Model pricing
GPT-5.3-Codex-Spark API list price — cost per token
Historical bundled rate; not verified against current published pricing. GPT-5.3-Codex-Spark costs $1.75 per million input tokens and $14.00 per million output tokens (USD).
| Token rate | USD / 1M tokens |
|---|---|
| Effortqualitative reasoning depth | High |
| Inputper 1M tokens | $1.75 |
| Output | $14.00 |
| Cache readper 1M tokens | $0.175 |
Notional list price. Historical bundled rate; not verified against current published pricing. These notional figures are retained for historical accounting, not a current price quote.
Cache & context economics
Cache reads cost $0.175 per million tokens — about a tenth of input.
Common questions
- How much does GPT-5.3-Codex-Spark cost per million tokens?
- $1.75 input and $14.00 output per million tokens (USD list price).
- What is the cache-read price for GPT-5.3-Codex-Spark?
- $0.175 per million cached-read tokens — about a tenth of the input rate.
Track your real cost with JP the Cat
A live menu-bar total, priced to the cent from your local logs — including the cache-write split most tools miss.
Download MeowPrefer Homebrew? Install the same signed, notarized app from JP's public tap.
brew tap 8bittts/jpthecat
brew trust 8bittts/jpthecat
brew install --cask jpthecat