Models

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

Balanced Mistral model for enterprise assistants, multilingual work, and tools

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

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

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

Efficient Mistral model for fast chat, extraction, and production assistants

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

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

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

DeepSeek chat model for instruction following, coding, and analysis

DeepSeek reasoning model for multi-step analysis, math, coding, and tools

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

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

Open Mistral reasoning model for transparent step-by-step problem solving

Mistral's larger vision model for document-heavy image understanding and chat

Flagship Mistral model for advanced reasoning, coding, and multilingual work

Mistral code model for completions, refactors, and developer IDE workflows