AI models directory for capability-aware discovery

UniDepth v2 (ViT-L/14) is a 0.4B-parameter PyTorch model for monocular metric depth estimation, leveraging a Vision Transformer backbone to predict scale-aware depth maps from single RGB images.

Tiangong AI is a comprehensive artificial intelligence platform developed by Kunlun Tech, designed primarily for Chinese-speaking users. It functions as an integrated ecosystem combining advanced AI-powered search capabilities with robust creative content generation tools. Unlike standalone large language models that focus solely on text completion or chat, Tiangong AI positions itself as a productivity suite that bridges the gap between information retrieval and content production. By leveraging large language models (LLMs) under the hood, it allows users to perform complex searches, synthesize real-time web data, and immediately transform those findings into structured articles, reports, or creative writing. The platform is accessible via web and mobile applications, emphasizing ease of use for professionals, students, and content creators operating within the Chinese digital landscape.

360 AI Search is a proprietary, LLM-integrated search service developed by Qihoo 360. It merges traditional web indexing with generative AI to provide direct, conversational answers while citing source URLs. Optimized primarily for the Chinese market, it operates within the 360 ecosystem, including the 360 Browser, and is not available as an open-source model or downloadable package.

GPT-4.1 is a hosted large language model from OpenAI optimized for practical software, agent, and business workflows. It is designed for general reasoning, coding assistance, and research tasks, with an API-first deployment model that simplifies integration but ties operations to OpenAI's infrastructure.

o3-mini is a compact reasoning model from OpenAI designed for efficient technical tasks, offering stronger reasoning than GPT-3.5 in a lighter package than GPT-4. It is typically accessed via hosted APIs, balancing cost and latency for coding, analysis, and research use cases.

Phi-4 is a compact open-weight language model from Microsoft, optimized for structured technical tasks like coding, analysis, and research. It balances efficiency and quality, making it suitable for self-hosted or resource-constrained deployments.

Kimi is a large language model developed by Moonshot AI, designed to handle extremely long context windows of up to 2 million tokens, making it suitable for processing extensive documents and research materials.

DeepSeek R1 is an open-weight reasoning model developed by DeepSeek, emphasizing chain-of-thought (CoT) style reasoning for complex problem-solving. It is designed for research and deployment, with weights released under a permissive license.

Qwen2.5-VL 72B is a large multimodal AI model from Alibaba Cloud's Qwen team, designed for vision-language tasks such as image understanding, document analysis, and visual reasoning. It is an open-weight model that can be self-hosted, making it suitable for teams seeking alternatives to hosted multimodal APIs. The model excels in processing screenshots, documents, and visual data, but requires significant GPU resources for deployment.

Claude 3.7 Sonnet is a hosted AI model from Anthropic, optimized for coding, reasoning, and enterprise writing. It excels in long-context tasks and is often compared with top models for its reliability in code generation, document analysis, and research workflows.

GPT-4o is a multimodal frontier model from OpenAI that processes text, images, and audio with low latency, designed for general-purpose assistant and reasoning tasks. It balances broad capability with strong multimodal utility, making it suitable for product-facing use cases. Deployment is primarily via hosted APIs or ChatGPT, offering fast adoption but vendor dependency.

Gemini 2.0 Flash is a fast, multimodal AI model from Google, optimized for responsive assistant experiences, reasoning, and agentic systems. It is designed for deployment within Google's managed ecosystem, offering low latency and strong alignment with Google Cloud and AI platform tools.

Claude 3.5 Sonnet is a mid-tier large language model by Anthropic, balancing capability and cost for general reasoning, coding, and long-context tasks. It is commonly evaluated for its strong performance in code review, long-form analysis, and deliberate written output, with deployment via hosted endpoints or first-party chat surfaces.

Command R+ is an enterprise-focused large language model optimized for retrieval-augmented generation (RAG), reasoning, and document-grounded tasks. It is designed for teams that need strong retrieval capabilities without relying on the largest platform vendors, and is typically accessed via partner clouds or managed APIs.

Gemini 1.5 Pro is a multimodal AI model from Google DeepMind, known for its exceptionally long context window (up to 2 million tokens) and strong reasoning capabilities. It is designed for complex tasks involving large documents, code, audio, video, and images, and is primarily accessed via Google Cloud's Vertex AI and the Gemini API.

Metaso is an AI-powered research assistant that combines retrieval-augmented generation (RAG) with large language model (LLM) summarization to help researchers and students find, synthesize, and understand academic literature. It is not a standalone AI model but a tool or application that integrates multiple models and retrieval techniques.