Pareto 26.9
unbiased/pareto-26.9Pareto 26.9 is an experimental multimodal composite model from Unbiased AI for research, coding, agentic workflows, and general-purpose tasks. It runs several frontier and open models for each request and returns a single selected or synthesized answer. This experimental release supports text and image input, tool calling, a 262K-token context window, and up to 131K output tokens. Its underlying model mix and behavior may change as it is evaluated. Request content may be retained for abuse prevention and security monitoring for up to 30 days, and is not used for model training without explicit consent.
Gemma 4 12B Starry Ocean
gemma-4-12b-it-starry-oceanGemma 4 12B Starry Ocean is an open-weight merge for storytelling, roleplay, and creative writing. It supports image understanding, tool calling, optional reasoning, and a 131,072-token context window.
DeepSeek V4 Flash Vision Exp Cybersecurity
deepseek/deepseek-v4-flash-vision-exp-cybersecurityA cybersecurity-focused variant of DeepSeek V4 Flash Vision Exp, with image understanding, tool calling, optional reasoning, and a 1,048,576-token context window.
Gemini 4 Argon
google/gemini-4-argonGoogle's Gemini 4 Argon is a flagship reasoning model for complex software engineering, mathematical and scientific problem solving, and multi-step agents. It accepts text, images, audio, video, and PDFs, with tool calling and structured outputs. Its 1,048,576-token context is shared across input, thinking, and output; synchronous output is capped at 65,536 tokens.
Muse Wonder
meta/muse-wonderMeta's Muse Wonder is a frontier reasoning model designed for complex personal and professional agentic tasks. It accepts text, images, audio, video, and PDF documents across a one-million-token context window, supports tool calling and structured output, and always reasons before answering.
