LLM expenses - 2026-03-25

Day summary

Requests Success Failed Input tokens Cached tokens Output tokens Total cost
142 127 15 4,145,257 2,175,251 221,311 €1.4227

Executions

Started Provider Model Requests Success Failed Input Output Cost
22:00:19 google gemini-3.1-flash-lite-preview 8 8 0 435,467 14,517 €0.1355
21:00:17 google gemini-3.1-flash-lite-preview 8 8 0 417,201 5,816 €0.1179
20:00:19 google gemini-3.1-flash-lite-preview 10 8 2 399,050 18,078 €0.1341
19:00:17 google gemini-3.1-flash-lite-preview 11 8 3 368,778 9,796 €0.1119
18:00:17 google gemini-3.1-flash-lite-preview 9 9 0 387,926 10,842 €0.1183
17:00:16 google gemini-3.1-flash-lite-preview 8 8 0 322,367 17,159 €0.1112
16:00:18 google gemini-3.1-flash-lite-preview 9 8 1 292,648 13,487 €0.0974
15:00:15 google gemini-3.1-flash-lite-preview 14 10 4 327,234 15,789 €0.1097
14:00:15 google gemini-3.1-flash-lite-preview 10 10 0 289,269 16,626 €0.1021
13:00:17 google gemini-3.1-flash-lite-preview 8 8 0 206,573 14,608 €0.0759
12:00:23 google gemini-3.1-flash-lite-preview 5 5 0 118,320 5,874 €0.0396
11:00:15 google gemini-3.1-flash-lite-preview 11 9 2 182,722 11,879 €0.0663
10:00:17 google gemini-3.1-flash-lite-preview 10 10 0 180,774 11,735 €0.0648
09:00:15 google gemini-3.1-flash-lite-preview 7 7 0 110,119 12,402 €0.0473
08:00:28 google gemini-3.1-flash-lite-preview 14 11 3 106,809 42,703 €0.0908

Model pricing (per 1M tokens)

Model Input Output Cache read Cache store
MiniMax-M1 $0.0000 $0.0000 $0.0000 $0.0000
deepseek-v4-flash $0.1400 $0.2800 $0.0280 $0.0000
deepseek-v4-pro $1.7400 $3.4800 $0.1450 $0.0000
gemini-2.5-flash $0.3000 $2.5000 $0.0300 $1.0000
gemini-2.5-flash-lite $0.1000 $0.4000 $0.0100 $1.0000
gemini-3.1-flash-lite-preview $0.2500 $1.5000 $0.0250 $1.0000
glm-4.7-flash $0.0000 $0.0000 $0.0000 $0.0000
gpt-5-mini $0.2500 $2.0000 $0.0000 $0.0000
gpt-5-nano $0.0500 $0.4000 $0.0000 $0.0000
mistral-small-latest $0.1000 $0.3000 $0.0000 $0.0000