GenAI Cost

AI economics intelligence

← Glossary

Output tokens

Tokens generated by the model in response — typically 3–5x more expensive than input tokens.

Output tokens dominate cost in writing-heavy workloads. Choosing models with low output pricing (Gemini Flash, GPT-5 mini) is the highest-leverage cost lever for high-volume drafting use cases.

Related terms

Input tokens

Tokens consumed by the prompt, system message and retrieved context fed into the model.

TPS (Tokens per Second)

Throughput metric for LLM inference — critical for sizing infrastructure.