 | (0) | 1.0.0 | Oct 22, 2026 |
| 10 | MiniMax-M3.1-Flash is a multimodal model from MiniMax. Compared with M3, it delivers significant improvements across multiple benchmarks, particularly in complex agentic tasks, coding, and… | MiniMax | 0 | (0) | 1.0.0 | Oct 20, 2026 |
| 11 | Inception | 0 | (0) | 1.0.0 | Oct 27, 2026 | |
| 12 | Pareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance across a broad range of general-purpose tasks. | Unbiased | 0 | (0) | 1.0.0 | Oct 25, 2026 |
| 13 | DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the deepseek-flash API model name. V4.1 Flash is a sparse mixture-of-experts model... | DeepSeek | 0 | (0) | 1.0.0 | Oct 24, 2026 |
| 14 | Elorian | 0 | (0) | 1.0.0 | Oct 24, 2026 | |
| 15 | Xing4.0-29B-A4B is an open-weight mixture-of-experts language model from China Telecom's AI team (TeleAI) and the successor to the TeleChat series. | Xingchen Agi | 0 | (0) | 1.0.0 | Oct 24, 2026 |
| 16 | Beam 1.0 is Reflection's open-weight reasoning model for coding and long-horizon agentic workflows. It uses a sparse mixture-of-experts architecture with 501B total and 23B active parameters per… | Reflection | 0 | (0) | 1.0.0 | Oct 24, 2026 |
| 17 | Moondream 3 Preview is a vision-language model from Moondream with 9B total parameters and 2B active (mixture-of-experts). | Moondream | 0 | (0) | 1.0.0 | Oct 24, 2026 |
| 18 | Moondream 3.1 is a vision-language model from Moondream, the successor to Moondream 3 Preview, with 9B total parameters and 2B active (mixture-of-experts). | Moondream | 0 | (0) | 1.0.0 | Oct 24, 2026 |
| 19 | Muse Spark Open is a coding-optimized open-weight model. Trained specifically for agentic coding workflows, it delivers higher first-attempt accuracy, reliable tool calling, and deep codebase… | Meta | 0 | (0) | 1.0.0 | Oct 24, 2026 |
| 20 | NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total. It takes text, images, documents, GUI screenshots, and video... | NVIDIA | 0 | (0) | 1.0.0 | Oct 24, 2026 |
| 21 | NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total. It takes text, images, documents, GUI screenshots, and video... | NVIDIA | 0 | (0) | 1.0.0 | Oct 24, 2026 |
| 22 | This model always redirects to the latest model in the Pareto family. | Unbiased | 0 | (0) | 1.0.0 | Oct 24, 2026 |
| 23 | Pareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance across a broad range of general-purpose tasks. | Unbiased | 0 | (0) | 1.0.0 | Oct 24, 2026 |
| 24 | LFM2.5-24B-A2B is a mixture-of-experts reasoning model from Liquid AI with 24B total and 2.45B active parameters. It always reasons before answering and is built for agents that call tools. Liquid... | Liquid AI | 0 | (0) | 1.0.0 | Oct 24, 2026 |
| 25 | Gemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem solving, and autonomous multi-step agents. | 0 | (0) | 1.0.0 | Oct 24, 2026 | |
| 26 | Gemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem solving, and autonomous multi-step agents. | 0 | (0) | 1.0.0 | Oct 24, 2026 | |
| 27 | Scaledown | 0 | (0) | 1.0.0 | Oct 24, 2026 | |
| 28 | Scaledown | 0 | (0) | 1.0.0 | Oct 24, 2026 | |
| 29 | Muse Wonder is a frontier reasoning model from Meta, designed for complex personal and professional agentic tasks. It accepts text, images, video, audio, and PDF documents and returns text, with... | Meta | 0 | (0) | 1.0.0 | Oct 24, 2026 |
| 30 | Step 5 Preview is StepFun's flagship model for agentic work, built on a sparse Mixture-of-Experts architecture (27B active / 600B total parameters). | StepFun | 0 | (0) | 1.0.0 | Oct 24, 2026 |
| 31 | Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use. | Anthropic | 0 | (0) | 1.0.0 | Oct 24, 2026 |
| 32 | Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use. | Anthropic | 0 | (0) | 1.0.0 | Oct 24, 2026 |
| 33 | Nano Banana 2.1 (Gemini Nano Banana 2.1) is Google's image generation and editing model on the Flash tier, succeeding Nano Banana 2 and Nano Banana Pro. It improves product recontextualization,... | 0 | (0) | 1.0.0 | Oct 24, 2026 | |
| 34 | Mistral Large 4 is a frontier multimodal (text and image input) model from Mistral AI built for reasoning, coding, and agentic workloads. It offers a 1M-token context window with up... | Mistral AI | 0 | (0) | 1.0.0 | Oct 24, 2026 |
| 35 | Ling 3.1 Flash is a hybrid reasoning mixture-of-experts model from inclusionAI, with 25B active parameters out of 560B total. | inclusionAI | 0 | (0) | 1.0.0 | Oct 24, 2026 |
| 36 | GPT-6.1 Sol Pro is the same underlying model as GPT-6.1 Sol, served with reasoning.mode set to pro for higher-quality responses on complex tasks. Cost note: pro mode spends far more... | OpenAI | 0 | (0) | 1.0.0 | Oct 24, 2026 |
| 37 | GPT-6.1 Sol Pro is the same underlying model as GPT-6.1 Sol, served with reasoning.mode set to pro for higher-quality responses on complex tasks. Cost note: pro mode spends far more... | OpenAI | 0 | (0) | 1.0.0 | Oct 24, 2026 |
| 38 | GPT-6.1 Sol is an upgrade to GPT-6 Sol from OpenAI, positioned below the flagship GPT-6 Astra in the GPT-6 series. It is suited for agentic coding, computer use, document-heavy professional... | OpenAI | 0 | (0) | 1.0.0 | Oct 24, 2026 |
| 39 | GPT-6.1 Sol is an upgrade to GPT-6 Sol from OpenAI, positioned below the flagship GPT-6 Astra in the GPT-6 series. It is suited for agentic coding, computer use, document-heavy professional... | OpenAI | 0 | (0) | 1.0.0 | Oct 24, 2026 |
| 40 | Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, succeeding Claude Sonnet 5 as a direct upgrade. | Anthropic | 0 | (0) | 1.0.0 | Oct 24, 2026 |
| 41 | Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, succeeding Claude Sonnet 5 as a direct upgrade. | Anthropic | 0 | (0) | 1.0.0 | Oct 24, 2026 |
| 42 | Jev Router picks the best model and reasoning effort for each request, balancing quality, speed, and cost. It runs on Jev, TypeSafe's first System One model, and adapts as your... | Typesafe | 0 | (0) | 1.0.0 | Oct 24, 2026 |
| 43 | Perceptron Mk1.5 is Perceptron's embodied reasoning model for physical agents. It accepts text, image, video, and audio input, and answers with text plus optional structured annotations: points… | Perceptron | 0 | (0) | 1.0.0 | Oct 24, 2026 |
| 44 | Fireworks | 0 | (0) | 1.0.0 | Oct 24, 2026 | |
| 45 | GLM-5.3-Prime is the high-speed variant of Z.ai's GLM-5.3, inheriting its full capabilities while delivering 1.5–2× the output throughput through inference acceleration. | Z.ai | 0 | (0) | 1.0.0 | Oct 24, 2026 |
| 46 | Qwen3.8 Max Prime is a higher-throughput variant of Qwen3.8 Max from Alibaba's Qwen team, served as a separate SKU at a higher price point. It accepts text, image, and video... | Qwen | 0 | (0) | 1.0.0 | Oct 24, 2026 |
| 47 | Aion 3.5 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It is the smaller, lower-cost sibling of Aion 3.5 and uses... | Aion Labs | 0 | (0) | 1.0.0 | Oct 24, 2026 |
| 48 | Aion Labs | 0 | (0) | 1.0.0 | Oct 24, 2026 | |
| 49 | Solar Mini 4 is Upstage's compact, cost-efficient language model, a 35B-parameter mixture-of-experts with 3B active parameters and a 524K context window. | Upstage | 0 | (0) | 1.0.0 | Oct 24, 2026 |
| 50 | Command A+ is Cohere's flagship model for enterprise agentic workflows. It accepts text and image inputs with a 192K context window, supports native tool calling with strict tool schemas… | Cohere | 0 | (0) | 1.0.0 | Oct 24, 2026 |
| 51 | GPT-6 Luna Pro is the same underlying model as GPT-6 Luna, served with reasoning.mode set to pro for higher-quality responses on complex tasks. Cost note: pro mode spends far more... | OpenAI | 0 | (0) | 1.0.0 | Oct 24, 2026 |
| 52 | GPT-6 Luna Pro is the same underlying model as GPT-6 Luna, served with reasoning.mode set to pro for higher-quality responses on complex tasks. Cost note: pro mode spends far more... | OpenAI | 0 | (0) | 1.0.0 | Oct 24, 2026 |
| 53 | GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol. It is suited for high-volume and latency-sensitive workloads such as chat, classification, and… | OpenAI | 0 | (0) | 1.0.0 | Oct 24, 2026 |
| 54 | GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol. It is suited for high-volume and latency-sensitive workloads such as chat, classification, and… | OpenAI | 0 | (0) | 1.0.0 | Oct 24, 2026 |
| 55 | GPT-6 Sol Pro is the same underlying model as GPT-6 Sol, served with reasoning.mode set to pro for higher-quality responses on complex tasks. Cost note: pro mode spends far more... | OpenAI | 0 | (0) | 1.0.0 | Oct 24, 2026 |
| 56 | GPT-6 Sol Pro is the same underlying model as GPT-6 Sol, served with reasoning.mode set to pro for higher-quality responses on complex tasks. Cost note: pro mode spends far more... | OpenAI | 0 | (0) | 1.0.0 | Oct 24, 2026 |
| 57 | OpenAI | 0 | (0) | 1.0.0 | Oct 24, 2026 | |
| 58 | GPT-6 Sol is the cost-efficient high-end model in OpenAI's GPT-6 series, positioned below the flagship GPT-6 Astra and above the fast GPT-6 Luna tier. It is suited for demanding professional... | OpenAI | 0 | (0) | 1.0.0 | Oct 24, 2026 |
| 59 | Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5. | Anthropic | 0 | (0) | 1.0.0 | Oct 24, 2026 |
| 60 | Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5. | Anthropic | 0 | (0) | 1.0.0 | Oct 24, 2026 |
| 61 | Switchyard is an open-source model router that switches between multiple models to optimize the cost of requests. By default it will use OpenRouter market data to select the most popular... | NVIDIA | 0 | (0) | 1.0.0 | Oct 24, 2026 |
| 62 | MiMo-V2.6-Pro-UltraSpeed is the fast speed edition of Xiaomi's flagship foundation model, MiMo-V2.6-Pro. | Xiaomi | 0 | (0) | 1.0.0 | Oct 24, 2026 |
| 63 | MiMo-V2.6-Flash is an open-source foundation model developed by Xiaomi. Built on a Mixture-of-Experts architecture with 309B total parameters and 15B activated per token, it employs a hybrid… | Xiaomi | 0 | (0) | 1.0.0 | Oct 24, 2026 |
| 64 | MiMo-V2.6-Pro is the flagship foundation model developed by Xiaomi. Built at a scale of over 1T parameters, it is designed to push the ceiling of capability for the most demanding... | Xiaomi | 0 | (0) | 1.0.0 | Oct 24, 2026 |
| 65 | xAI | 0 | (0) | 1.0.0 | Oct 24, 2026 | |
| 66 | Qwen3.8 Omni Flash is an omni-modal reasoning model from Alibaba, the first Qwen model built around agentic capabilities with native audio-video understanding. | Qwen | 0 | (0) | 1.0.0 | Oct 24, 2026 |
| 67 | Bonsai 2 27B is a 27B-parameter reasoning model from PrismML derived from Qwen3.8-27B. It supports coding, mathematics, tool calling, and image understanding with a 262K-token context window. | Prism Ml | 0 | (0) | 1.0.0 | Oct 24, 2026 |
| 68 | GLM-5.3-FlashX is the high-speed variant of Z.ai's GLM-5.3-Flash, a native multimodal model delivering inference speeds of up to 200 tokens/s. | Z.ai | 0 | (0) | 1.0.0 | Oct 24, 2026 |
| 69 | This model always redirects to the latest model in the DeepSeek Pro family. | DeepSeek | 0 | (0) | 1.0.0 | Oct 24, 2026 |
| 70 | This model always redirects to the latest model in the DeepSeek Flash family. | DeepSeek | 0 | (0) | 1.0.0 | Oct 24, 2026 |
| 71 | Schematron V2 Turbo is a 3B-parameter HTML-to-JSON extraction model from Inference.net. It prioritizes throughput for high-volume extraction workloads. | Inference Net | 0 | (0) | 1.0.0 | Oct 24, 2026 |
| 72 | Schematron V2 Small is a 3B-parameter HTML-to-JSON extraction model from Inference.net. It prioritizes extraction quality for complex schemas and long pages. | Inference Net | 0 | (0) | 1.0.0 | Oct 24, 2026 |
| 73 | This model always redirects to the latest model in the GPT Astra family. | OpenAI | 0 | (0) | 1.0.0 | Oct 24, 2026 |
| 74 | This model always redirects to the latest model in the GPT Sol family. | OpenAI | 0 | (0) | 1.0.0 | Oct 24, 2026 |
| 75 | This model always redirects to the latest model in the GPT Terra family. | OpenAI | 0 | (0) | 1.0.0 | Oct 24, 2026 |
| 76 | This model always redirects to the latest model in the GPT Luna family. | OpenAI | 0 | (0) | 1.0.0 | Oct 24, 2026 |
| 77 | Fugu Ultra v2 is the higher-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language model trained to... | Sakana | 0 | (0) | 1.0.0 | Oct 24, 2026 |
| 78 | Sakana | 0 | (0) | 1.0.0 | Oct 24, 2026 | |
| 79 | Ling 3.0 Flash VL builds on Ling 3.0 Flash (124B total / 5.5B active MoE from InclusionAI), further strengthening its language capabilities while adding native visual perception and advanced visual... | inclusionAI | 0 | (0) | 1.0.0 | Oct 24, 2026 |
| 80 | DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. | DeepSeek | 0 | (0) | 1.0.0 | Oct 24, 2026 |
| 81 | DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. | DeepSeek | 0 | (0) | 1.0.0 | Oct 24, 2026 |
| 82 | Mercury 2.5 is the fastest reasoning LLM, and the latest diffusion LLM (dLLM) from Inception. Instead of generating tokens sequentially, Mercury 2.5 produces and refines multiple tokens in parallel… | Inception | 0 | (0) | 1.0.0 | Oct 24, 2026 |
| 83 | Nex-N2.5 is an agentic model built to turn goals into working, verified outcomes. Its core strength is agentic coding within a visual feedback loop: it can explore codebases, implement multi-file... | Nex Agi | 0 | (0) | 1.0.0 | Oct 24, 2026 |
| 84 | Nex-N2.5 is an agentic model built to turn goals into working, verified outcomes. Its core strength is agentic coding within a visual feedback loop: it can explore codebases, implement multi-file... | Nex Agi | 0 | (0) | 1.0.0 | Oct 24, 2026 |
| 85 | GPT-6 Astra is OpenAI's flagship model for demanding end-to-end work. It is suited for advanced analysis, software engineering, deep research, scientific work, and document creation, with particular… | OpenAI | 0 | (0) | 1.0.0 | Oct 24, 2026 |
| 86 | GPT-6 Astra is OpenAI's flagship model for demanding end-to-end work. It is suited for advanced analysis, software engineering, deep research, scientific work, and document creation, with particular… | OpenAI | 0 | (0) | 1.0.0 | Oct 24, 2026 |
| 87 | GPT-6 Astra Pro is the same underlying model as GPT-6 Astra, served with reasoning.mode set to pro for higher-quality responses on complex tasks. Cost note: pro mode spends far more... | OpenAI | 0 | (0) | 1.0.0 | Oct 24, 2026 |
| 88 | GPT-6 Astra Pro is the same underlying model as GPT-6 Astra, served with reasoning.mode set to pro for higher-quality responses on complex tasks. Cost note: pro mode spends far more... | OpenAI | 0 | (0) | 1.0.0 | Oct 24, 2026 |
| 89 | Qwen3.8 Max 0902 is an updated snapshot of Qwen3.8 Max from Alibaba's Qwen team. It is a 2.4-trillion-parameter mixture-of-experts model that accepts text, image, and video input and returns text,... | Qwen | 0 | (0) | 1.0.0 | Oct 24, 2026 |
| 90 | Muse Spark 1.3 Contributor is the cost-efficient contributor tier of Meta’s multimodal reasoning model for experimentation, learning, and early-stage agentic, multi-agent, and coding workflows. | Meta | 0 | (0) | 1.0.0 | Oct 24, 2026 |
| 91 | Muse Spark 1.3 is a multimodal reasoning model from Meta for long-running agentic, multi-agent, and coding workflows. It is designed to keep track of information across extended tasks, work through... | Meta | 0 | (0) | 1.0.0 | Oct 24, 2026 |
| 92 | Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning. | 0 | (0) | 1.0.0 | Oct 24, 2026 | |
| 93 | Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning. | 0 | (0) | 1.0.0 | Oct 24, 2026 | |
| 94 | Claude Fable 5.1 improves on Claude Fable 5 across the board, with the biggest gains in agentic coding, long-running agentic workflows, and knowledge work: long code refactors, front-end and visual... | Anthropic | 0 | (0) | 1.0.0 | Oct 24, 2026 |
| 95 | Claude Fable 5.1 improves on Claude Fable 5 across the board, with the biggest gains in agentic coding, long-running agentic workflows, and knowledge work: long code refactors, front-end and visual... | Anthropic | 0 | (0) | 1.0.0 | Oct 24, 2026 |
| 96 | Granite 4.2 8B is a dense reasoning model from IBM. It is suited for mathematics, code generation, multilingual dialogue, and agentic workflows that need multi-step reasoning. | Ibm Granite | 0 | (0) | 1.0.0 | Oct 24, 2026 |
| 97 | Tencent: Hy4 preview is a mixture-of-experts model from Tencent, with 49B active parameters out of 770B total. | Tencent | 0 | (0) | 1.0.0 | Oct 24, 2026 |
| 98 | This model always redirects to the latest model in the GLM Flash family. | Z.ai | 0 | (0) | 1.0.0 | Oct 24, 2026 |
| 99 | Qwen3.8 Flash is a multimodal reasoning model from Alibaba. It is suited for coding assistance, agentic workflows, visual understanding, document and codebase analysis, desktop interaction, chart… | Qwen | 0 | (0) | 1.0.0 | Oct 24, 2026 |
| 100 | GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. | Z.ai | 0 | (0) | 1.0.0 | Oct 24, 2026 |
482 published models; ratings are a Bayesian average - the mean shrunk towards 3.5 until 5 ratings are in - so one five-star review does not top the chart. Publishers appear by name only.
The catalogue prints input and output prices and what three typical monthly workloads cost on each.
Free plan, no card. Fifteen thousand decisions a month with the full trace.
