GPT-6.2 Astra in OpenAI Codex
OpenAI - Powerful
In OpenAI Codex, GPT-6.2 Astra meters at 200 credits per 1M input tokens and 1000 per 1M output tokens. At $0.04 per credit that is exactly $8.00 and $40.00 per 1M tokens, the same as calling the OpenAI API directly. A typical daily-coding request works out to about 2.8 credits (about $0.11). Verified against OpenAI's Codex rate card on 2026-11-20.
Credit rate card
- Credits / 1M in
- 200
- Credits / 1M cached
- 10
- Credits / 1M out
- 1,000
- Cost per credit
- $0.04
Credits per request
Defined workload baskets, not measured tasks.
| Workload | Credits | Cost | Direct API cost |
|---|---|---|---|
| Short chat turn | 1.4 | $0.06 | $0.06 |
| Daily coding request | 2.8 | $0.11 | $0.11 |
| Agent session step | 9.1 | $0.36 | $0.36 |
At about 2.8 credits per daily-coding request, GPT-6.2 Astra ranks #10 of 11 current-generation models by cost, about 78.3x the cheapest (GPT-6 Luna).
Credit-to-API parity
The implied dollar value of a credit spent on GPT-6.2 Astra, backed out from the direct API rate card divided by the credit rate card. It should land on $0.04 for both input and output.
- Implied $ / credit, input
- $0.04
- Implied $ / credit, output
- $0.04
- Markup at the daily workload
- 0.00%
- Ratio match
- Exact
Input : cached : output ratio in credits is 20 : 1 : 100, versus 20 : 1 : 100 in direct API dollars.