models.md +37 −86
1# Codex Models1# Codex Models
2 2
3Meet the AI models that power Codex
4
5## Recommended models3## Recommended models
6 4
75
8 6
97gpt-5.3-codexgpt-5.4
10 8
119Most 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.
12 10
1311codex -m gpt-5.3-codexcodex -m gpt-5.4
14 12
15Copy command13Copy command
16 14
28 26
29API Access27API Access
30 28
3129
32 30
3331gpt-5.3-codex-sparkgpt-5.4-mini
34 32
3533Text-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.
36 34
3735codex -m gpt-5.3-codex-sparkcodex -m gpt-5.4-mini
38 36
39Copy command37Copy command
40 38
52 50
53API Access51API Access
54 52
5553
56 54
5755gpt-5.2-codexgpt-5.3-codex
58 56
5957Advanced coding model for real-world engineering. Succeeded by GPT-5.3-Codex.Industry-leading coding model for complex software engineering. Its coding capabilities now also power GPT-5.4.
60 58
6159codex -m gpt-5.2-codexcodex -m gpt-5.3-codex
62 60
63Copy command61Copy command
64 62
76 74
77API Access75API Access
78 76
7977For most coding tasks in Codex, start with gpt-5.3-codex. It is available for
80ChatGPT-authenticated Codex sessions in the Codex app, CLI, IDE extension, and
81Codex Cloud. API access for GPT-5.3-Codex will come soon. The
82gpt-5.3-codex-spark model is available in research preview for ChatGPT Pro
83subscribers.
84
85## Alternative models
86
87
88
89gpt-5.2
90
91Our best general agentic model for tasks across industries and domains.
92
93codex -m gpt-5.2
94
95Copy command
96
97Show details
98
99
100
101gpt-5.1-codex-max
102
103Optimized for long-horizon, agentic coding tasks in Codex.
104
105codex -m gpt-5.1-codex-max
106
107Copy command
108
109Show details
110
111
112
113gpt-5.1
114
115Great for coding and agentic tasks across domains. Succeeded by GPT-5.2.
116
117codex -m gpt-5.1
118
119Copy command
120
121Show details
122
123
124 78
12579gpt-5.1-codexgpt-5.3-codex-spark
126 80
12781Optimized 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.
128 82
12983codex -m gpt-5.1-codexcodex -m gpt-5.3-codex-spark
130 84
131Copy command85Copy command
132 86
13387Show detailsCapability
134
135
136
137gpt-5-codex
138
139Version of GPT-5 tuned for long-running, agentic coding tasks. Succeeded by GPT-5.1-Codex.
140
141codex -m gpt-5-codex
142 88
14389Copy commandSpeed
144 90
14591Show detailsCodex CLI & SDK
146 92
14793Codex app & IDE extension
148 94
14995gpt-5-codex-miniCodex Cloud
150 96
15197Smaller, more cost-effective version of GPT-5-Codex. Succeeded by GPT-5.1-Codex-Mini.ChatGPT Credits
152 98
15399codex -m gpt-5-codexAPI Access
154 100
155101Copy 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.
156 107
157108Show details## Alternative models
158 109
159110
160 111
161112gpt-5gpt-5.2
162 113
163114Reasoning 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.
164 115
165116codex -m gpt-5codex -m gpt-5.2
166 117
167Copy command118Copy command
168 119
170 121
171## Other models122## Other models
172 123
173124Codex works best with the models listed above.When you sign in with ChatGPT, Codex works best with the models listed above.
174 125
175You 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.
176 127
184The 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.
185 136
186```137```
187138model = "gpt-5.2"model = "gpt-5.4"
188```139```
189 140
190### Choosing a different local model temporarily141### Choosing a different local model temporarily
194To 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:
195 146
196```bash147```bash
197148codex -m gpt-5.3-codexcodex -m gpt-5.4
198```149```
199 150
200### Choosing your model for cloud tasks151### Choosing your model for cloud tasks