GPT-6 Luna in OpenAI Codex
OpenAI - Lightweight
In OpenAI Codex, GPT-6 Luna meters at 2.5 credits per 1M input tokens and 12.5 per 1M output tokens. At $0.04 per credit that is exactly $0.10 and $0.50 per 1M tokens, the same as calling the OpenAI API directly. A typical daily-coding request works out to about 0 credits (about $0.00). Verified against OpenAI's Codex rate card on 2026-09-28.
Credit rate card
- Credits / 1M in
- 2.5
- Credits / 1M cached
- 0.25
- Credits / 1M out
- 12.5
- Cost per credit
- $0.04
Credits per request
Defined workload baskets, not measured tasks.
| Workload | Credits | Cost | Direct API cost |
|---|---|---|---|
| Short chat turn | 0.0 | $0.00 | $0.00 |
| Daily coding request | 0.0 | $0.00 | $0.00 |
| Agent session step | 0.1 | $0.00 | $0.00 |
At about 0.0 credits per daily-coding request, GPT-6 Luna ranks #1 of 7 current-generation models by cost, about 1x the cheapest (GPT-6 Luna).
Credit-to-API parity
The implied dollar value of a credit spent on GPT-6 Luna, 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 10 : 1 : 50, versus 10 : 1 : 50 in direct API dollars.