DeepSeek-V4.1-Flash-1017 is a minor update to DeepSeek-V4.1-Flash, delivering substantial improvements across reasoning, coding, agentic tasks, and visual benchmarks. Alongside these gains, the model…
Glimpse is a multimodal visual reasoning model from Elorian, built for visual understanding and complex visual reasoning in the physical world. It reasons directly over images and video rather than...
Apache-2.0 weights with switchable thinking; supports domain fine-tuning and vLLM, SGLang or KTransformers deployment.
Explore interactive worlds in real time with movement and camera controls.
Apache-2.0 text model with 501B total and 23B active parameters; ships BF16, FP8 and NVFP4 weights.
Explore interactive worlds in real time with movement and camera controls.
Moondream 3 Preview is a vision-language model from Moondream with 9B total parameters and 2B active (mixture-of-experts). It handles visual question answering, captioning, OCR, and visual reasoning over…
Native object detection and pointing return structured coordinates; runs locally on Apple Silicon or NVIDIA GPUs.
Direct a continuous world in real time with image references and text prompts.
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...
Ask NVIDIA Nemotron 3.5 Super questions about an image: describe scenes, read text and charts, and reason over what it sees.
Chat and reason with NVIDIA Nemotron 3.5 Super, a hybrid Mamba-Transformer mixture-of-experts model with optional step-by-step thinking.
OpenRouter lists a 1,048,576-token context and up to 943,718 output tokens for this open-weight model aimed at agentic coding.
120B/12B-active Mamba-2 hybrid with a vision encoder; native speculative decoding and switchable thinking.
Universal-3.6 Pro is AssemblyAI's speech-to-text model and the successor to Universal-3.5 Pro, served here through AssemblyAI's Sync API. Compared with Universal-3.5 Pro, AssemblyAI reports 30% fewer errors…
This model always redirects to the latest model in the Pareto family.
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.
24B total, 2.45B active parameters; always reasons before answering, with GGUF and MLX releases for local deployment.
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. Google trained it to keep…
Summarize is an abstractive summarization model from ScaleDown. It condenses long text and documents into a fluent, faithful rewrite rather than lifting sentences from the source, and is suited for...
Define entity types in plain English; returns matching spans, confidence and character offsets, with built-in scan/PDF OCR.
Switch reasoning on or off; hybrid linear attention and multi-token prediction support long-context self-hosted inference.
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...