Prompt Cost Calculator
Estimate tokens, cost, and latency for a prompt across IN2PETA and popular models. Token counts are heuristic estimates, not billing-grade.
Prompt
Paste the prompt you want to price out.
Characters: 0
≈ 0 input tokens
Model
Input / 1M
$0.22
Output / 1M
$0.66
Cache read / 1M
$0.044
Context
1M
Estimate settings
500
0%
Share of the prompt assumed to be served from the model's prompt cache at the cache-read rate.
Estimate
Input tokens
0
0 cached
Output tokens
500
user-set
Latency
2.5s
approx
Total cost
$0.00033
$0.033 credits
Cost breakdown
Per-token math behind the total.
| Line | Tokens | Rate / 1M | Cost |
|---|---|---|---|
| Input (uncached) — full prompt | 0 | $0.22 | $0 |
| Input (cache read) | 0 | $0.044 | $0 |
| Output | 500 | $0.66 | $0.00033 |
| Total | 500 | — | $0.00033 |