Tap the moonlit garden to grow a glowing flower. Make a new night or save the scene as a PNG. Built with HTML, CSS and Canvas; no account or build step.
Moon Garden: a tiny interactive postcard
- Elapsed
- 38s
- Typed turns
- 2
- Tool calls
- 5
Recorded details and sources
Recorded tokens
Text the model read and wrote.
- 230.8K
Est. dollars*
List-price cost of the recorded model usage.
- $0.12
Elapsed
Time between the first and last captured event, including waiting.
- 38 sec
About these measurements
Recorded tokens. 229,262 input + 1,549 output. Cached input is included; only calls with recorded usage are counted.
Est. dollars. Model-price comparison from stored capture inputs, not a bill. Excludes subscription terms, tool fees and taxes; standard-assumed means processing speed was not recorded. Capture window 2026-10-10T23:31:32.584000Z to 2026-10-10T23:32:11.213000Z; source SHA-256 6ab3aeea683d8703d8e3fb4b8c8158e9189eaa185b56e822b85bb3533d5a95f9. gpt-6-sol (primary): 229262 input including 198784 cache reads, 0 5-minute writes and 0 1-hour writes; 1549 output. Rates USD per million {"input":2,"output":10,"cache_read":0.2,"cache_write_1h":null,"cache_write_5m":null}. https://developers.openai.com/api/docs/models/gpt-6-sol, provider-model-page-2026-10-11, checked 2026-10-11; service tier standard-assumed; context tier input <=272K. Null rates apply only to token categories with zero usage. Method model-price-v1. Captures and price inputs are uploader-supplied, not independently verified by STRIVE.
Tool activity. 2 occupied clock minutes: unique 60-second clock bins contain at least one recorded tool call. This counts occupied bins, including partial boundary minutes; it is not continuous tool runtime or measured human active time. Origin 2026-10-10T23:31:00Z; method occupied-tool-minutes-v1. Capture window 2026-10-10T23:31:32.584000Z to 2026-10-10T23:32:11.213000Z; source SHA-256 6ab3aeea683d8703d8e3fb4b8c8158e9189eaa185b56e822b85bb3533d5a95f9.
Model. Model names from the capture.
You typed. Recorded human messages, not words or keystrokes.
Elapsed. Time between the first and last captured event, including waiting.
Models and usage
- Platform / harness
- Codex
- Recorded models
- gpt-6-sol
- Recorded tokens
- 230,811
Where these numbers come from
Model names and usage come from the imported capture. STRIVE has not verified them with the provider. Source: codex-records.
229,262 input + 1,549 output tokens. Cached input and reasoning tokens are already included, and are not added again. Only calls with recorded usage are included; missing usage remains unknown. This is not a bill or a measure of wasted work.
Recorded activity
Human messages: 2
Messages typed or queued by a person; excludes tool results and injected context.
Tool requests: 5
Requests the agent made to tools. A request does not prove a successful action.
Source and limits
Imported · client-reported. The capture supplied these numbers. STRIVE has not independently verified the source or outcome.
Recorded session span; may include idle time. Not human effort. Session date supplied by the capture.
The measurement reference identifies this submitted capture. A hash is not proof the counters are true.
Photos and descriptions are chosen by the author. They do not attest to when a session happened or what succeeded.