How long an LLM response actually takes — time to first token plus generation.
Users judge speed on how fast the first token lands and how fast the rest flows. This tool separates both so you can pick a model and streaming strategy that feels fast. Size the bill behind that speed on the token cost calculator.
Free LLM latency calculator — output tokens, generation speed and time to first token to the real response time your users will feel.
Two things: time to first token (TTFT) — the wait before streaming begins, typically 0.3–2s and higher for reasoning models — and tokens per second, the generation rate. Total time = TTFT + (output tokens ÷ tokens per second). Input length mainly affects TTFT, output length affects generation.
Because users read tokens as they stream in, so perceived latency is close to TTFT rather than total time. Non-streamed responses (structured JSON, tool calls, batch jobs) block until the whole answer is ready, so the full response time is felt. Stream anything a human waits on.