OpenAI - Codex Docs Changes 2026-03-05 00:34 UTC → 2026-03-05 18:41 UTC

244{ "method": "model/list", "id": 6, "params": { "limit": 20, "includeHidden": false } }244{ "method": "model/list", "id": 6, "params": { "limit": 20, "includeHidden": false } }

245{ "id": 6, "result": {245{ "id": 6, "result": {

246 "data": [{246 "data": [{

247 "id": "gpt-5.2-codex",247 "id": "gpt-5.4",

248 "model": "gpt-5.2-codex",248 "model": "gpt-5.4",

249 "upgrade": "gpt-5.3-codex",249 "displayName": "GPT-5.4",

250 "displayName": "GPT-5.2 Codex",

251 "hidden": false,250 "hidden": false,

252 "defaultReasoningEffort": "medium",251 "defaultReasoningEffort": "medium",

253 "reasoningEffort": [{252 "supportedReasoningEfforts": [{

254 "effort": "low",253 "reasoningEffort": "low",

255 "description": "Lower latency"254 "description": "Lower latency"

256 }],255 }],

257 "inputModalities": ["text", "image"],256 "inputModalities": ["text", "image"],

264 263 

265Each model entry can include:264Each model entry can include:

266 265 

267- `reasoningEffort` - supported effort options for the model.266- `supportedReasoningEfforts` - supported effort options for the model.

268- `defaultReasoningEffort` - suggested default effort for clients.267- `defaultReasoningEffort` - suggested default effort for clients.

269- `upgrade` - optional recommended upgrade model id for migration prompts in clients.268- `upgrade` - optional recommended upgrade model id for migration prompts in clients.

269- `upgradeInfo` - optional upgrade metadata for migration prompts in clients.

270- `hidden` - whether the model is hidden from the default picker list.270- `hidden` - whether the model is hidden from the default picker list.

271- `inputModalities` - supported input types for the model (for example `text`, `image`).271- `inputModalities` - supported input types for the model (for example `text`, `image`).

272- `supportsPersonality` - whether the model supports personality-specific instructions such as `/personality`.272- `supportsPersonality` - whether the model supports personality-specific instructions such as `/personality`.

868 868 

869When `networkApprovalContext` is present, the prompt is for managed network access (not a general shell-command approval). The current v2 schema exposes the target `host` and `protocol`; clients should render a network-specific prompt and not rely on `command` being a user-meaningful shell command preview.869When `networkApprovalContext` is present, the prompt is for managed network access (not a general shell-command approval). The current v2 schema exposes the target `host` and `protocol`; clients should render a network-specific prompt and not rely on `command` being a user-meaningful shell command preview.

870 870 

871Codex deduplicates concurrent network approval prompts by destination (`host`, protocol, and port). The app-server may therefore send one prompt that unblocks multiple queued requests to the same destination, while different ports on the same host are treated separately.871Codex groups concurrent network approval prompts by destination (`host`, protocol, and port). The app-server may therefore send one prompt that unblocks multiple queued requests to the same destination, while different ports on the same host are treated separately.

872 872 

873### File change approvals873### File change approvals

874 874 

21For enterprises, administrators can deploy the app with Microsoft Store app21For enterprises, administrators can deploy the app with Microsoft Store app

22distribution through enterprise management tools.22distribution through enterprise management tools.

23 23 

24If you prefer a command-line install path, or need an alternative to opening

25the Microsoft Store UI, run:

26 

27```powershell

28winget install --id 9PLM9XGG6VKS

29```

30 

24## Customize for your dev setup31## Customize for your dev setup

25 32 

26### Preferred editor33### Preferred editor

156Local setup scripts run in the agent environment: WSL if the agent uses WSL,163Local setup scripts run in the agent environment: WSL if the agent uses WSL,

157and PowerShell otherwise.164and PowerShell otherwise.

158 165 

166### Share config, auth, and sessions with WSL

167 

168The Windows app uses the same Codex home directory as native Codex on Windows:

169`%USERPROFILE%\.codex`.

170 

171If you also run the Codex CLI inside WSL, the CLI uses the Linux home

172directory by default, so it does not automatically share configuration, cached

173auth, or session history with the Windows app.

174 

175To share them, use one of these approaches:

176 

177- Sync WSL `~/.codex` with `%USERPROFILE%\.codex` on your file system.

178- Point WSL at the Windows Codex home directory by setting `CODEX_HOME`:

179 

180```bash

181export CODEX_HOME=/mnt/c/Users/<windows-user>/.codex

182```

183 

184If you want that setting in every shell, add it to your WSL shell profile, such

185as `~/.bashrc` or `~/.zshrc`.

186 

159### Git features are unavailable187### Git features are unavailable

160 188 

161If you don't have Git installed natively on Windows, the app can't use some189If you don't have Git installed natively on Windows, the app can't use some

162features. Install it with `winget install Git.Git` from PowerShell or `cmd.exe`.190features. Install it with `winget install Git.Git` from PowerShell or `cmd.exe`.

163 191 

192### Git isn't detected for projects opened from `\\wsl$`

193 

194For now, if you want to use the Windows-native agent with a project that is

195also accessible from WSL, the most reliable workaround is to store the project

196on the native Windows drive and access it in WSL through `/mnt/<drive>/...`.

197 

164### Cmder is not listed in the open dialog198### Cmder is not listed in the open dialog

165 199 

166If Cmder is installed but doesn’t show in Codex’s open dialog, add it to the200If Cmder is installed but doesn’t show in Codex’s open dialog, add it to the

55 55 

56Run `codex` to start an interactive terminal UI (TUI) session.](https://developers.openai.com/codex/cli/features#running-in-interactive-mode)[### Control model and reasoning56Run `codex` to start an interactive terminal UI (TUI) session.](https://developers.openai.com/codex/cli/features#running-in-interactive-mode)[### Control model and reasoning

57 57 

58Use `/model` to switch between GPT-5.3-Codex and other available models, or adjust reasoning levels.](https://developers.openai.com/codex/cli/features#models-reasoning)[### Image inputs58Use `/model` to switch between GPT-5.4, GPT-5.3-Codex, and other available models, or adjust reasoning levels.](https://developers.openai.com/codex/cli/features#models-reasoning)[### Image inputs

59 59 

60Attach screenshots or design specs so Codex reads them alongside your prompt.](https://developers.openai.com/codex/cli/features#image-inputs)[### Run local code review60Attach screenshots or design specs so Codex reads them alongside your prompt.](https://developers.openai.com/codex/cli/features#image-inputs)[### Run local code review

61 61 

46 46 

47## Models and reasoning47## Models and reasoning

48 48 

49For most coding tasks in Codex, `gpt-5.3-codex` is the go-to model. It’s available for ChatGPT-authenticated Codex sessions in the Codex app, CLI, IDE extension, and Codex Cloud. For extra fast tasks, ChatGPT Pro subscribers have access to the GPT-5.3-Codex-Spark model in research preview.49For most tasks in Codex, `gpt-5.4` is the recommended model. It brings the industry-leading coding capabilities of `gpt-5.3-codex` to OpenAI’s flagship frontier model, combining frontier coding performance with stronger reasoning, native computer use, and broader professional workflows. For extra fast tasks, ChatGPT Pro subscribers have access to the GPT-5.3-Codex-Spark model in research preview.

50 50 

51Switch models mid-session with the /model command, or specify one when launching the CLI.51Switch models mid-session with the `/model` command, or specify one when launching the CLI.

52 52 

53```bash53```bash

54codex --model gpt-5.3-codex54codex --model gpt-5.4

55```55```

56 56 

57[Learn more about the models available in Codex](https://developers.openai.com/codex/models).57[Learn more about the models available in Codex](https://developers.openai.com/codex/models).

45 45 

46```shell46```shell

47# Dedicated flag47# Dedicated flag

48codex --model gpt-5.248codex --model gpt-5.4

49 49 

50# Generic key/value override (value is TOML, not JSON)50# Generic key/value override (value is TOML, not JSON)

51codex --config model='"gpt-5.2"'51codex --config model='"gpt-5.4"'

52codex --config sandbox_workspace_write.network_access=true52codex --config sandbox_workspace_write.network_access=true

53codex --config 'shell_environment_policy.include_only=["PATH","HOME"]'53codex --config 'shell_environment_policy.include_only=["PATH","HOME"]'

54```54```

190 190 

191Pick approval strictness (affects when Codex pauses) and sandbox level (affects file/network access).191Pick approval strictness (affects when Codex pauses) and sandbox level (affects file/network access).

192 192 

193For operational details that are easy to miss while editing `config.toml`, see [Common sandbox and approval combinations](https://developers.openai.com/codex/security#common-sandbox-and-approval-combinations), [Protected paths in writable roots](https://developers.openai.com/codex/security#protected-paths-in-writable-roots), and [Network access](https://developers.openai.com/codex/security#network-access).193For operational details people often miss while editing `config.toml`, see [Common sandbox and approval combinations](https://developers.openai.com/codex/security#common-sandbox-and-approval-combinations), [Protected paths in writable roots](https://developers.openai.com/codex/security#protected-paths-in-writable-roots), and [Network access](https://developers.openai.com/codex/security#network-access).

194 194 

195You can also use a granular reject policy (`approval_policy = { reject = { ... } }`) to auto-reject only selected prompt categories (sandbox approvals, execpolicy rule prompts, or MCP elicitations) while keeping other prompts interactive.195You can also use a granular reject policy (`approval_policy = { reject = { ... } }`) to auto-reject only selected prompt categories, such as sandbox approvals, `execpolicy` rule prompts, or MCP input requests (`mcp_elicitations`), while keeping other prompts interactive.

196 196 

197```197```

198approval_policy = "untrusted" # Other options: on-request, never, or { reject = { ... } }198approval_policy = "untrusted" # Other options: on-request, never, or { reject = { ... } }

46Choose the model Codex uses by default in the CLI and IDE.46Choose the model Codex uses by default in the CLI and IDE.

47 47 

48```toml48```toml

49model = "gpt-5.2"49model = "gpt-5.4"

50```50```

51 51 

52#### Approval prompts52#### Approval prompts

71 71 

72#### Windows sandbox mode72#### Windows sandbox mode

73 73 

74When running Codex natively on Windows, set the native sandbox mode to `elevated` in the `windows` table. Use `unelevated` only if you do not have administrator permissions or if elevated setup fails.74When running Codex natively on Windows, set the native sandbox mode to `elevated` in the `windows` table. Use `unelevated` only if you don't have administrator permissions or if elevated setup fails.

75 75 

76```toml76```toml

77[windows]77[windows]

1# Sample Configuration1# Sample Configuration

2 2 

3Use this example configuration as a starting point. It includes most keys Codex reads from `config.toml`, along with defaults and short notes.3Use this example configuration as a starting point. It includes most keys Codex reads from `config.toml`, along with default behaviors, recommended values where helpful, and short notes.

4 4 

5For explanations and guidance, see:5For explanations and guidance, see:

6 6 

15```toml15```toml

16# Codex example configuration (config.toml)16# Codex example configuration (config.toml)

17#17#

18# This file lists all keys Codex reads from config.toml, their default values,18# This file lists all keys Codex reads from config.toml, along with default

19# and concise explanations. Values here mirror the effective defaults compiled19# behaviors, recommended examples, and concise explanations. Adjust as needed.

20# into the CLI. Adjust as needed.

21#20#

22# Notes21# Notes

23# - Root keys must appear before tables in TOML.22# - Root keys must appear before tables in TOML.

28# Core Model Selection27# Core Model Selection

29################################################################################28################################################################################

30 29 

31# Primary model used by Codex. Default: "gpt-5.2-codex" on all platforms.30# Primary model used by Codex. Recommended example for most users: "gpt-5.4".

32model = "gpt-5.2-codex"31model = "gpt-5.4"

33 32 

34# Default communication style for supported models. Default: "friendly".33# Default communication style for supported models. Default: "friendly".

35# Allowed values: none | friendly | pragmatic34# Allowed values: none | friendly | pragmatic

36# personality = "friendly"35# personality = "friendly"

37 36 

38# Optional model override for /review. Default: unset (uses current session model).37# Optional model override for /review. Default: unset (uses current session model).

39# review_model = "gpt-5.2-codex"38# review_model = "gpt-5.4"

40 39 

41# Provider id selected from [model_providers]. Default: "openai".40# Provider id selected from [model_providers]. Default: "openai".

42model_provider = "openai"41model_provider = "openai"

48# Uncomment to force values.47# Uncomment to force values.

49# model_context_window = 128000 # tokens; default: auto for model48# model_context_window = 128000 # tokens; default: auto for model

50# model_auto_compact_token_limit = 0 # tokens; unset uses model defaults49# model_auto_compact_token_limit = 0 # tokens; unset uses model defaults

51# tool_output_token_limit = 10000 # tokens stored per tool output; default: 10000 for gpt-5.2-codex50# tool_output_token_limit = 10000 # tokens stored per tool output

52# model_catalog_json = "/absolute/path/to/models.json" # optional startup-only model catalog override51# model_catalog_json = "/absolute/path/to/models.json" # optional startup-only model catalog override

53# background_terminal_max_timeout = 300000 # ms; max empty write_stdin poll window (default 5m)52# background_terminal_max_timeout = 300000 # ms; max empty write_stdin poll window (default 5m)

54# log_dir = "/absolute/path/to/codex-logs" # directory for Codex logs; default: "$CODEX_HOME/log"53# log_dir = "/absolute/path/to/codex-logs" # directory for Codex logs; default: "$CODEX_HOME/log"

58# Reasoning & Verbosity (Responses API capable models)57# Reasoning & Verbosity (Responses API capable models)

59################################################################################58################################################################################

60 59 

61# Reasoning effort: minimal | low | medium | high | xhigh (default: medium; xhigh on gpt-5.2-codex and gpt-5.2)60# Reasoning effort: minimal | low | medium | high | xhigh (default: medium; `xhigh` availability is model-dependent)

62model_reasoning_effort = "medium"61model_reasoning_effort = "medium"

63 62 

64# Reasoning summary: auto | concise | detailed | none (default: auto)63# Reasoning summary: auto | concise | detailed | none (default: auto)

438[profiles]437[profiles]

439 438 

440# [profiles.default]439# [profiles.default]

441# model = "gpt-5.2-codex"440# model = "gpt-5.4"

442# model_provider = "openai"441# model_provider = "openai"

443# approval_policy = "on-request"442# approval_policy = "on-request"

444# sandbox_mode = "read-only"443# sandbox_mode = "read-only"

536 535 

537[windows]536[windows]

538 537 

539# Native Windows sandbox mode (Windows only): unelevated | elevated538# Native Windows sandbox mode (Windows only). The example below uses the

540 539 

541sandbox = "unelevated"540# recommended elevated mode.

541 

542sandbox = “elevated”

2 2 

3## Recommended models3## Recommended models

4 4 

5![gpt-5.4](/images/codex/codex-wallpaper-3.webp)

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 

5![gpt-5.3-codex](/images/codex/codex-wallpaper-1.webp)29![gpt-5.3-codex](/images/codex/codex-wallpaper-1.webp)

6 30 

7gpt-5.3-codex31gpt-5.3-codex

8 32 

9Most capable agentic coding model to date, combining frontier coding performance with stronger reasoning and professional knowledge capabilities.33Industry-leading coding model for complex software engineering. Its coding capabilities now also power GPT-5.4.

10 34 

11codex -m gpt-5.3-codex35codex -m gpt-5.3-codex

12 36 

50 74 

51API Access75API Access

52 76 

53The gpt-5.3-codex-spark model is available in research preview for ChatGPT Pro77For most tasks in Codex, start with `gpt-5.4`. It combines strong coding,

54subscribers. It is optimized for near-instant, real-time coding iteration.78reasoning, native computer use, and broader professional workflows in one

79model. The `gpt-5.3-codex-spark` model is available in research preview for

80ChatGPT Pro subscribers and is optimized for near-instant, real-time coding

81iteration.

55 82 

56## Alternative models83## Alternative models

57 84 

71 98 

72gpt-5.299gpt-5.2

73 100 

74Our best general agentic model for tasks across industries and domains.101Previous general-purpose model for coding and agentic tasks across industries and domains. Succeeded by GPT-5.4.

75 102 

76codex -m gpt-5.2103codex -m gpt-5.2

77 104 

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.194The 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.

168 195 

169```196```

170model = "gpt-5.2"197model = "gpt-5.4"

171```198```

172 199 

173### Choosing a different local model temporarily200### 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:204To 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:

178 205 

179```bash206```bash

180codex -m gpt-5.3-codex207codex -m gpt-5.4

181```208```

182 209 

183### Choosing your model for cloud tasks210### Choosing your model for cloud tasks

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 is currently supported on GPT-5.4. When enabled, speed is increased

9by 1.5x and credits are consumed at a 2x rate.

10 

11Enable it by typing `/fast`. It is available in Codex IDE Extensions, Codex

12CLI, and the Codex app.

13 

14[

15Your browser does not support the video tag.

16](/videos/codex/fast-mode-demo.mp4)

17 

18## Codex-Spark

19 

20GPT-5.3-Codex-Spark is a separate fast, less-capable Codex model optimized for near-instant, real-time coding iteration. Unlike fast mode, which speeds up GPT-5.4 at a higher credit rate,

21Codex-Spark is its own model choice and has its own usage limits.

22 

23During research preview Codex-Spark is only available for ChatGPT Pro subscribers.