GPT-5.6 Terra in OpenAI Codex
OpenAI - Versatile
In OpenAI Codex, GPT-5.6 Terra meters at 62.5 credits per 1M input tokens and 375 per 1M output tokens. At $0.04 per credit that is exactly $2.50 and $15.00 per 1M tokens, the same as calling the OpenAI API directly. A typical daily-coding request works out to about 1 credits (about $0.04). Verified against OpenAI's Codex rate card on 2026-07-21.
Credit rate card
- Credits / 1M in
- 62.5
- Credits / 1M cached
- 6.25
- Credits / 1M out
- 375
- Cost per credit
- $0.04
Credits per request
Defined workload baskets, not measured tasks.
| Workload | Credits | Cost | Direct API cost |
|---|---|---|---|
| Short chat turn | 0.5 | $0.02 | $0.02 |
| Daily coding request | 1.0 | $0.04 | $0.04 |
| Agent session step | 3.3 | $0.13 | $0.13 |
At about 1.0 credits per daily-coding request, GPT-5.6 Terra ranks #3 of 4 current-generation models by cost, about 3.3x the cheapest (GPT-5.4 mini).
Credit-to-API parity
The implied dollar value of a credit spent on GPT-5.6 Terra, 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 : 60, versus 10 : 1 : 60 in direct API dollars.