models.md Codex Docs, 2026-03-05 00:34 UTC → 2026-03-17 18:24 UTC

2 2 

3## Recommended models3## Recommended models

4 4 

5![gpt-5.4](/images/api/models/gpt-5.4.jpg)

6 

7gpt-5.4

8 

9Flagship frontier model for professional work that brings the industry-leading coding capabilities of GPT-5.3-Codex together with stronger reasoning, tool use, and agentic workflows.

10 

11codex -m gpt-5.4

12 

13Copy command

14 

15Capability

16 

17Speed

18 

19Codex CLI & SDK

20 

21Codex app & IDE extension

22 

23Codex Cloud

24 

25ChatGPT Credits

26 

27API Access

28 

29![gpt-5.4-mini](/images/api/models/gpt-5-mini.jpg)

30 

31gpt-5.4-mini

32 

33Fast, efficient mini model for responsive coding tasks and subagents.

34 

35codex -m gpt-5.4-mini

36 

37Copy command

38 

39Capability

40 

41Speed

42 

43Codex CLI & SDK

44 

45Codex app & IDE extension

46 

47Codex Cloud

48 

49ChatGPT Credits

50 

51API Access

52 

5![gpt-5.3-codex](/images/codex/codex-wallpaper-1.webp)53![gpt-5.3-codex](/images/codex/codex-wallpaper-1.webp)

6 54 

7gpt-5.3-codex55gpt-5.3-codex

8 56 

9Most capable agentic coding model to date, combining frontier coding performance with stronger reasoning and professional knowledge capabilities.57Industry-leading coding model for complex software engineering. Its coding capabilities now also power GPT-5.4.

10 58 

11codex -m gpt-5.3-codex59codex -m gpt-5.3-codex

12 60 

50 98 

51API Access99API Access

52 100 

53The gpt-5.3-codex-spark model is available in research preview for ChatGPT Pro101For most tasks in Codex, start with `gpt-5.4`. It combines strong coding,

54subscribers. It is optimized for near-instant, real-time coding iteration.102reasoning, native computer use, and broader professional workflows in one

103model. Use `gpt-5.4-mini` when you want a faster, lower-cost option for

104lighter coding tasks or subagents. The `gpt-5.3-codex-spark` model remains

105available in research preview for ChatGPT Pro subscribers and is optimized for

106near-instant, text-only iteration.

55 107 

56## Alternative models108## Alternative models

57 109 

71 123 

72gpt-5.2124gpt-5.2

73 125 

74Our best general agentic model for tasks across industries and domains.126Previous general-purpose model for coding and agentic tasks across industries and domains. Succeeded by GPT-5.4.

75 127 

76codex -m gpt-5.2128codex -m gpt-5.2

77 129 

167The Codex CLI and IDE extension use the same `config.toml` [configuration file](https://developers.openai.com/codex/config-basic). To specify a model, add a `model` entry to your configuration file. If you don't specify a model, the Codex app, CLI, or IDE Extension defaults to a recommended model.219The Codex CLI and IDE extension use the same `config.toml` [configuration file](https://developers.openai.com/codex/config-basic). To specify a model, add a `model` entry to your configuration file. If you don't specify a model, the Codex app, CLI, or IDE Extension defaults to a recommended model.

168 220 

169```221```

170model = "gpt-5.2"222model = "gpt-5.4"

171```223```

172 224 

173### Choosing a different local model temporarily225### Choosing a different local model temporarily

177To start a new Codex CLI thread with a specific model or to specify the model for `codex exec` you can use the `--model`/`-m` flag:229To start a new Codex CLI thread with a specific model or to specify the model for `codex exec` you can use the `--model`/`-m` flag:

178 230 

179```bash231```bash

180codex -m gpt-5.3-codex232codex -m gpt-5.4

181```233```

182 234 

183### Choosing your model for cloud tasks235### Choosing your model for cloud tasks