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

DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes

Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work

Open MoE flagship with million-token context for coding and long agent runs

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

Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution

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

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.

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

Open GPT reasoning model for self-hosted agents and controllable deployments

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

Thinking Kimi model for slower research passes, planning, and hard technical questions

Open GPT reasoning model for self-hosted agents and controllable deployments

Cohere command model for multilingual enterprise agents, tools, and chat

DeepSeek chat model for instruction following, coding, and analysis

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

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