Loading
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 |
|---|---|---|---|---|---|---|
| 1 | 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. Ternary | Prism Ml | 0 |
455 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.
Raw numbers: /api/v1/rankings/listings and the kinds at /api/v1/rankings/listings/kinds. Browse everything on the marketplace.
| 1.0.0 |
| Sep 20, 2026 |
| 2 | 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. Built on the same hybrid sparse and linear attention arch | Z.ai | 0 | (0) | 1.0.0 | Sep 20, 2026 |
| 3 | Unbiased | 0 | (0) | 1.0.0 | Sep 19, 2026 |
| 4 | Qwen3.8 27B is an open-weight dense vision-language model from Qwen. It is suited for coding, professional workflows, research, multimodal interaction, and long-running agent tasks, with flexible thin | Qwen | 0 | (0) | 1.0.0 | Sep 19, 2026 |
| 5 | DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workfl | DeepSeek | 0 | (0) | 1.0.0 | Sep 19, 2026 |
| 6 | Union Alpha is a multimodal model built for research, coding, and agentic workflows, while delivering frontier-level performance across a broad range of general-purpose tasks. Union Alpha is a stealth | Stealth | 0 | (0) | 1.0.0 | Sep 17, 2026 |
| 7 | GLM 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for long-horizon agent workflows, project-level software engineering | Z.ai | 0 | (0) | 1.0.0 | Sep 16, 2026 |
| 8 | This model always redirects to the latest model in the DeepSeek Pro family. | DeepSeek | 0 | (0) | 1.0.0 | Sep 15, 2026 |
| 9 | This model always redirects to the latest model in the DeepSeek Flash family. | DeepSeek | 0 | (0) | 1.0.0 | Sep 15, 2026 |
| 10 | Schematron V2 Turbo is a 3B-parameter HTML-to-JSON extraction model from Inference.net. It prioritizes throughput for high-volume extraction workloads. Extraction instructions must be supplied through | Inference Net | 0 | (0) | 1.0.0 | Sep 20, 2026 |
| 11 | 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. Extraction instructions must be supplied t | Inference Net | 0 | (0) | 1.0.0 | Sep 20, 2026 |
| 12 | This model always redirects to the latest model in the GPT Astra family. | OpenAI | 0 | (0) | 1.0.0 | Sep 19, 2026 |
| 13 | This model always redirects to the latest model in the GPT Sol family. | OpenAI | 0 | (0) | 1.0.0 | Sep 19, 2026 |
| 14 | This model always redirects to the latest model in the GPT Terra family. | OpenAI | 0 | (0) | 1.0.0 | Sep 19, 2026 |
| 15 | This model always redirects to the latest model in the GPT Luna family. | OpenAI | 0 | (0) | 1.0.0 | Sep 19, 2026 |
| 16 | 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 | Sep 19, 2026 |
| 17 | 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 | Sep 19, 2026 |
| 18 | Sakana | 0 | (0) | 1.0.0 | Sep 19, 2026 |
| 19 | 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 | Sep 19, 2026 |
| 20 | 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. It activates 8B parameters on input and 16B on.. | DeepSeek | 0 | (0) | 1.0.0 | Sep 19, 2026 |
| 21 | 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, a | Inception | 0 | (0) | 1.0.0 | Sep 19, 2026 |
| 22 | 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 | Sep 19, 2026 |
| 23 | 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 | Sep 19, 2026 |
| 24 | 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 s | OpenAI | 0 | (0) | 1.0.0 | Sep 19, 2026 |
| 25 | 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 s | OpenAI | 0 | (0) | 1.0.0 | Sep 19, 2026 |
| 26 | GPT-6 Astra Pro is the same underlying model as [GPT-6 Astra](https://openrouter.ai/openai/gpt-6-astra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. Learn | OpenAI | 0 | (0) | 1.0.0 | Sep 19, 2026 |
| 27 | GPT-6 Astra Pro is the same underlying model as [GPT-6 Astra](https://openrouter.ai/openai/gpt-6-astra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. Learn | OpenAI | 0 | (0) | 1.0.0 | Sep 19, 2026 |
| 28 | Ling 3.0 Flash Sante is a health and medicine-focused mixture-of-experts model from InclusionAI, built on Ling 3.0 Flash with 5.1B active parameters out of 124B total. It is designed for... | inclusionAI | 0 | (0) | 1.0.0 | Sep 19, 2026 |
| 29 | 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 | Sep 19, 2026 |
| 30 | 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. It is | Meta | 0 | (0) | 1.0.0 | Sep 19, 2026 |
| 31 | 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 | Sep 19, 2026 |
| 32 | 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 | Sep 19, 2026 |
| 33 | 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 | Sep 19, 2026 |
| 34 | 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 | Sep 19, 2026 |
| 35 | 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 | Sep 19, 2026 |
| 36 | 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. It supports full, low-ef | Ibm Granite | 0 | (0) | 1.0.0 | Sep 19, 2026 |
| 37 | Tencent: Hy4 preview is a mixture-of-experts model from Tencent, with 49B active parameters out of 770B total. It is designed for coding agents, complex tool-use workflows, and productivity tasks that | Tencent | 0 | (0) | 1.0.0 | Sep 19, 2026 |
| 38 | Ling 3.0 Flash Fin is a finance-focused mixture-of-experts model from InclusionAI, built on Ling 3.0 Flash with 5.1B active parameters out of 124B total. It is designed for real-world investment... | inclusionAI | 0 | (0) | 1.0.0 | Sep 19, 2026 |
| 39 | Ling 3.0 Flash Fin is a finance-focused mixture-of-experts model from InclusionAI, built on Ling 3.0 Flash with 5.1B active parameters out of 124B total. It is designed for real-world investment... | inclusionAI | 0 | (0) | 1.0.0 | Sep 19, 2026 |
| 40 | This model always redirects to the latest model in the GLM Flash family. | Z.ai | 0 | (0) | 1.0.0 | Sep 19, 2026 |
| 41 | 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 anal | Qwen | 0 | (0) | 1.0.0 | Sep 19, 2026 |
| 42 | GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention architecture maintains accurate long-contex | Z.ai | 0 | (0) | 1.0.0 | Sep 19, 2026 |
| 43 | GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention architecture maintains accurate long-contex | Z.ai | 0 | (0) | 1.0.0 | Sep 19, 2026 |
| 44 | Muse Spark 1.2 contributor tier is a reasoning model from Meta designed for developers who want to start building at an even lower cost. It’s meaningfully cheaper than Muse Spark... | Meta | 0 | (0) | 1.0.0 | Sep 19, 2026 |
| 45 | DeepSeek V4 Flash Vision Exp is an experimental vision-enabled version of [DeepSeek V4 Flash 0731](https://openrouter.ai/deepseek/deepseek-v4-flash-0731) from DeepSeek, adding image understanding whil | DeepSeek | 0 | (0) | 1.0.0 | Sep 19, 2026 |
| 46 | DeepSeek V4 Flash Vision Exp is an experimental vision-enabled version of [DeepSeek V4 Flash 0731](https://openrouter.ai/deepseek/deepseek-v4-flash-0731) from DeepSeek, adding image understanding whil | DeepSeek | 0 | (0) | 1.0.0 | Sep 19, 2026 |
| 47 | Hy-MT2-1.8B is a compact 1.8B-parameter translation model from Tencent. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for structured, delimiter-bas | Tencent | 0 | (0) | 1.0.0 | Sep 19, 2026 |
| 48 | Hy-MT2-30B-A3B is Tencent's flagship translation model in the Hy-MT2 family. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for structured, delimite | Tencent | 0 | (0) | 1.0.0 | Sep 19, 2026 |
| 49 | This model always redirects to the latest GLM model from Z.ai. | Z.ai | 0 | (0) | 1.0.0 | Sep 19, 2026 |
| 50 | Tencent | 0 | (0) | 1.0.0 | Sep 19, 2026 |
| 51 | Z.ai | 0 | (0) | 1.0.0 | Sep 19, 2026 |
| 52 | GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. It supports text input and output with a 1M-token context window, and improves. | Z.ai | 0 | (0) | 1.0.0 | Sep 19, 2026 |
| 53 | Qwen3.8 27B is an open-weight dense vision-language model from Qwen. It is suited for coding, professional workflows, research, multimodal interaction, and long-running agent tasks, with flexible thin | Qwen | 0 | (0) | 1.0.0 | Sep 19, 2026 |
| 54 | Dots3-Note Preview is an open-weight mixture-of-experts model from Dots Studio, with 16B active parameters out of 280B total. It is the lightest model in the Dots 3 family and is... | Dots Studio | 0 | (0) | 1.0.0 | Sep 19, 2026 |
| 55 | Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed for tasks that require responsive performance and reliable multi | 0 | (0) | 1.0.0 | Sep 19, 2026 |
| 56 | Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed for tasks that require responsive performance and reliable multi | 0 | (0) | 1.0.0 | Sep 19, 2026 |
| 57 | Seed 2.1 Turbo is a multimodal model from ByteDance Seed for coding and long-horizon agent workflows. It is suited for end-to-end software delivery, multi-step task execution, and understanding visual | ByteDance Seed | 0 | (0) | 1.0.0 | Sep 19, 2026 |
| 58 | Qwen3.8 2.4T A95B is an open-weight sparse mixture-of-experts model from Qwen and the open-weight variant of [Qwen3.8 Max](/qwen/qwen3.8-max), with 95 billion active parameters out of 2.4 trillion tot | Qwen | 0 | (0) | 1.0.0 | Sep 19, 2026 |
| 59 | Qwen3.8 2.4T A95B is an open-weight sparse mixture-of-experts model from Qwen and the open-weight variant of [Qwen3.8 Max](/qwen/qwen3.8-max), with 95 billion active parameters out of 2.4 trillion tot | Qwen | 0 | (0) | 1.0.0 | Sep 19, 2026 |
| 60 | Seed 2.0 Code is a model from ByteDance Seed optimized for agentic coding. It is suited for frontend development, multilingual programming tasks, and coding-agent workflows in tools such as Claude... | ByteDance Seed | 0 | (0) | 1.0.0 | Sep 19, 2026 |
| 61 | DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro. | DeepSeek | 0 | (0) | 1.0.0 | Sep 19, 2026 |
| 62 | DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro. | DeepSeek | 0 | (0) | 1.0.0 | Sep 19, 2026 |
| 63 | xAI | 0 | (0) | 1.0.0 | Sep 19, 2026 |
| 64 | 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 | Sep 19, 2026 |
| 65 | NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited for high-throughput agentic workloads and specialized tasks that | NVIDIA | 0 | (0) | 1.0.0 | Sep 19, 2026 |
| 66 | NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited for high-throughput agentic workloads and specialized tasks that | NVIDIA | 0 | (0) | 1.0.0 | Sep 19, 2026 |
| 67 | Sakana Namazu is a Japanese-specialized reasoning model from Sakana AI, based on Kimi K2.6 with additional training for Japanese language and business contexts. It is suited for Japanese instruction f | Sakana | 0 | (0) | 1.0.0 | Sep 19, 2026 |
| 68 | Solar Pro 4 is Upstage's cost-efficient large language model, featuring a 524K context window. It is built for long-horizon tasks and agentic workflows, with strong capabilities in office productivity | Upstage | 0 | (0) | 1.0.0 | Sep 19, 2026 |
| 69 | Muse Glimmer 30B is a dense, open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark and optimized for autonomous agents on consumer hardware. It is suited for long-ho | Meta | 0 | (0) | 1.0.0 | Sep 19, 2026 |
| 70 | Muse Glimmer 30B is a dense, open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark and optimized for autonomous agents on consumer hardware. It is suited for long-ho | Meta | 0 | (0) | 1.0.0 | Sep 19, 2026 |
| 71 | Muse Spark 1.2 is a reasoning model from Meta, designed for complex agentic tasks. It accepts text, images, video, audio, and PDF documents, returns text, and offers a 1M-token context... | Meta | 0 | (0) | 1.0.0 | Sep 19, 2026 |
| 72 | This model always redirects to the latest model in the DeepSeek V4 Flash family. | DeepSeek | 0 | (0) | 1.0.0 | Sep 19, 2026 |
| 73 | DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workfl | DeepSeek | 0 | (0) | 1.0.0 | Sep 19, 2026 |
| 74 | DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workfl | DeepSeek | 0 | (0) | 1.0.0 | Sep 19, 2026 |
| 75 | Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total. It is positioned as the smaller, more efficient member of. | Thinking Machines | 0 | (0) | 1.0.0 | Sep 19, 2026 |
| 76 | Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total. It is positioned as the smaller, more efficient member of. | Thinking Machines | 0 | (0) | 1.0.0 | Sep 11, 2026 |
| 77 | Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total. It is positioned as the smaller, more efficient member of. | Thinking Machines | 0 | (0) | 1.0.0 | Sep 19, 2026 |
| 78 | Qwen3.7 Flash is a vision-language reasoning model from Alibaba. It is suited for multimodal agents, visual coding, search, and computer interaction, with strengths in object recognition, spatial unde | Qwen | 0 | (0) | 1.0.0 | Sep 19, 2026 |
| 79 | Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end software tasks, code review and bug finding, visual | Anthropic | 0 | (0) | 1.0.0 | Sep 19, 2026 |
| 80 | Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end software tasks, code review and bug finding, visual | Anthropic | 0 | (0) | 1.0.0 | Sep 19, 2026 |
| 81 | *Ling-3.0-flash* is a *124B-parameter Mixture-of-Experts (MoE) model*, with approximately *5.1B parameters activated per token*. The model is designed with *token efficiency and production-scale agent | inclusionAI | 0 | (0) | 1.0.0 | Sep 19, 2026 |
| 82 | Laguna S 2.1 is the latest coding agent model from [Poolside](<https://poolside.ai/>). Laguna S 2.1 is a 118B total parameter model with 8B active parameters, scoring 70.2% on Terminal-Bench 2.1 and.. | Poolside | 0 | (0) | 1.0.0 | Sep 19, 2026 |
| 83 | Laguna S 2.1 is the latest coding agent model from [Poolside](<https://poolside.ai/>). Laguna S 2.1 is a 118B total parameter model with 8B active parameters, scoring 70.2% on Terminal-Bench 2.1 and.. | Poolside | 0 | (0) | 1.0.0 | Sep 19, 2026 |
| 84 | Gemini 3.6 Flash is a high-efficiency model from Google for coding, agentic workflows, and web and app development. It is designed to produce polished outputs with fewer unnecessary edits and... | 0 | (0) | 1.0.0 | Sep 19, 2026 |
| 85 | Gemini 3.6 Flash is a high-efficiency model from Google for coding, agentic workflows, and web and app development. It is designed to produce polished outputs with fewer unnecessary edits and... | 0 | (0) | 1.0.0 | Sep 19, 2026 |
| 86 | Gemini 3.5 Flash Lite is a high-efficiency model from Google with upgraded agentic capabilities. It is suited for subagents that execute focused tasks within complex, multi-agent workflows. | 0 | (0) | 1.0.0 | Sep 19, 2026 |
| 87 | Gemini 3.5 Flash Lite is a high-efficiency model from Google with upgraded agentic capabilities. It is suited for subagents that execute focused tasks within complex, multi-agent workflows. | 0 | (0) | 1.0.0 | Sep 19, 2026 |
| 88 | LongCat 2.0 is a sparse mixture-of-experts language model from Meituan, with 48B active parameters out of 1.6T total. It is suited for coding, repository-level changes, long-horizon problem solving, a | Meituan | 0 | (0) | 1.0.0 | Sep 19, 2026 |
| 89 | Thinking Machines | 0 | (0) | 1.0.0 | Sep 19, 2026 |
| 90 | Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning, coding, agentic an | Thinking Machines | 0 | (0) | 1.0.0 | Sep 19, 2026 |
| 91 | Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning, coding, agentic an | Thinking Machines | 0 | (0) | 1.0.0 | Sep 19, 2026 |
| 92 | The experimental version of our Auto Router where we test new improvements. Use it to get the latest and greatest version of our general purpose auto router, but expect beta... | OpenRouter | 0 | (0) | 1.0.0 | Sep 19, 2026 |
| 93 | Moonshot AI | 0 | (0) | 1.0.0 | Sep 19, 2026 |
| 94 | Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at. | Moonshot AI | 0 | (0) | 1.0.0 | Sep 19, 2026 |
| 95 | Muse Spark 1.1 is a multimodal reasoning model from Meta, built for agentic tasks. It accepts text, images, video, audio, and PDF documents and returns text, with a 1M-token context... | Meta | 0 | (0) | 1.0.0 | Sep 19, 2026 |
| 96 | KAT-Coder-Pro V2.5 is a flagship-level Agentic Coding model that can directly hand over an entire issue or an entire business workflow to it, allowing it to autonomously locate and make... | Kwaipilot | 0 | (0) | 1.0.0 | Sep 19, 2026 |
| 97 | GPT-5.6 Luna Pro is the same underlying model as [GPT-5.6 Luna](https://openrouter.ai/openai/gpt-5.6-luna), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. Lea | OpenAI | 0 | (0) | 1.0.0 | Sep 19, 2026 |
| 98 | GPT-5.6 Luna Pro is the same underlying model as [GPT-5.6 Luna](https://openrouter.ai/openai/gpt-5.6-luna), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. Lea | OpenAI | 0 | (0) | 1.0.0 | Sep 19, 2026 |
| 99 | GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic workflows, providin | OpenAI | 0 | (0) | 1.0.0 | Sep 19, 2026 |
| 100 | GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic workflows, providin | OpenAI | 0 | (0) | 1.0.0 | Sep 19, 2026 |