LLMOps · Cost & Latency

Token Cost & Latency

Set the tokens and the model — estimate the bill, the time-to-first-token and the streaming speed.

INPUT TOK 2,000 OUTPUT TOK 500 model

total cost

$0.0135

total latency

6.7s

latency timeline6.71 s

TTFT 0.46 sstream 6.25 s

cost breakdown$0.0135

input $0.0060output $0.0075

TTFT

0.46 s

throughput

85 tok/s

rate $/1M

3 / 15

illustrative rates — real prices vary by provider & tier

estimate.py