Gate News message, April 27 — Ant Group's inclusionAI has released Ling-2.6-1T, a new trillion-parameter flagship instruction model in the Ling series. Unlike long-chain reasoning models, Ling-2.6-1T employs a "Fast-Thinking" mechanism designed for precise task execution with minimal token consumption.
The model represents a significant upgrade over Ling-1T, with overall intelligence approaching GPT-5.4 non-reasoning mode while achieving improved token efficiency. Ling-2.6-1T targets execution-focused tasks in the agent era, including code modification, tool calling, complex instruction following, and high-frequency production environment deployment. OpenRouter currently provides free API access supporting 262.1k token context window and maximum output of 32.8k tokens.
Ant Group has announced plans to open-source Ling-2.6-1T in the coming weeks.