Models

Open-weight experimental preview of the Qwen4 architecture: hybrid-attention MoE (125B total, 6B active) with vision encoder for coding, agent tasks, and image and video understanding

Native multimodal GLM model for efficient coding and long-horizon agent tasks

Dense 27B vision-language model for coding, agent tasks, and image and video understanding

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

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

MiniMax multimodal model for long-context coding, perception, and agent planning

Qwen vision-language model for visual reasoning, documents, and agent tasks

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

Open multimodal Qwen MoE for local agents that need vision, audio, and code

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

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

Fast Mistral production model for chat, extraction, and cost-sensitive agents

Qwen vision-language model for visual reasoning, documents, and agent tasks

Qwen instruction model for multilingual chat, reasoning, and tool use

Large open Qwen multimodal MoE for visual agents and long technical tasks

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

Open multimodal Llama for strong reasoning with efficient everyday serving

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

Mistral's largest general model for enterprise agents, coding, and multilingual reasoning