# Goodput

> Goodput: The rate of requests that meet the latency objective (SLO). Slow requests count toward throughput but not goodput.

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

The rate of requests that meet the latency objective (SLO). Slow requests count toward throughput but not goodput.

Learn it in the lesson: [Goodput: counting only what meets the target](https://llmdojo.dev/learn/inference-optimization/measuring-inference/goodput) (Inference and Model Optimization · Measuring Inference: Latency, Throughput and Goodput).

## Interview questions about Goodput

- [Your team wants to raise the batch size to cut serving cost. What happens to users, and which number would you use to decide?](https://llmdojo.dev/interview/q/your-team-wants-to-raise-the-batch-size-to-cut-serving-cost)

## Related
- [Time to first token (TTFT)](https://llmdojo.dev/glossary/ttft)
- [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)
- [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)