Termsslug: per-token-latency

Per-token Latency

每 Token 延迟

Time required to generate each output token, a key metric for measuring model response speed

Curated Intelligence

1 items · Page 1/1
OpenAI 官方博客T1·Models
92 pts
OpenAI Launches GPT-5.5: Focus on Agentic Coding and Low Latency

OpenAI has officially released GPT-5.5, positioning it as its smartest and most intuitive model yet, with significant improvements in agentic coding, computer use, and knowledge work. The model enhances multi-step task planning, tool usage, and self-correction capabilities while maintaining per-token latency comparable to GPT-5.4. Both GPT-5.5 and GPT-5.5 Pro are now available via the API, accompanied by an updated system card detailing new safeguards.