Admin
What NephAI has been doing
The work NephAI carried out for you over the last 7 days, and what it cost.
10 kinds of work ran
- What it cost
- $29.85
- Times it thought something through
- 14,133
- Amount of text handled
- 35,726,125
- Average cost each time
- $0.0021
Where the work went
10 in use
| Kind of work | Calls | Tokens | Cost | Share |
|---|---|---|---|---|
| Automation reasoning Plans and verifies the next covered action from current evidence. | 1,600 | 10,805,516 | $17.26 | 57.8% |
| Automation follow-through Confirms from current evidence when prepared Automation work has finished. | 237 | 4,254,277 | $6.44 | 21.6% |
| Contact profiles Learns enough about a new correspondent to prepare work correctly. | 11,606 | 14,014,750 | $4.27 | 14.3% |
| Thread sorting Separates Church, work, and personal conversations. | 237 | 177,295 | $0.6698 | 2.2% |
| Prepared replies Writes the canonical reply waiting in a conversation. | 38 | 429,154 | $0.4123 | 1.4% |
| Handbook fact-checking Checks a prepared Church draft against retrieved Handbook passages. | 29 | 130,093 | $0.3740 | 1.3% |
| Handbook lookup Plans the Handbook questions and passages needed for a response. | 29 | 69,880 | $0.1880 | 0.6% |
| Stewardship review Reviews your stewardships and prepares the next useful move. | 11 | 83,415 | $0.1112 | 0.4% |
| Inbox understanding Reads each conversation and works out what it needs. | 342 | 5,745,610 | $0.0841 | 0.3% |
| Draft checking Checks every prepared reply against your own words and calendar before you see it. | 4 | 16,135 | $0.0408 | 0.1% |
Which model did it
7 in use
| Model | Calls | Tokens | Cost | Share |
|---|---|---|---|---|
| GPT 5.6 Terra | 1,855 | 15,117,722 | $22.10 | 74.1% |
| Gemini 3.1 Flash Lite | 11,606 | 14,014,750 | $4.27 | 14.3% |
| Claude Opus 4.7 | 18 | 317,652 | $1.73 | 5.8% |
| Kimi K3 | 237 | 177,295 | $0.6698 | 2.2% |
| Grok 4.5 | 62 | 216,108 | $0.6028 | 2.0% |
| Claude Opus 4.8 | 3 | 66,897 | $0.3662 | 1.2% |
| GLM 5.2 | 11 | 83,415 | $0.1112 | 0.4% |