# Time to first token (TTFT)

> Time to first token (TTFT): How long from sending a request until the first output token arrives. Mostly the prefill, so it grows with the prompt's length.

Canonical: https://llmdojo.dev/glossary/ttft

Also called time to first token, TTFT.

How long from sending a request until the first output token arrives. Mostly the prefill, so it grows with the prompt's length.

Learn it in the lesson: [What users wait for](https://llmdojo.dev/learn/inference-optimization/measuring-inference/what-users-wait-for) (Inference and Model Optimization · Measuring Inference: Latency, Throughput and Goodput).

## Interview questions about Time to first token (TTFT)

- [How do you get TTFT, inter-token latency, TPOT and total latency from one streamed reply?](https://llmdojo.dev/interview/q/how-do-you-get-ttft-inter-token-latency-tpot-and-total-latency)
- [Server logs show a TTFT of 80 ms, yet users of your reasoning assistant say it takes seconds to start answering. Explain the gap.](https://llmdojo.dev/interview/q/server-logs-show-a-ttft-of-80-ms-yet-users-of-your)
- [A provider's status page shows a p50 TTFT of 180 ms. You need 300 ms for 9 in 10 of your users. What do you do before signing up?](https://llmdojo.dev/interview/q/a-provider-s-status-page-shows-a-p50-ttft-of-180-ms)
- [Users say your summariser 'takes ages to start' on long documents but then writes quickly. Explain what's happening in terms of prefill and decode.](https://llmdojo.dev/interview/q/users-say-your-summariser-takes-ages-to-start-on-long-documents-but)
- [Request A has a 960-token prompt and 10 output tokens. Request B has a 16-token prompt and 200 output tokens. Same model and machine: which finishes first, and what does that tell you about a chat app that resends the full history every turn?](https://llmdojo.dev/interview/q/request-a-has-a-960-token-prompt-and-10-output-tokens-request)
- [A chat reply streams in token by token. What two waits does the user feel, and which one does streaming make matter most?](https://llmdojo.dev/interview/q/a-chat-reply-streams-in-token-by-token-what-two-waits-does)
- [Your AI chatbot takes too long to respond. What do you do?](https://llmdojo.dev/interview/q/your-ai-chatbot-takes-too-long-to-respond-what-do-you-do)
- [Design request batching for GPU inference, including scheduling, autoscaling and routing.](https://llmdojo.dev/interview/q/design-request-batching-for-gpu-inference-including-scheduling-autoscaling-and-routing)

## Related
- [Time per output token (TPOT)](https://llmdojo.dev/glossary/tpot)
- [Inter-token latency](https://llmdojo.dev/glossary/itl)
- [Percentile (p50, p99)](https://llmdojo.dev/glossary/percentile)
- [Throughput](https://llmdojo.dev/glossary/throughput)
- [Goodput](https://llmdojo.dev/glossary/goodput)
- [Service level objective (SLO)](https://llmdojo.dev/glossary/slo)
- [Time to publish](https://llmdojo.dev/glossary/time-to-publish)
- [Glossary of every term](https://llmdojo.dev/glossary)