2 Commits
Author SHA1 Message Date
Alex 3a30f5cce9 feat(pricing): rates for the default DocsGPT model
$0.15 input, $0.50 output and $0.03 cached input per 1M tokens, so cost
budgets see usage of the default model instead of recording it at $0.
2026-09-21 13:36:22 +01:00
Alex b77561288d feat(pricing): per-million model rates and a cost module
Rename the unused *_cost_per_token capability fields to USD per 1M tokens,
add prompt-cache read/write rates, and ship list prices for the hosted
catalogs. The old per-token keys still load, scaled, with a warning.

docsgpt/pricing.py turns a call's token bins into a USD cost. Models with
no declared rate cost $0 unless QUOTA_UNPRICED_RATE_PER_MILLION is set.
2026-09-21 11:38:22 +01:00