Devasheesh Mishra devasheeshG
🚢
devasheeshG
/ llm_cost_calc.py
Last active
March 26, 2026 20:42
Cost estimator for agentic LLM runs with prompt caching — models per-turn input, output, cache read/write across tool call loops.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| def estimate_agent_cost( | |
| # pricing (per token) | |
| input_price: float, | |
| output_price: float, | |
| cache_read_price: float, | |
| cache_write_price: float, | |
| # initial turn | |
| # global system prompt + tool definitions | |
| system_prompt_tokens: int, |
OlderNewer