Model pricing
GPT-6 Astra API list price — cost per token
GPT-6 Astra costs $10.00 per million input tokens and $50.00 per million output tokens (USD). Requests over 272K tokens are billed at a premium tier for the whole request.
| Token rate | USD / 1M tokens |
|---|---|
| Effortqualitative reasoning depth | High |
| Inputper 1M tokens | $10.00 |
| Output | $50.00 |
| Cache write · 5-minute1.25× input | $12.50 |
| Cache write · 1-hour2× input | $12.50 |
| Cache read0.1× input | $1.00 |
Notional list price. These are OpenAI (GPT-5.x / Codex) API list prices in USD. On a Codex usage this is a notional list price — what usage would cost at API rates, not metered spend.
Cache & context economics
GPT-6 Astra adds cache reads at $1.00 / 1M — about a tenth of input, cache writes at $12.50 (5-minute) or $12.50 (1-hour) / 1M.
Common questions
- How much does GPT-6 Astra cost per million tokens?
- $10.00 input and $50.00 output per million tokens (USD list price).
- What is the cache-read price for GPT-6 Astra?
- $1.00 per million cached-read tokens — about a tenth of the input rate.
- How is cache writing priced for GPT-6 Astra?
- A 5-minute cache write is $12.50 and a 1-hour write is $12.50 per million tokens — the split most trackers miss.
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