Dùng thử miễn phí: mở iMini Agent

Efficiency-oriented V4 MoE for high-throughput coding, chat, and short-to-mid agents — free to try in iMini Agent.

Best for high-throughput agent tasks, everyday coding help, and lower-cost runs.

• 284B MoE with ~13B active parameters per token
• 1M-token context window for long agent sessions
• Ideal when you want speed and lower cost without leaving the browser

Flagship V4 MoE for hard-constraint reasoning, full-repo coding, and long multi-step tool jobs — free to try in iMini Agent.

Best for hard reasoning, agentic coding, and multi-step creative or research work.

• 1.6T MoE with ~49B active parameters per token
• 1M-token context for long-horizon agent tasks
• Strong fit when you need deeper planning and code quality in-browser