models.md +44 −76
2 2
3## Recommended models3## Recommended models
4 4
55
6 6
77gpt-5.3-codexgpt-5.4
8 8
99Most capable agentic coding model to date, combining frontier coding performance with stronger reasoning and professional knowledge capabilities.Flagship 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 10
1111codex -m gpt-5.3-codexcodex -m gpt-5.4
12 12
13Copy command13Copy command
14 14
26 26
27API Access27API Access
28 28
2929
30 30
3131gpt-5.3-codex-sparkgpt-5.4-mini
32 32
3333Text-only research preview model optimized for near-instant, real-time coding iteration. Available to ChatGPT Pro users.Fast, efficient mini model for responsive coding tasks and subagents.
34 34
3535codex -m gpt-5.3-codex-sparkcodex -m gpt-5.4-mini
36 36
37Copy command37Copy command
38 38
50 50
51API Access51API Access
52 52
5353The gpt-5.3-codex-spark model is available in research preview for ChatGPT Pro
54subscribers. It is optimized for near-instant, real-time coding iteration.
55
56## Alternative models
57
58
59
60gpt-5.2-codex
61
62Advanced coding model for real-world engineering. Succeeded by GPT-5.3-Codex.
63
64codex -m gpt-5.2-codex
65
66Copy command
67
68Show details
69
70
71
72gpt-5.2
73
74Our best general agentic model for tasks across industries and domains.
75
76codex -m gpt-5.2
77
78Copy command
79
80Show details
81
82
83 54
8455gpt-5.1-codex-maxgpt-5.3-codex
85 56
8657Optimized for long-horizon, agentic coding tasks in Codex.Industry-leading coding model for complex software engineering. Its coding capabilities now also power GPT-5.4.
87 58
8859codex -m gpt-5.1-codex-maxcodex -m gpt-5.3-codex
89 60
90Copy command61Copy command
91 62
9263Show detailsCapability
93 64
9465Speed
95 66
9667gpt-5.1Codex CLI & SDK
97 68
9869Great for coding and agentic tasks across domains. Succeeded by GPT-5.2.Codex app & IDE extension
99 70
10071codex -m gpt-5.1Codex Cloud
101 72
10273Copy commandChatGPT Credits
103 74
10475Show detailsAPI Access
105 76
10677
107 78
10879gpt-5.1-codexgpt-5.3-codex-spark
109 80
11081Optimized for long-running, agentic coding tasks in Codex. Succeeded by GPT-5.1-Codex-Max.Text-only research preview model optimized for near-instant, real-time coding iteration. Available to ChatGPT Pro users.
111 82
11283codex -m gpt-5.1-codexcodex -m gpt-5.3-codex-spark
113 84
114Copy command85Copy command
115 86
11687Show detailsCapability
117
118
119
120gpt-5-codex
121
122Version of GPT-5 tuned for long-running, agentic coding tasks. Succeeded by GPT-5.1-Codex.
123
124codex -m gpt-5-codex
125 88
12689Copy commandSpeed
127 90
12891Show detailsCodex CLI & SDK
129 92
13093Codex app & IDE extension
131 94
13295gpt-5-codex-miniCodex Cloud
133 96
13497Smaller, more cost-effective version of GPT-5-Codex. Succeeded by GPT-5.1-Codex-Mini.ChatGPT Credits
135 98
13699codex -m gpt-5-codexAPI Access
137 100
138101Copy commandFor most tasks in Codex, start with `gpt-5.4`. It combines strong coding,
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 is
105available in research preview for ChatGPT Pro subscribers and is optimized for
106near-instant, real-time coding iteration.
139 107
140108Show details## Alternative models
141 109
142110
143 111
144112gpt-5gpt-5.2
145 113
146114Reasoning model for coding and agentic tasks across domains. Succeeded by GPT-5.1.Previous general-purpose model for coding and agentic tasks, including hard debugging tasks that benefit from deeper deliberation.
147 115
148116codex -m gpt-5codex -m gpt-5.2
149 117
150Copy command118Copy command
151 119
153 121
154## Other models122## Other models
155 123
156124Codex works best with the models listed above.When you sign in with ChatGPT, Codex works best with the models listed above.
157 125
158You can also point Codex at any model and provider that supports either the [Chat Completions](https://platform.openai.com/docs/api-reference/chat) or [Responses APIs](https://platform.openai.com/docs/api-reference/responses) to fit your specific use case.126You can also point Codex at any model and provider that supports either the [Chat Completions](https://platform.openai.com/docs/api-reference/chat) or [Responses APIs](https://platform.openai.com/docs/api-reference/responses) to fit your specific use case.
159 127
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.135The 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.
168 136
169```137```
170138model = "gpt-5.2"model = "gpt-5.4"
171```139```
172 140
173### Choosing a different local model temporarily141### 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:145To 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:
178 146
179```bash147```bash
180148codex -m gpt-5.3-codexcodex -m gpt-5.4
181```149```
182 150
183### Choosing your model for cloud tasks151### Choosing your model for cloud tasks