Documentation 2026-10-12 22:58 UTC to 2026-10-13 23:00 UTC

8 8 

9This page lists all API deprecations, along with recommended replacements.9This page lists all API deprecations, along with recommended replacements.

10 10 

11To monitor model shutdowns programmatically, call the [List models endpoint](https://developers.openai.com/api/reference/resources/models/methods/list) (`GET /v1/models`) and check each model's optional `shutdown_date` field. When present, this field contains the shutdown date as a `YYYY-MM-DD` string, or `null` if no shutdown date has been announced; the field is also available from the [Retrieve a model endpoint](https://developers.openai.com/api/reference/resources/models/methods/retrieve).

12 

11## Model deprecation notice periods13## Model deprecation notice periods

12 14 

13We provide advance notice before retiring models so customers have time to plan and migrate. When we announce a model deprecation, we notify customers who are actively using the model by email and document the deprecation on this page.15We provide advance notice before retiring models so customers have time to plan and migrate. When we announce a model deprecation, we notify customers who are actively using the model by email and document the deprecation on this page.

34 36 

35Upcoming deprecations are listed below, with the most recent announcements at the top.37Upcoming deprecations are listed below, with the most recent announcements at the top.

36 38 

39### 2026-10-14: GPT-4 series model deprecations

40 

41On October 14, 2026, we notified developers using certain GPT-4 series models of their deprecation and removal from the API on January 14, 2027.

42 

43| Shutdown date | Model / system | Recommended replacement |

44| ---------------- | ------------------------------------------------- | ----------------------- |

45| January 14, 2027 | GPT-4o (`gpt-4o-2024-08-06`, `gpt-4o-2024-11-20`) | `gpt-6-luna` |

46| January 14, 2027 | GPT-4o mini (`gpt-4o-mini-2024-07-18`) | `gpt-6-luna` |

47| January 14, 2027 | GPT-4.1 (`gpt-4.1-2025-04-14`) | `gpt-6-luna` |

48| January 14, 2027 | GPT-4.1 mini (`gpt-4.1-mini-2025-04-14`) | `gpt-6-luna` |

49 

50Fine-tuned versions of these models follow the same shutdown schedule as their underlying base models.

51 

37### 2026-10-01: GPT-5.3-Codex, GPT-5.1, GPT-5.4-Nano52### 2026-10-01: GPT-5.3-Codex, GPT-5.1, GPT-5.4-Nano

38 53 

39The following models are deprecated and will be removed from the API on April 1, 2027, with six months' notice. Migrate to the recommended replacements before the shutdown date.54The following models are deprecated and will be removed from the API on April 1, 2027, with six months' notice. Migrate to the recommended replacements before the shutdown date.

155| July 2, 2026 | Creating fine-tuning jobs is no longer available to organizations that have not run inference on a fine-tuned model in the past 60 days. |170| July 2, 2026 | Creating fine-tuning jobs is no longer available to organizations that have not run inference on a fine-tuned model in the past 60 days. |

156| Jan 6, 2027 | Active existing customers will no longer be able to create new fine-tuning jobs on this date. Inference on fine-tuned models will be disabled only when the underlying base model is deprecated. |171| Jan 6, 2027 | Active existing customers will no longer be able to create new fine-tuning jobs on this date. Inference on fine-tuned models will be disabled only when the underlying base model is deprecated. |

157 172 

158## Past deprecations

159 

160Past deprecations are listed below, with the most recent announcements at the top.

161 

162### 2026-09-11: GPT-5.4-Cyber

163 

164The `gpt-5.4-cyber` model is deprecated and will be removed from the API on October 1, 2026. Migrate to the most capable cyber model available to you before the shutdown date.

165 

166| Shutdown date | Model / system | Recommended replacement |

167| ------------- | --------------- | ---------------------------------------------- |

168| Oct 1, 2026 | `gpt-5.4-cyber` | The most capable cyber model available to you. |

169 

170### 2026-05-08: `gpt-5.2-chat-latest` and `gpt-5.3-chat-latest` model snapshots

171 

172On May 8th, 2026, we notified developers using `gpt-5.2-chat-latest` and `gpt-5.3-chat-latest` model snapshots of their deprecation and removal from the API.

173 

174| Shutdown date | Model / system | Recommended replacement |

175| ------------- | --------------------- | ----------------------- |

176| Aug 10, 2026 | `gpt-5.2-chat-latest` | `gpt-5.6-sol` |

177| Aug 10, 2026 | `gpt-5.3-chat-latest` | `gpt-5.6-sol` |

178 

179### 2026-04-22: Legacy GPT model snapshots173### 2026-04-22: Legacy GPT model snapshots

180 174 

181To improve reliability and make it easier for developers to choose the right models, we are deprecating a set of older OpenAI models. Access to these models will be shut down on the dates below.175To improve reliability and make it easier for developers to choose the right models, we are deprecating a set of older OpenAI models. Access to these models will be shut down on the dates below.

205| October 23, 2026 | `ft-babbage-002` | `gpt-5.6-terra` |199| October 23, 2026 | `ft-babbage-002` | `gpt-5.6-terra` |

206| October 23, 2026 | `ft-davinci-002` | `gpt-5.6-terra` |200| October 23, 2026 | `ft-davinci-002` | `gpt-5.6-terra` |

207 201 

202## Past deprecations

203 

204Past deprecations are listed below, with the most recent announcements at the top.

205 

206### 2026-09-11: GPT-5.4-Cyber

207 

208The `gpt-5.4-cyber` model is deprecated and will be removed from the API on October 1, 2026. Migrate to the most capable cyber model available to you before the shutdown date.

209 

210| Shutdown date | Model / system | Recommended replacement |

211| ------------- | --------------- | ---------------------------------------------- |

212| Oct 1, 2026 | `gpt-5.4-cyber` | The most capable cyber model available to you. |

213 

214### 2026-05-08: `gpt-5.2-chat-latest` and `gpt-5.3-chat-latest` model snapshots

215 

216On May 8th, 2026, we notified developers using `gpt-5.2-chat-latest` and `gpt-5.3-chat-latest` model snapshots of their deprecation and removal from the API.

217 

218| Shutdown date | Model / system | Recommended replacement |

219| ------------- | --------------------- | ----------------------- |

220| Aug 10, 2026 | `gpt-5.2-chat-latest` | `gpt-5.6-sol` |

221| Aug 10, 2026 | `gpt-5.3-chat-latest` | `gpt-5.6-sol` |

222 

208### 2026-04-22: Legacy GPT model snapshots (July 2026 shutdown)223### 2026-04-22: Legacy GPT model snapshots (July 2026 shutdown)

209 224 

210On April 22, 2026, we announced the deprecation of the following older OpenAI models. Access to these models was shut down on July 23, 2026.225On April 22, 2026, we announced the deprecation of the following older OpenAI models. Access to these models was shut down on July 23, 2026.

20 20 

21## Pricing21## Pricing

22 22 

23Pre-warming a sandbox is free, including container usage before attachment. Unattached pre-warmed sandboxes expire after five minutes.23Pre-warming a sandbox is free, including container usage before attachment. Unattached pre-warmed sandboxes expire after 5 minutes.

24 24 

25After you attach a pre-warmed sandbox to a session, standard [container pricing](https://developers.openai.com/api/docs/pricing#container-usage-pricing) applies.25After you attach a pre-warmed sandbox to a session, standard [container pricing](https://developers.openai.com/api/docs/pricing#container-usage-pricing) applies.

26 26 

28 28 

29This example installs pandas and loads a small CSV before starting an agent. The agent then uses the prepared workspace to calculate the total.29This example installs pandas and loads a small CSV before starting an agent. The agent then uses the prepared workspace to calculate the total.

30 30 

31The create and attach examples require Python SDK 3.27.0, Node.js SDK 7.31.0, Java SDK 4.79.0, or Ruby SDK 0.102.0 or later. Upgrade your SDK if these methods are unavailable.31Use Python SDK 3.28.0, Node.js SDK 7.32.0, Java SDK 4.80.0, or Ruby SDK 0.103.0 or later for this guide.

32 32 

33### 1. Create the environment33### 1. Create the environment

34 34 

294 294 

295| Error or symptom | How to resolve |295| Error or symptom | How to resolve |

296| -------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |296| -------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |

297| Attaching an expired environment. | Create a new environment and use its new ID. Unused environments expire after approximately five minutes. Retrying an expired ID will not restore its workspace. |297| Attaching an expired environment. | Create a new environment and use its new ID. Unused environments expire after 5 minutes. Retrying an expired ID will not restore its workspace. |

298| `404`: environment not found. | Check the environment ID and use the same organization, project, and creating identity as the creation request. If the environment has expired or is no longer available, create a new one. |298| `404`: environment not found. | Check the environment ID and use the same organization, project, and creating identity as the creation request. If the environment has expired or is no longer available, create a new one. |

299| `409`: shared environment has reached its session limit. | A shared environment supports up to 128 attached sessions. Reuse an existing session or create another environment for additional sessions. |299| `409`: shared environment has reached its session limit. | A shared environment supports up to 128 attached sessions. Reuse an existing session or create another environment for additional sessions. |

300 300 

486```486```

487 487 

488 488 

489The list includes environments before and after session attachment, with statuses `pending`, `ready`, `connected`, or `disconnected`. It excludes failed, expired, deleted, and terminated environments. An environment appearing in the list may already be attached to one or more sessions.489The list includes environments before and after session attachment, with statuses `pending`, `ready`, `connected`, `disconnected`, or `suspended`. It excludes failed, expired, deleted, and terminated environments. An environment appearing in the list may already be attached to one or more sessions.

490 490 

491Results are newest first by default. If `has_more` is true, set `after` to the previous response's `last_id` to fetch the next page. `limit` accepts 1–100 and defaults to 20; `order` accepts `asc` or `desc`.491Results are newest first by default. If `has_more` is true, set `after` to the previous response's `last_id` to fetch the next page. `limit` accepts 1–100 and defaults to 20; `order` accepts `asc` or `desc`.

492 492 

493## Lifetime and reuse493## Lifetime and reuse

494 494 

495- **Multiple sessions can share one environment.** Pass the same `environment_id` when creating each session. They share the running workspace, including files, processes, installed packages, and environment configuration. Each session keeps its own conversation history. Changes to the workspace are visible to other attached sessions, so create separate environments when tasks need separate workspaces. A shared environment supports up to 128 attached sessions. This behavior applies to newly created standalone environments; older environments retain their original lifecycle.495- **Multiple sessions can share one environment.** Pass the same `environment_id` when creating each session. They share the running workspace, including files, processes, installed packages, and environment configuration. Each session keeps its own conversation history. Changes to the workspace are visible to other attached sessions, so create separate environments when tasks need separate workspaces. A shared environment supports up to 128 attached sessions. This behavior applies to newly created standalone environments; older environments retain their original lifecycle.

496- **Unused environments expire.** An environment that remains unattached expires after approximately 5 minutes. Prewarm close to when you expect a task to start.496- **Unused environments expire.** An environment that remains unattached expires after 5 minutes. Prewarm close to when you expect a task to start.

497- **Keep the creating identity consistent.** Retrieval, listing, and attachment require the same organization, project, and authenticated identity that created the environment. Different API keys for that identity can access the same environments, including after key rotation.497- **Keep the creating identity consistent.** Retrieval, listing, and attachment require the same organization, project, and authenticated identity that created the environment. Different API keys for that identity can access the same environments, including after key rotation.

498- **Shared environments expire after inactivity.** The first attachment starts a 20-minute idle lifetime. Activity in any attached session or through the environment file API extends it; pending work and active turns prevent idle expiry. Deleting a session removes that session from the environment without deleting the shared workspace. Even after the last session is deleted, the environment remains available for attachment until its idle deadline. The API has no standalone environment deletion endpoint.498- **Shared environments expire after inactivity.** The first attachment starts a 20-minute idle lifetime. Activity in any attached session or through the environment file API extends it; pending work and active turns prevent idle expiry. Deleting a session removes that session from the environment without deleting the shared workspace. Even after the last session is deleted, the environment remains available for attachment until its idle deadline. The API has no standalone environment deletion endpoint.

499 499 

245 245 

246### Greet before the caller speaks246### Greet before the caller speaks

247 247 

248To have GPT-Live open the conversation, send greeting instructions after `session.started`. Specify the language, what the assistant should say, and that it should begin immediately, then pause to listen. Use the application’s chosen greeting language until the caller speaks. For example:248For best results when GPT-Live should open the conversation, include greeting instructions in a `developer` message in `session.input` when you create the session. On WebSocket, include the message in the `session.start` event instead of waiting until `session.started` to append it. This makes the greeting instructions available from the start.

249 

250Specify the language, what the assistant should say, and that it should begin immediately, then pause to listen. Use the application’s chosen greeting language until the caller speaks. For example, use this text for the developer message:

249 251 

250> Greet the caller now in English. Introduce yourself as the support assistant and ask how you can help. Then pause and listen.252> Greet the caller now in English. Introduce yourself as the support assistant and ask how you can help. Then pause and listen.

251 253 

2521. Keep input audio running throughout this sequence, including silence before the caller speaks. On WebSocket, continue sending `session.input_audio.append`; on WebRTC, keep the input audio track active.2541. Add the message to `session.input` with `role: "developer"` and one `input_text` content part. See [Seed a session with prior conversation](#seed-a-session-with-prior-conversation) for the message format.

2532. Send the instructions once with `session.instructions.append` and `delegation_id: null`.2552. Wait for `session.started`, then keep input audio running, including silence before the caller speaks. On WebSocket, continue sending `session.input_audio.append`; on WebRTC, keep the input audio track active.

2543. Match `session.instructions.appended` to your command using `client_event_id`, and handle any error. This acknowledgment confirms that the instructions were accepted.2563. Check the output audio and transcript to verify that the assistant greeted the caller. Startup instructions can improve greeting behavior, but do not guarantee that the model will speak.

255 257 

256For exact wording and a known playback-completion point, play a verified recording or rendered clip through your application and [control GPT-Live playback while it plays](https://developers.openai.com/api/docs/guides/voice-server-controls?api=live#control-playback-when-needed). Test greetings in the languages you support, including when the caller starts speaking during the greeting. See [Prompting voice models](https://developers.openai.com/api/docs/guides/live-prompting) for prompt design.258For predictable greeting playback, exact wording, or a known playback-completion point, play a verified recording or rendered clip through your application and [control GPT-Live playback while it plays](https://developers.openai.com/api/docs/guides/voice-server-controls?api=live#control-playback-when-needed). Test greetings in the languages you support, including when the caller starts speaking during the greeting. See [Prompting voice models](https://developers.openai.com/api/docs/guides/live-prompting) for prompt design.

257 259 

258### Deliver a disclosure260### Deliver a disclosure

259 261 

308Choose an event based on how GPT-Live should use the content:308Choose an event based on how GPT-Live should use the content:

309 309 

310| What you want to send | Event |310| What you want to send | Event |

311| ----------------------------------------------------------------------------------------------------------- | ----------------------------- |311| ------------------------------------------------------------------------------------------------- | ----------------------------- |

312| System-level instructions for the live model, such as a greeting, disclosure, or direction to stop speaking | `session.instructions.append` |312| Instructions for an ongoing live conversation, such as a disclosure or direction to stop speaking | `session.instructions.append` |

313| Information for internal reasoning, not spoken on append but usable for relevant user questions | `session.thinking.append` |313| Information for internal reasoning, not spoken on append but usable for relevant user questions | `session.thinking.append` |

314| Information the model should speak aloud, paraphrasing the appended text | `session.commentary.append` |314| Information the model should speak aloud, paraphrasing the appended text | `session.commentary.append` |

315 315 

316All three use a plain-string `content`, limited to 500 tokens per append. Include `delegation_id`: use the original client delegation ID for an update about that task, or `null` for general session context. A non-null ID must identify a known client delegation. Instructions still apply to the live session; an ID does not turn them into a separate backend prompt.316All three use a plain-string `content`, limited to 500 tokens per append. Include `delegation_id`: use the original client delegation ID for an update about that task, or `null` for general session context. A non-null ID must identify a known client delegation. Instructions still apply to the live session; an ID does not turn them into a separate backend prompt.

317 317 

318For an opening greeting, include a `developer` message in `session.input` at startup instead. See [Greet before the caller speaks](https://developers.openai.com/api/docs/guides/live-conversations#greet-before-the-caller-speaks).

319 

318An appended instruction can interrupt the model's current speech or behavior. Use it when the application needs to redirect the conversation; enforce any related tool or action block in application state.320An appended instruction can interrupt the model's current speech or behavior. Use it when the application needs to redirect the conversation; enforce any related tool or action block in application state.

319 321 

320For quiet progress during a client-managed task:322For quiet progress during a client-managed task:

125Say the user's name Rosalia as "roh-sah-LEE-ah", IPA /rosaˈli.a/ (Spanish).125Say the user's name Rosalia as "roh-sah-LEE-ah", IPA /rosaˈli.a/ (Spanish).

126```126```

127 127 

128To open the conversation in a chosen language, wait for `session.started`, keep input audio running, and send `session.instructions.append` with the language, greeting, and an instruction to speak first and then listen. Handle its acknowledgment or error while audio continues. Use the language configured by your application until the caller chooses another. See [Greet the caller](https://developers.openai.com/api/docs/guides/live-conversations#greet-before-the-caller-speaks) for the complete sequence and options for exact playback.128To open the conversation in a chosen language, include a `developer` message in `session.input` when you create the session. Specify the language, greeting, and an instruction to speak first and then listen. On WebSocket, include this message in `session.start` instead of appending it after startup. After `session.started`, keep input audio running. Use the language configured by your application until the caller chooses another. Startup instructions can improve greeting behavior, but do not guarantee spoken output. See [Greet the caller](https://developers.openai.com/api/docs/guides/live-conversations#greet-before-the-caller-speaks) for the complete sequence and application-controlled playback options.

129 129 

130### Translation130### Translation

131 131 

89| Host running `tunnel-client` | `mtls.api.openai.com:443` over HTTPS on `/v1/tunnel/*` | Polling and response posting when control-plane mTLS is configured. |89| Host running `tunnel-client` | `mtls.api.openai.com:443` over HTTPS on `/v1/tunnel/*` | Polling and response posting when control-plane mTLS is configured. |

90| Host running `tunnel-client` | The configured stdio command or MCP server URL | Forwarding MCP requests from inside your network. |90| Host running `tunnel-client` | The configured stdio command or MCP server URL | Forwarding MCP requests from inside your network. |

91 91 

92## Limits

93 

94Secure MCP Tunnel applies these default hosted-service limits to connector MCP traffic:

95 

96| Limit | Default | Scope |

97| ------------------------------ | ------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |

98| MCP request rate | 600 requests per minute (10 per second sustained) | Shared by requests with the same tunnel ID and calling application ID across MCP channels. If the calling application ID is unavailable, requests with the same tunnel ID and user share the limit. Running more than one `tunnel-client` process does not multiply the allowance. |

99| Serialized request or response | 10 MiB (10,485,760 bytes) | Applies to the complete serialized tunnel envelope, including headers and protocol metadata, so usable MCP content is slightly smaller. The service applies the limit to each streaming notification and final response. |

100| Request deadline | 120 seconds | One absolute budget from when the request enters the hosted queue through final response delivery. Queue time consumes this budget, and progress notifications do not reset it. |

101| Pending queue | 1,000 requests per tunnel | Shared across MCP channels. Counts requests waiting for `tunnel-client` to poll them; requests already fetched for execution are not included. |

102 

103These limits are service protections, not throughput or latency guarantees. Queue-record retention for cleanup does not extend the 120-second request deadline. To request a change to these limits, contact [OpenAI Support](https://help.openai.com/en/articles/6614161-how-can-i-contact-support).

104 

92## Set up tunnel-client105## Set up tunnel-client

93 106 

94Open [Platform tunnel settings](https://platform.openai.com/settings/organization/tunnels), then use the download link there or the latest public `tunnel-client` release from [openai/tunnel-client](https://github.com/openai/tunnel-client/releases/latest). Keep your runbook pointed at the latest-release URL instead of hard-coding a specific release URL.107Open [Platform tunnel settings](https://platform.openai.com/settings/organization/tunnels), then use the download link there or the latest public `tunnel-client` release from [openai/tunnel-client](https://github.com/openai/tunnel-client/releases/latest). Keep your runbook pointed at the latest-release URL instead of hard-coding a specific release URL.

139 152 

140If the tunnel does not appear in ChatGPT, verify that the tunnel is associated with the target ChatGPT workspace, not only with a Platform organization, and that the app creator has Tunnels **Read** + **Use**.153If the tunnel does not appear in ChatGPT, verify that the tunnel is associated with the target ChatGPT workspace, not only with a Platform organization, and that the app creator has Tunnels **Read** + **Use**.

141 154 

155## Set up and verify with Codex

156 

157To have Codex guide the setup, give it browser access to Platform and ChatGPT

158and terminal access to the host that can reach your private MCP server. Paste

159this prompt into Codex:

160 

161```text

162Help me set up and verify a private Secure MCP Tunnel from my internal MCP

163server to ChatGPT end to end. Use browser/computer access and a terminal,

164following https://developers.openai.com/api/docs/guides/secure-mcp-tunnels

165and https://github.com/openai/tunnel-client/blob/master/docs/onboarding.md;

166check the current UI and CLI help as you go.

167 

168First identify the intended Platform organization and ChatGPT workspace, MCP

169server HTTP URL or stdio command, and client host. Inspect any existing tunnel,

170key, and ChatGPT custom MCP plugin; reuse suitable resources. Confirm the

171tunnel's organization and workspace association and permissions: tunnel

172creators need Tunnels Read + Manage; the restricted runtime key and plugin

173operator need Tunnels Read + Use.

174 

175Keep literal secrets out of chat, command arguments, logs, screenshots, and

176config files. Have me enter them locally through a secure input or environment

177reference. Install the supported tunnel-client; run

178`tunnel-client help quickstart`, configure the server, run

179`tunnel-client doctor --profile <name> --explain`, start the client, and

180verify readiness and active polling. Keep it running for discovery and calls.

181 

182In ChatGPT Plugins, add or finish a private custom MCP server with

183Connection: Tunnel, select the same tunnel, configure required authentication,

184and make a safe representative tool call. Report observed evidence for each

185checkpoint and the exact error and next action for any blocker. Call setup

186complete only after the ChatGPT tool call succeeds.

187```

188 

142## Connect from the Responses API189## Connect from the Responses API

143 190 

144Pass the tunnel identifier as `tunnel_id` in the MCP tool definition. Do not pass the OpenAI-hosted tunnel endpoint as `server_url`; use `server_url` only for an MCP server that the Responses API can reach directly.191Pass the tunnel identifier as `tunnel_id` in the MCP tool definition. Do not pass the OpenAI-hosted tunnel endpoint as `server_url`; use `server_url` only for an MCP server that the Responses API can reach directly.

173<dependency>173<dependency>

174 <groupId>com.openai</groupId>174 <groupId>com.openai</groupId>

175 <artifactId>openai-java</artifactId>175 <artifactId>openai-java</artifactId>

176 <version>4.80.0</version>176 <version>4.81.0</version>

177</dependency>177</dependency>

178```178```

179 179 

90- [GPT-5 Pro](/api/docs/models/gpt-5-pro.md): Version of GPT-5 that produces smarter and more precise responses90- [GPT-5 Pro](/api/docs/models/gpt-5-pro.md): Version of GPT-5 that produces smarter and more precise responses

91- [o3-pro](/api/docs/models/o3-pro.md): Version of o3 with more compute for better responses91- [o3-pro](/api/docs/models/o3-pro.md): Version of o3 with more compute for better responses

92- [o3](/api/docs/models/o3.md): Reasoning model for complex tasks, succeeded by GPT-592- [o3](/api/docs/models/o3.md): Reasoning model for complex tasks, succeeded by GPT-5

93- [GPT-4.1](/api/docs/models/gpt-4.1.md): Smartest non-reasoning model

94- [GPT-4.1 Mini](/api/docs/models/gpt-4.1-mini.md): Smaller, faster version of GPT-4.1

95- [omni-moderation](/api/docs/models/omni-moderation-latest.md): Identify potentially harmful content in text and images93- [omni-moderation](/api/docs/models/omni-moderation-latest.md): Identify potentially harmful content in text and images

96- [GPT-4o Mini](/api/docs/models/gpt-4o-mini.md): Fast, affordable small model for focused tasks

97- [GPT-4o](/api/docs/models/gpt-4o.md): Fast, intelligent, flexible GPT model

98- [Daybreak Red](/api/docs/models/gpt-daybreak-red-latest.md): Deprecated. An alias for advanced cybersecurity models for authorized vulnerability research and security testing.94- [Daybreak Red](/api/docs/models/gpt-daybreak-red-latest.md): Deprecated. An alias for advanced cybersecurity models for authorized vulnerability research and security testing.

99- [Daybreak Blue](/api/docs/models/gpt-daybreak-blue-latest.md): Deprecated. An alias for flagship general-purpose models with safeguards for defensive cybersecurity work.95- [Daybreak Blue](/api/docs/models/gpt-daybreak-blue-latest.md): Deprecated. An alias for flagship general-purpose models with safeguards for defensive cybersecurity work.

100- [GPT-5.4 nano](/api/docs/models/gpt-5.4-nano.md): Deprecated. Our cheapest GPT-5.4-class model for simple high-volume tasks96- [GPT-5.4 nano](/api/docs/models/gpt-5.4-nano.md): Deprecated. Our cheapest GPT-5.4-class model for simple high-volume tasks

102- [GPT-5.1](/api/docs/models/gpt-5.1.md): Deprecated. The best model for coding and agentic tasks with configurable reasoning effort98- [GPT-5.1](/api/docs/models/gpt-5.1.md): Deprecated. The best model for coding and agentic tasks with configurable reasoning effort

103- [GPT-Realtime](/api/docs/models/gpt-realtime.md): Deprecated. Model capable of realtime text and audio inputs and outputs99- [GPT-Realtime](/api/docs/models/gpt-realtime.md): Deprecated. Model capable of realtime text and audio inputs and outputs

104- [GPT-Audio](/api/docs/models/gpt-audio.md): Deprecated. For audio inputs and outputs with Chat Completions API100- [GPT-Audio](/api/docs/models/gpt-audio.md): Deprecated. For audio inputs and outputs with Chat Completions API

101- [GPT-4.1](/api/docs/models/gpt-4.1.md): Deprecated. Smartest non-reasoning model

102- [GPT-4.1 Mini](/api/docs/models/gpt-4.1-mini.md): Deprecated. Smaller, faster version of GPT-4.1

103- [GPT-4o Mini](/api/docs/models/gpt-4o-mini.md): Deprecated. Fast, affordable small model for focused tasks

105- [TTS-1](/api/docs/models/tts-1.md): Deprecated. Text-to-speech model optimized for speed104- [TTS-1](/api/docs/models/tts-1.md): Deprecated. Text-to-speech model optimized for speed

106- [TTS-1 HD](/api/docs/models/tts-1-hd.md): Deprecated. Text-to-speech model optimized for quality105- [TTS-1 HD](/api/docs/models/tts-1-hd.md): Deprecated. Text-to-speech model optimized for quality

107- [GPT-5.3 Chat](/api/docs/models/gpt-5.3-chat-latest.md): Deprecated. GPT-5.3 Instant model used in ChatGPT106- [GPT-5.3 Chat](/api/docs/models/gpt-5.3-chat-latest.md): Deprecated. GPT-5.3 Instant model used in ChatGPT

126- [o1](/api/docs/models/o1.md): Deprecated. Previous full o-series reasoning model125- [o1](/api/docs/models/o1.md): Deprecated. Previous full o-series reasoning model

127- [o1-mini](/api/docs/models/o1-mini.md): Deprecated. A small model alternative to o1126- [o1-mini](/api/docs/models/o1-mini.md): Deprecated. A small model alternative to o1

128- [o1 Preview](/api/docs/models/o1-preview.md): Deprecated. Preview of our first o-series reasoning model127- [o1 Preview](/api/docs/models/o1-preview.md): Deprecated. Preview of our first o-series reasoning model

128- [GPT-4o](/api/docs/models/gpt-4o.md): Deprecated. Fast, intelligent, flexible GPT model

129- [GPT-4o Audio](/api/docs/models/gpt-4o-audio-preview.md): Deprecated. GPT-4o models capable of audio inputs and outputs129- [GPT-4o Audio](/api/docs/models/gpt-4o-audio-preview.md): Deprecated. GPT-4o models capable of audio inputs and outputs

130- [GPT-4o Mini Audio](/api/docs/models/gpt-4o-mini-audio-preview.md): Deprecated. Smaller model capable of audio inputs and outputs130- [GPT-4o Mini Audio](/api/docs/models/gpt-4o-mini-audio-preview.md): Deprecated. Smaller model capable of audio inputs and outputs

131- [GPT-4o Mini Realtime](/api/docs/models/gpt-4o-mini-realtime-preview.md): Deprecated. Smaller realtime model for text and audio inputs and outputs131- [GPT-4o Mini Realtime](/api/docs/models/gpt-4o-mini-realtime-preview.md): Deprecated. Smaller realtime model for text and audio inputs and outputs

190<dependency>190<dependency>

191 <groupId>com.openai</groupId>191 <groupId>com.openai</groupId>

192 <artifactId>openai-java</artifactId>192 <artifactId>openai-java</artifactId>

193 <version>4.80.0</version>193 <version>4.81.0</version>

194</dependency>194</dependency>

195```195```

196 196