Models

2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows

Preview Qwen flagship for million-token multimodal reasoning and long-horizon agentic workflows

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

Muse Spark is a natively multimodal reasoning model with support for tool-use, visual chain of thought, and multi-agent orchestration.

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

Fast Gemini model balancing multimodal reasoning, tool use, and cost

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

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

Fast Gemini model balancing multimodal reasoning, tool use, and cost

Reasoning-first Gemini preview for agentic coding and complex problem solving

Fast Gemini model balancing multimodal reasoning, tool use, and cost

Preview Gemini flagship for complex reasoning, coding, and rich multimodal prompts

New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs

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