Models

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

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

General GLM flagship for coding, analysis, and tool-heavy engineering workflows

Prior MiniMax coding model for agent workflows, office edits, and automation

Budget GLM lane for fast coding help, routing, and everyday automation

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

Earlier MiniMax agent model for practical coding and productivity tasks

Mature GLM model for dependable coding, reasoning, and structured agent tasks

Hybrid-reasoning DeepSeek model with thinking and non-thinking modes, sparse attention, and tool-use

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

Efficient open MiniMax model built for coding agents and tool-heavy workflows

Open multimodal Llama for strong reasoning with efficient everyday serving

Smaller Qwen coder for efficient local agents and repo-level fixes

Open Qwen coding heavyweight for repository reasoning and agentic engineering

Dense open Qwen model for self-hosted chat, reasoning, and coding

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

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

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

Classic open reasoning model for transparent math, coding, and deliberate problem solving