OpenAI lansează „Ultrafast”, un mod care accelerează de până la 14 ori GPT-5.6 Sol

OpenAI has launched a new processing mode for its GPT-5.6 Sol model, enabling response speeds of up to 750 tokens per second. This Ultrafast mode allows for processing up to 14 times faster than the standard, aimed at scenarios where quick responses are crucial. The model is part of the GPT-5.6 family and is designed for complex tasks like programming and cybersecurity. The speed enhancement is made possible through infrastructure developed with Cerebras. OpenAI also introduced an 'ultra' function that utilizes multiple sub-agents for parallel task execution, enhancing efficiency. This development comes amid increasing competition in the AI model market.