Usage
Last updatedSince September 2025: 44.77B tokens across 279 active days, mostly Claude Opus 5.5 via Claude Code. Current streak: 196 days.
- API equivalent
- US$32.5K
- Tokens
- 44.77B
- Active days
- 279
- Models
- 60
The API equivalent of my AI coding agents at provider list prices. Tokens, cost, and reasoning effort. Not what I paid. Aggregates only.
Model character
Cache reuse, blended price, how often each model runs, and when it last ran. Open a model's profile for its full history.
| Model | Cache hit | $ / 1M tokens | Active days | Last used |
|---|---|---|---|---|
Claude Opus 5.5 | 97% | US$0.41 | 36 | 29/10/2026 |
GPT-5.6 Sol | 97% | US$0.73 | 28 | 24/09/2026 |
Claude Opus 5 | 97% | US$0.79 | 53 | 19/10/2026 |
Claude Opus 4.8 | 95% | US$0.92 | 60 | 01/08/2026 |
Claude Fable 5 | 96% | US$1.60 | 49 | 23/08/2026 |
GPT-5.5 | 93% | US$0.91 | 68 | 01/08/2026 |
GPT 5.5 (Fast) | 94% | US$2.08 | 39 | 01/07/2026 |
Claude Opus 4.7 | 92% | US$1.16 | 100 | 04/10/2026 |
Where the money goes
Blended price per million tokens against volume, per model. Bigger dots mean more messages. Both axes are log scale.
Biggest spenders: Claude Opus 5.5, US$5,758.87 at US$0.41 per million tokens; GPT-5.6 Sol, US$4,477.95 at US$0.73 per million tokens; Claude Opus 5, US$4,214.62 at US$0.79 per million tokens; Claude Opus 4.8, US$4,086.80 at US$0.92 per million tokens; Claude Fable 5, US$3,835.83 at US$1.60 per million tokens. Every model's figures are in the Explorer table below.
Cache & effort
Prompt tokens served from cache, what that saved against the full input price, and how hard I pushed the models.
- Cache hit rate
- 96%
- Saved by caching
- US$194.4K
Effort levels
5,281 of 6,117 sessions classified.
Minimal
15 (0%)
Low
557 (11%)
Medium
2,533 (48%)
High
361 (7%)
Extra high
1,558 (30%)
Max
36 (1%)
Ultra
212 (4%)
Mixed
9 (0%)
Token mix
All 44.77B tokens by category
Cache read
42.62B (95%)
Cache write
1.18B (3%)
Input
796.87M (2%)
Output
131.44M (0%)
Reasoning
38.28M (0%)