Estimate your monthly LLM API bill across nine models: pick a task profile or paste your own prompt, set requests per day, and compare Fable 5, Opus 5, GPT-5.6, Sonnet 5, Haiku 4.5, and Pareto side by side at published list prices.
Monthly bill estimator, list prices: OpenAI and Pareto 2026-09-17; other models 2026-07-28
| Model | Per request | Per month | Per year |
|---|---|---|---|
| Claude Fable 5 | $0.1360 | $4,080 | $49,640 |
| GPT-5.6 Sol | $0.0544 | $1,632 | $19,856 |
| Claude Opus 5 | $0.0680 | $2,040 | $24,820 |
| Claude Opus 4.8 | $0.0680 | $2,040 | $24,820 |
| GPT-5.6 Terra | $0.0326 | $978.00 | $11,899 |
| Claude Sonnet 5 | $0.0272 | $816.00 | $9,928 |
| GPT-5.6 Luna | $0.0033 | $97.80 | $1,190 |
| Claude Haiku 4.5 | $0.0136 | $408.00 | $4,964 |
| Pareto | $0.0205 | $615.00 | $7,483 |
Or paste your actual prompt
Paste a prompt above to price it.
Token profiles come from tasks we ran and metered on July 28, 2026. The verbosity adjustment scales each model's output tokens by its measured Verbosity Index (Edition 1); GPT-5.6 models stay unadjusted until we can meter them. Sonnet 5 at $2/$10, now its standard rate (the September 1 increase was cancelled). The Pareto row uses its published 26.9 rates ($2.50 in / $7.50 out per MTok), verified 2026-09-17. OpenAI Standard rates for at most 272K input tokens, verified September 17, 2026; Sol promotional through November 21, 2026. Longer contexts cost more. Other provider rates verified July 28, 2026.
The data behind this tool: prices.json · measured-bills.json, both verified and dated.
Compare any two models
List rates and dated competitor measurements: prices and measured bills. Pareto 26.9 measured task costs are not published. Verbosity: Edition 2.