speed.md +30 −0 added
1# Speed
2
3## Fast mode
4
5Codex offers the ability to increase the speed of the model for increased
6credit consumption.
7
8Fast mode increases supported model speed by 1.5x and consumes credits at a
9higher rate than Standard mode. It currently supports GPT-5.5 and GPT-5.4,
10consuming credits at 2.5x the Standard rate for GPT-5.5 and 2x the Standard
11rate for GPT-5.4.
12
13Use `/fast on`, `/fast off`, or `/fast status` in the CLI to change or inspect
14the current setting. You can also persist the default with `service_tier = "fast"` plus `[features].fast_mode = true` in `config.toml`. Fast mode is
15available in the Codex IDE extension, Codex CLI, and the Codex app when you
16sign in with ChatGPT. With an API key, Codex uses standard API pricing instead
17and you can't use Fast mode credits.
18
19[
20Your browser does not support the video tag.
21](/videos/codex/fast-mode-demo.mp4)
22
23## Codex-Spark
24
25GPT-5.3-Codex-Spark is a separate fast, less-capable Codex model optimized for
26near-instant, real-time coding iteration. Unlike fast mode, which speeds up a
27supported model at a higher credit rate, Codex-Spark is its own model choice
28and has its own usage limits.
29
30During research preview Codex-Spark is only available for ChatGPT Pro subscribers.