Models

Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work

Experimental multimodal DeepSeek V4 Flash model for image understanding, coding, and agentic work

Multimodal Kimi workhorse for agent loops, coding tasks, and visual context

Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking

Open agentic MoE model (397B total, 17B active) for coding, tool use, and research workflows

Native multimodal hybrid MoE model for image and video understanding, reasoning, and visual agents

Open MiMo model for multimodal coding agents and long-context automation

Multimodal MoE reasoning model (276B total, 12B active) for text, image, and audio

Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio

Muse Glimmer is a 30-billion-parameter open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark for always-on local agents, tool use, coding, and image understanding.

Earlier Kimi frontier model for long-context agents, coding, and multimodal work

Largest Gemma 4 instruction model for open, self-hosted chat and reasoning

Newer StepFun flash model for faster agents, coding, and multimodal prompts

Open Gemma instruction model for efficient chat and self-hosted deployments

Largest open Gemma 3 instruction model for multilingual text generation and visual understanding

Open multimodal Gemma instruction model for multilingual text generation and image understanding

Efficient on-device Gemma 3n model for text, image, and audio understanding

Open multimodal Gemma instruction model for efficient text generation and image understanding