Documentation 2026-11-11 23:57 UTC to 2026-11-12 22:57 UTC

65 65 

66Fine-tuned versions of these models follow the same shutdown schedule as their underlying base models.66Fine-tuned versions of these models follow the same shutdown schedule as their underlying base models.

67 67 

68### 2026-10-01: GPT-5.3-Codex, GPT-5.1, GPT-5.4-Nano68### 2026-10-01: GPT-5.3-Codex, GPT-5.1, GPT-5.4 nano

69 69 

70The 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.70The 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.

71 71 

425 425 

426### 2023-11-06: Chat model updates426### 2023-11-06: Chat model updates

427 427 

428On November 6th, 2023, we [announced](https://openai.com/blog/new-models-and-developer-products-announced-at-devday) the release of an updated GPT-3.5-Turbo model (which now comes by default with 16k context) along with deprecation of `gpt-3.5-turbo-0613` and ` gpt-3.5-turbo-16k-0613`. As of June 17, 2024, only existing users of these models will be able to continue using them.428On November 6th, 2023, we [announced](https://openai.com/blog/new-models-and-developer-products-announced-at-devday) the release of an updated GPT-3.5 Turbo model (which now comes by default with 16k context) along with deprecation of `gpt-3.5-turbo-0613` and ` gpt-3.5-turbo-16k-0613`. As of June 17, 2024, only existing users of these models will be able to continue using them.

429 429 

430| Shutdown date | Deprecated model | Deprecated model price | Recommended replacement |430| Shutdown date | Deprecated model | Deprecated model price | Recommended replacement |

431| ------------- | ------------------------ | -------------------------------------------------- | ----------------------- |431| ------------- | ------------------------ | -------------------------------------------------- | ----------------------- |

36 36 

37Agent workflows may do something you don't want due to hallucination, misunderstanding, ambiguous user input, etc. For example, an agent may offer a refund it's not supposed to or delete information it shouldn't. The best way to mitigate this risk is to strengthen your prompts with good documentation of your desired policies and clear examples. Anticipate unintended scenarios and provide examples so the agent knows what to do in these cases.37Agent workflows may do something you don't want due to hallucination, misunderstanding, ambiguous user input, etc. For example, an agent may offer a refund it's not supposed to or delete information it shouldn't. The best way to mitigate this risk is to strengthen your prompts with good documentation of your desired policies and clear examples. Anticipate unintended scenarios and provide examples so the agent knows what to do in these cases.

38 38 

39## Use GPT-5 or GPT-5-mini39## Use GPT-5 or GPT-5 mini

40 40 

41These models are more disciplined about following developer instructions and exhibit stronger robustness against jailbreaks and indirect prompt injections. Configure these models at the agent node level for a more resilient default posture, especially for higher-risk workflows.41These models are more disciplined about following developer instructions and exhibit stronger robustness against jailbreaks and indirect prompt injections. Configure these models at the agent node level for a more resilient default posture, especially for higher-risk workflows.

42 42 

4 4 

5Register an RSA-3072 asymmetric key pair from your cloud provider for use with OpenAI.5Register an RSA-3072 asymmetric key pair from your cloud provider for use with OpenAI.

6 6 

7Your private key stays in AWS KMS, Azure Key Vault, or Google Cloud KMS. OpenAI stores a copy of the corresponding public key at registration.7Your private key stays in AWS KMS, Azure Key Vault, Google Cloud KMS, or Oracle Cloud Infrastructure (OCI) Vault. OpenAI stores a copy of the corresponding public key at registration.

8 8 

9Registering a key doesn't configure product features or storage. This guide9Registering a key doesn't configure product features or storage. This guide

10 covers keys for [PSP10 covers keys for [PSP

264 264 

265 265 

266 266 

267 

268 

269<a id="oci-vault"></a>

270 

271 

272 

273### OCI Vault

274 

275 

276 

277#### 1. Create the vault and RSA key

278 

279Confirm OCI key registration and region availability with your OpenAI contact. Your tenancy and OpenAI's tenancy both need a subscription to the region.

280 

281In the OCI Console, open **Vault**. Create or select a vault in a commercial OCI region, such as `us-ashburn-1`. Wait for the vault to become **Active**.

282 

283Open **Master encryption keys** and choose **Create key**. Use RSA with a length of 3072 bits and software protection. Keep the key enabled. Use a separate AES-256 key if you also configure EKM.

284 

285![OCI key creation form with Software protection, the name asymmetric-key-oci, RSA, and a 3072-bit key length.](https://developers.openai.com/images/platform/guides/asymmetric-keys/oci-rsa3072-key-settings.webp)

286 

287#### 2. Tag the key for your organization

288 

289Add this free-form tag to the key:

290 

291| Tag field | Value |

292| ------------- | -------------------------------------------------------- |

293| Tag namespace | None (free-form tag) |

294| Tag key | `openai_organization_id` |

295| Tag value | Your OpenAI organization ID, including the `org-` prefix |

296 

297The tag must be on the key itself, even if you also tag the vault or compartment.

298 

299![OCI key Tags section with a free-form organization ID tag and the example value org-example.](https://developers.openai.com/images/platform/guides/asymmetric-keys/oci-key-organization-tag.webp)

300 

301#### 3. Grant public-key read access

302 

303In **Identity & Security > Policies**, select your tenancy's root compartment and create a policy. Turn on **Show manual editor** and enter these statements with your vault OCID and key OCID. Keep OpenAI's tenancy and group identifiers unchanged.

304 

305```text snippet=configuration reason="OCI IAM policy granting scoped vault and public-key reads"

306Define tenancy OpenAIEKM as ocid1.tenancy.oc1..aaaaaaaa4kzwe5jdr4gsxft7dfnwbnp3aozhxeskabsqo7czdkbp6fkh3uha

307Define group OpenAIEKMProduction as ocid1.group.oc1..aaaaaaaaerxukyeaxwqtbsxasnp54mem3sfgyokzdk7s27o7yvepluynxi5q

308Admit group OpenAIEKMProduction of tenancy OpenAIEKM to {VAULT_READ} in tenancy where target.vault.id = '<CUSTOMER_VAULT_OCID>'

309Admit group OpenAIEKMProduction of tenancy OpenAIEKM to {KEY_READ} in tenancy where target.key.id = '<CUSTOMER_KEY_OCID>'

310```

311 

312`VAULT_READ` lets OpenAI discover the vault endpoints. `KEY_READ` covers key metadata and the public key at the selected version. These grants don't include decryption, key export, or key management. Use this key-management identity even if you already configured a separate OCI Object Storage policy for PSP.

313 

314#### 4. Record the exact key version

315 

316Record the region identifier, vault OCID, and key OCID. In the key's versions list, copy the full OCID of the version you want to register. It starts with `ocid1.keyversion.`, not `ocid1.key.`.

317 

318Use the exact version OCID, not `latest` or a version number. The vault, key, and version must belong to the same commercial region, and the key must belong to the registered vault.

319 

320 

321 

322 

323 

267## Register your key324## Register your key

268 325 

269The examples use `curl` and a Bash-compatible shell. Load `OPENAI_ADMIN_KEY` securely, then set your organization ID:326The examples use `curl` and a Bash-compatible shell. Load `OPENAI_ADMIN_KEY` securely, then set your organization ID:

329}386}

330```387```

331 388 

389#### OCI Vault request

390 

391```json snippet=configuration reason="OCI external-key registration request body"

392{

393 "type": "oci",

394 "purpose": "psp_decryption",

395 "name": "asymmetric-key-oci",

396 "region": "us-ashburn-1",

397 "vault_ocid": "<CUSTOMER_VAULT_OCID>",

398 "key_ocid": "<CUSTOMER_KEY_OCID>",

399 "key_version_ocid": "<CUSTOMER_KEY_VERSION_OCID>"

400}

401```

402 

332### 1. Register and validate the key403### 1. Register and validate the key

333 404 

334```bash405```bash

401 472 

402## Replace a key473## Replace a key

403 474 

4041. Create a replacement AWS key or Azure/GCP version and grant read access.4751. Create a replacement AWS key or Azure/GCP/OCI key version and grant read access.

4052. Register the replacement.4762. Register the replacement.

4063. [Select the new `extkey` ID on the project](https://developers.openai.com/api/docs/guides/private-safety-processing#select-a-key-for-psp-decryption) and verify the selection.4773. [Select the new `extkey` ID on the project](https://developers.openai.com/api/docs/guides/private-safety-processing#select-a-key-for-psp-decryption) and verify the selection.

407 478 

422## Troubleshooting493## Troubleshooting

423 494 

424| Error | What to check |495| Error | What to check |

425| -------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------- |496| -------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------ |

426| 401 or 403 | Use an organization Admin API key and confirm access to external-key registration. |497| 401 or 403 | Use an organization Admin API key and confirm access to external-key registration. |

427| 400 `external_key_provider_error` | Check cloud trust, read permissions, network access, and the key's enabled state and algorithm. |498| 400 `external_key_provider_error` | Check cloud trust, read permissions, network access, and the key's enabled state and algorithm. |

428| 400 request-validation errors | Check the purpose, concrete AWS key ARN, and exact Azure/GCP version. |499| 400 request-validation errors | Check the purpose, concrete AWS key ARN, and exact Azure/GCP/OCI version. |

500| OCI key validation fails | Check the key's `openai_organization_id` tag, RSA-3072 size, enabled state, vault ownership, and scoped vault/key read grants. |

429| 404 | Check the registration ID and organization. Deleted registrations and registrations from another organization can't be used. |501| 404 | Check the registration ID and organization. Deleted registrations and registrations from another organization can't be used. |

430| `external_key_used_by_active_projects` | Clear or replace all active project selections. |502| `external_key_used_by_active_projects` | Clear or replace all active project selections. |

431| Key no longer matches | Register the replacement and select its new ID. |503| Key no longer matches | Register the replacement and select its new ID. |

637 637 

638Most models support the Batch API. Check the [model reference](https://developers.openai.com/api/docs/models) for your model. GPT-6 Sol and Luna support EU data residency with Standard, Flex, and Batch processing. See [data residency eligibility](https://developers.openai.com/api/docs/guides/your-data#which-models-and-features-are-eligible-for-data-residency).638Most models support the Batch API. Check the [model reference](https://developers.openai.com/api/docs/models) for your model. GPT-6 Sol and Luna support EU data residency with Standard, Flex, and Batch processing. See [data residency eligibility](https://developers.openai.com/api/docs/guides/your-data#which-models-and-features-are-eligible-for-data-residency).

639 639 

640GPT Image 2.5 supports batch image generation and editing with `gpt-image-2.5-flare` and `gpt-image-2.5-sunburst`, including their `2026-09-08` snapshots. Use `/v1/images/generations` or `/v1/images/edits` and see [image generation pricing](https://developers.openai.com/api/docs/pricing?multimodal-image-pricing=batch#image-generation) for Batch rates.640GPT-Image-2.5 supports batch image generation and editing with `gpt-image-2.5-flare` and `gpt-image-2.5-sunburst`, including their `2026-09-08` snapshots. Use `/v1/images/generations` or `/v1/images/edits` and see [image generation pricing](https://developers.openai.com/api/docs/pricing?multimodal-image-pricing=batch#image-generation) for Batch rates.

641 641 

642## Rate limits642## Rate limits

643 643 

54GPT-5.5-Cyber (existing access only)54GPT-5.5-Cyber (existing access only)

55 55 

56 56

57GPT-5.6-Cyber57GPT-5.6 Cyber

58 58 

59 59

60 60 

88 </td>88 </td>

89 </tr>89 </tr>

90 <tr>90 <tr>

91 <td>GPT-6-Cyber</td>91 <td>GPT-6 Cyber</td>

92 <td>Red + additional model approval</td>92 <td>Red + additional model approval</td>

93 <td>93 <td>

94 `daybreak_red`94 `daybreak_red`

171 171 

172When no program is specified and the request uses standard safeguards, `access_programs` is `null`. For a `-latest` alias, inspect `model` to see which model served the request. Alias resolution can change and depends on your approved access.172When no program is specified and the request uses standard safeguards, `access_programs` is `null`. For a `-latest` alias, inspect `model` to see which model served the request. Alias resolution can change and depends on your approved access.

173 173 

174## Set up GPT-6-Cyber174## Set up GPT-6 Cyber

175 175 

176Confirm with your account team that your organization has Daybreak Red access and approval for [GPT-6-Cyber](https://developers.openai.com/api/docs/models/gpt-6-cyber).176Confirm with your account team that your organization has Daybreak Red access and approval for [GPT-6 Cyber](https://developers.openai.com/api/docs/models/gpt-6-cyber).

177 177 

178**Project access.** Ask an organization owner to [enable Daybreak Red](https://help.openai.com/en/articles/20001531-openai-daybreak-set-up-access-for-your-team) for the project that will send requests. With project-level controls, use a non-default project and a key from that project.178**Project access.** Ask an organization owner to [enable Daybreak Red](https://help.openai.com/en/articles/20001531-openai-daybreak-set-up-access-for-your-team) for the project that will send requests. With project-level controls, use a non-default project and a key from that project.

179 179 

180**IP allowlisting.** To use GPT-6-Cyber through the API, [configure an IP allowlist](https://developers.openai.com/api/docs/guides/ip-allowlist) for the public IPs your application sends requests from. If you have received approval to embed the model in a product, end users without direct model access don’t need to allowlist their own IPs.180**IP allowlisting.** To use GPT-6 Cyber through the API, [configure an IP allowlist](https://developers.openai.com/api/docs/guides/ip-allowlist) for the public IPs your application sends requests from. If you have received approval to embed the model in a product, end users without direct model access don’t need to allowlist their own IPs.

181 181 

182**Zero Data Retention.** If the project uses ZDR, [configure Private Safety Processing](https://developers.openai.com/api/docs/guides/private-safety-processing) (PSP). Check that storage shows “Validated” and that the project’s retention policy is “Zero Data Retention with Private Safety Processing.” PSP applies to all API traffic in that project.182**Zero Data Retention.** If the project uses ZDR, [configure Private Safety Processing](https://developers.openai.com/api/docs/guides/private-safety-processing) (PSP). Check that storage shows “Validated” and that the project’s retention policy is “Zero Data Retention with Private Safety Processing.” PSP applies to all API traffic in that project.

183 183 

184### Send a GPT-6-Cyber request184### Send a GPT-6 Cyber request

185 185 

186Set `OPENAI_API_KEY` to a key from the approved project. Replace the sample safety identifier with a stable, pseudonymous identifier for the user making the request.186Set `OPENAI_API_KEY` to a key from the approved project. Replace the sample safety identifier with a stable, pseudonymous identifier for the user making the request.

187 187 

3800### Historical output costs3800### Historical output costs

3801 3801 

3802`gpt-image-2` supports thousands of valid resolutions; the table below lists the3802`gpt-image-2` supports thousands of valid resolutions; the table below lists the

3803same sizes used for previous GPT Image models for comparison. For GPT-Image-1.5,3803same sizes used for previous GPT Image models for comparison. For GPT Image 1.5,

3804GPT-Image-1, and GPT-Image-1 Mini, the legacy per-image output pricing table is3804GPT Image 1, and GPT Image 1 mini, the legacy per-image output pricing table is

3805also listed below. You should still account for text and image input tokens when3805also listed below. You should still account for text and image input tokens when

3806estimating the total cost of a request.3806estimating the total cost of a request.

3807 3807 

3856 3856 

3857 <tr>3857 <tr>

3858 <td rowSpan="3" style={{ padding: "8px", width: "28%" }}>3858 <td rowSpan="3" style={{ padding: "8px", width: "28%" }}>

3859 GPT-Image-1.53859 GPT Image 1.5

3860 </td>3860 </td>

3861 <td style={{ padding: "8px" }}>Low</td>3861 <td style={{ padding: "8px" }}>Low</td>

3862 <td style={{ padding: "8px" }}>$0.009</td>3862 <td style={{ padding: "8px" }}>$0.009</td>

3878 3878 

3879 <tr>3879 <tr>

3880 <td rowSpan="3" style={{ padding: "8px", width: "28%" }}>3880 <td rowSpan="3" style={{ padding: "8px", width: "28%" }}>

3881 GPT-Image-13881 GPT Image 1

3882 </td>3882 </td>

3883 <td style={{ padding: "8px" }}>Low</td>3883 <td style={{ padding: "8px" }}>Low</td>

3884 <td style={{ padding: "8px" }}>$0.011</td>3884 <td style={{ padding: "8px" }}>$0.011</td>

3900 3900 

3901 <tr>3901 <tr>

3902 <td rowSpan="3" style={{ padding: "8px", width: "28%" }}>3902 <td rowSpan="3" style={{ padding: "8px", width: "28%" }}>

3903 GPT-Image-1 Mini3903 GPT Image 1 mini

3904 </td>3904 </td>

3905 <td style={{ padding: "8px" }}>Low</td>3905 <td style={{ padding: "8px" }}>Low</td>

3906 <td style={{ padding: "8px" }}>$0.005</td>3906 <td style={{ padding: "8px" }}>$0.005</td>

715. **Tune one setting at a time.** Change either quality or complexity. Repeat each request and compare how often the output meets your criteria and how long it takes.715. **Tune one setting at a time.** Change either quality or complexity. Repeat each request and compare how often the output meets your criteria and how long it takes.

726. **Roll out by workflow.** Move a small share of traffic after the new model meets your criteria. Track response time, failures, retries, and cost per accepted image before you expand.726. **Roll out by workflow.** Move a small share of traffic after the new model meets your criteria. Track response time, failures, retries, and cost per accepted image before you expand.

73 73 

74When migrating from GPT-Image-1 or GPT-Image-1.5, use its reference tab to check parameter differences and shutdown dates. If part of an image must remain pixel-identical, composite the approved edit into the original.74When migrating from GPT Image 1 or GPT Image 1.5, use its reference tab to check parameter differences and shutdown dates. If part of an image must remain pixel-identical, composite the approved edit into the original.

75 75 

76## Prompting fundamentals76## Prompting fundamentals

77 77 

15335. **Tune one setting at a time.** Compare quality levels before rewriting the prompt. Measure typical and slow responses, failures, retries, and cost per accepted image. Confirm current pricing rather than assuming the faster model costs less.15335. **Tune one setting at a time.** Compare quality levels before rewriting the prompt. Measure typical and slow responses, failures, retries, and cost per accepted image. Confirm current pricing rather than assuming the faster model costs less.

15346. **Roll out by workflow.** Once the released model passes your acceptance criteria, move a small share of traffic, monitor the same measures, and expand gradually. Keep the previous model available for rollback while it remains supported.15346. **Roll out by workflow.** Once the released model passes your acceptance criteria, move a small share of traffic, monitor the same measures, and expand gradually. Keep the previous model available for rollback while it remains supported.

1535 1535 

1536When migrating from GPT-Image-1 or GPT-Image-1.5, use the reference tabs to check parameter differences and shutdown dates. Test the candidate model's supported request settings rather than copying older settings unchanged. For GPT-Image-2, keep your existing resolution and transparency requirements in the comparison.1536When migrating from GPT Image 1 or GPT Image 1.5, use the reference tabs to check parameter differences and shutdown dates. Test the candidate model's supported request settings rather than copying older settings unchanged. For GPT-Image-2, keep your existing resolution and transparency requirements in the comparison.

1537 1537 

1538Repeated edits can still change details you intended to preserve. Restate those constraints and inspect each result. If a region must remain pixel-identical, composite the approved edit into the original image instead of relying on prompting alone.1538Repeated edits can still change details you intended to preserve. Restate those constraints and inspect each result. If a region must remain pixel-identical, composite the approved edit into the original image instead of relying on prompting alone.

1539 1539 

2937 id="gpt-image-1.5-guide"2937 id="gpt-image-1.5-guide"

2938 className="m-0 text-3xl font-semibold text-default"2938 className="m-0 text-3xl font-semibold text-default"

2939 >2939 >

2940 {"GPT-Image-1.5 reference"}2940 {"GPT Image 1.5 reference"}

2941 </h2>2941 </h2>

2942 2942

2943 2943 

2944 Overview and request settings for existing GPT-Image-1.5 workflows.2944 Overview and request settings for existing GPT Image 1.5 workflows.

2945 2945

2946 2946 

2947 </header>2947 </header>

2954 notice](https://developers.openai.com/api/docs/deprecations#2026-06-02-gpt-image-model-deprecations) and2954 notice](https://developers.openai.com/api/docs/deprecations#2026-06-02-gpt-image-model-deprecations) and

2955 validate existing workflows with `gpt-image-2` before migrating.2955 validate existing workflows with `gpt-image-2` before migrating.

2956 2956 

2957GPT-Image-1.5 supports image generation and editing, including text rendering, photorealistic images, and reference-based edits. Use this reference to maintain existing integrations. The [prompting guide](https://developers.openai.com/api/docs/guides/image-prompting?model=gpt-image-2.5) covers shared techniques for composition, text, reference images, and preserving details during edits. Test those techniques with your model and inputs; outputs can differ across models.2957GPT Image 1.5 supports image generation and editing, including text rendering, photorealistic images, and reference-based edits. Use this reference to maintain existing integrations. The [prompting guide](https://developers.openai.com/api/docs/guides/image-prompting?model=gpt-image-2.5) covers shared techniques for composition, text, reference images, and preserving details during edits. Test those techniques with your model and inputs; outputs can differ across models.

2958 2958 

2959## Model parameters2959## Model parameters

2960 2960 

2961Use `client.images.generate` for generation and `client.images.edit` for edits. See the [image generation guide](https://developers.openai.com/api/docs/guides/image-generation) for API setup and request examples.2961Use `client.images.generate` for generation and `client.images.edit` for edits. See the [image generation guide](https://developers.openai.com/api/docs/guides/image-generation) for API setup and request examples.

2962 2962 

2963| Parameter | GPT-Image-1.5 |2963| Parameter | GPT Image 1.5 |

2964| -------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |2964| -------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |

2965| `model` | `gpt-image-1.5` |2965| `model` | `gpt-image-1.5` |

2966| `quality` | `low`, `medium`, `high`, or `auto` |2966| `quality` | `low`, `medium`, `high`, or `auto` |

2980 id="gpt-image-1-guide"2980 id="gpt-image-1-guide"

2981 className="m-0 text-3xl font-semibold text-default"2981 className="m-0 text-3xl font-semibold text-default"

2982 >2982 >

2983 {"GPT-Image-1 reference"}2983 {"GPT Image 1 reference"}

2984 </h2>2984 </h2>

2985 2985

2986 2986 

2987 Legacy request settings for migrating GPT-Image-1 workflows.2987 Legacy request settings for migrating GPT Image 1 workflows.

2988 2988

2989 2989 

2990 </header>2990 </header>

2998 notice](https://developers.openai.com/api/docs/deprecations#2026-04-22-legacy-gpt-model-snapshots) for2998 notice](https://developers.openai.com/api/docs/deprecations#2026-04-22-legacy-gpt-model-snapshots) for

2999 migration details.2999 migration details.

3000 3000 

3001GPT-Image-1 supported image generation and editing with reference images and masks. Use this reference when migrating existing integrations. For shared techniques such as describing a scene, preserving details, and refining an edit, see the [prompting guide](https://developers.openai.com/api/docs/guides/image-prompting?model=gpt-image-2.5).3001GPT Image 1 supported image generation and editing with reference images and masks. Use this reference when migrating existing integrations. For shared techniques such as describing a scene, preserving details, and refining an edit, see the [prompting guide](https://developers.openai.com/api/docs/guides/image-prompting?model=gpt-image-2.5).

3002 3002 

3003## Model parameters3003## Model parameters

3004 3004 

3005These settings describe legacy GPT-Image-1 requests. See the [image generation guide](https://developers.openai.com/api/docs/guides/image-generation) for supported models, API setup, and current request examples.3005These settings describe legacy GPT Image 1 requests. See the [image generation guide](https://developers.openai.com/api/docs/guides/image-generation) for supported models, API setup, and current request examples.

3006 3006 

3007| Parameter | GPT-Image-1 |3007| Parameter | GPT Image 1 |

3008| -------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |3008| -------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |

3009| `model` | `gpt-image-1` |3009| `model` | `gpt-image-1` |

3010| `quality` | `low`, `medium`, `high`, or `auto` |3010| `quality` | `low`, `medium`, `high`, or `auto` |

676 676 

677When using Predicted Outputs, you should consider the following factors and limitations.677When using Predicted Outputs, you should consider the following factors and limitations.

678 678 

679- Predicted Outputs are only supported with the GPT-4o, GPT-4o-mini, GPT-4.1, GPT-4.1-mini, and GPT-4.1-nano series of models.679- Predicted Outputs are only supported with the GPT-4o, GPT-4o mini, GPT-4.1, GPT-4.1 mini, and GPT-4.1 nano series of models.

680- When providing a prediction, any tokens provided that are not part of the final completion are still charged at completion token rates. See the [`rejected_prediction_tokens` property of the `usage` object](https://developers.openai.com/api/reference/resources/chat#chat/object-usage) to see how many tokens are not used in the final response.680- When providing a prediction, any tokens provided that are not part of the final completion are still charged at completion token rates. See the [`rejected_prediction_tokens` property of the `usage` object](https://developers.openai.com/api/reference/resources/chat#chat/object-usage) to see how many tokens are not used in the final response.

681- The following [API parameters](https://developers.openai.com/api/reference/resources/chat) are not supported when using Predicted Outputs:681- The following [API parameters](https://developers.openai.com/api/reference/resources/chat) are not supported when using Predicted Outputs:

682 - `n`: values higher than 1 are not supported682 - `n`: values higher than 1 are not supported

115 115 

116PSP decryption lets you decrypt customer content in PSP records stored in your connected cloud storage using an asymmetric key that you control. OpenAI uses the public key, while the private key stays in your cloud key-management service. This is separate from EKM and doesn't grant OpenAI personnel access to your content.116PSP decryption lets you decrypt customer content in PSP records stored in your connected cloud storage using an asymmetric key that you control. OpenAI uses the public key, while the private key stays in your cloud key-management service. This is separate from EKM and doesn't grant OpenAI personnel access to your content.

117 117 

118See [Set up asymmetric keys](https://developers.openai.com/api/docs/guides/asymmetric-keys) for AWS KMS, Azure Key Vault, and Google Cloud KMS setup and key registration. Confirm PSP decryption availability and activation with your OpenAI contact. Registering a key doesn't enable PSP or configure storage, and only records written with PSP decryption enabled for your key can be decrypted with that key. Existing records aren't converted.118See [Set up asymmetric keys](https://developers.openai.com/api/docs/guides/asymmetric-keys) for AWS KMS, Azure Key Vault, Google Cloud KMS, and OCI Vault setup and key registration. Confirm PSP decryption availability and activation with your OpenAI contact. Registering a key doesn't enable PSP or configure storage, and only records written with PSP decryption enabled for your key can be decrypted with that key. Existing records aren't converted.

119 119 

120For the decryption steps, record format, and key derivation, see [Decrypt PSP records](https://developers.openai.com/api/docs/guides/psp-decryption).120For the decryption steps, record format, and key derivation, see [Decrypt PSP records](https://developers.openai.com/api/docs/guides/psp-decryption).

121 121 

28 28 

29Read the record from your cloud storage. If it has an EKM storage envelope, decrypt that layer with its original EKM configuration first.29Read the record from your cloud storage. If it has an EKM storage envelope, decrypt that layer with its original EKM configuration first.

30 30 

31For OCI EKM, your recovery application also needs `KEY_DECRYPT` on the original AES key. Preserve the envelope's key version and scope-associated data when decrypting that layer.

32 

31Parse the resulting JSON bundle containing `protected_record` and `customer_access`, as shown in [Bundle format](#bundle-format). If `customer_access` is `null`, PSP decryption is unavailable for that record.33Parse the resulting JSON bundle containing `protected_record` and `customer_access`, as shown in [Bundle format](#bundle-format). If `customer_access` is `null`, PSP decryption is unavailable for that record.

32 34 

33### 2. Select the original key35### 2. Select the original key

40 42 

41Send the decoded `customer_access.recovery_secret` to your cloud key-management service for RSA-OAEP-SHA256 decryption.43Send the decoded `customer_access.recovery_secret` to your cloud key-management service for RSA-OAEP-SHA256 decryption.

42 44 

45For OCI Vault, use the vault's cryptographic endpoint and the [Decrypt operation](https://docs.oracle.com/en-us/iaas/api/#/en/key/release/DecryptedData/Decrypt) with these fields:

46 

47| Field | Value |

48| --------------------- | ---------------------------------------------------- |

49| `keyId` | The original registration's `key_ocid` |

50| `keyVersionId` | The original registration's exact `key_version_ocid` |

51| `encryptionAlgorithm` | `RSA_OAEP_SHA_256` |

52| `ciphertext` | The recovery-secret bytes encoded as standard Base64 |

53 

54The bundle uses base64url encoding. Decode `recovery_secret` before encoding those bytes as standard Base64 for OCI. Decode the response's Base64 `plaintext` to get the recovery capsule for step 4. It isn't the recovered record yet.

55 

56Your recovery application's OCI identity needs `KEY_DECRYPT` on the original RSA key. This is separate from OpenAI's public-key read access. Keep the original version available after rotation, and omit `associatedData` for this RSA operation.

57 

43### 4. Decrypt and verify the content58### 4. Decrypt and verify the content

44 59 

45Use the [Python example](#python-example) to check the capsule's binding to the record and decrypt the content locally.60Use the [Python example](#python-example) to check the capsule's binding to the record and decrypt the content locally.

38Application-level tool review and Codex product-side sandboxing are separate38Application-level tool review and Codex product-side sandboxing are separate

39from the API cybersecurity safeguards described on this page.39from the API cybersecurity safeguards described on this page.

40 40 

41For GPT-6-Cyber, [configure your project and IP allowlist](https://developers.openai.com/api/docs/guides/daybreak#set-up-gpt-6-cyber) before sending requests.41For GPT-6 Cyber, [configure your project and IP allowlist](https://developers.openai.com/api/docs/guides/daybreak#set-up-gpt-6-cyber) before sending requests.

42 42 

43## Safeguard actions for non-ZDR Organizations43## Safeguard actions for non-ZDR Organizations

44 44 

3877 OpenAI::Models::Responses::ResponseTextDeltaEvent3877 OpenAI::Models::Responses::ResponseTextDeltaEvent

3878 print(event.delta)3878 print(event.delta)

3879 when OpenAI::Models::Responses::ResponseErrorEvent3879 when OpenAI::Models::Responses::ResponseErrorEvent

3880 warn(event.message)3880 raise event.message

3881 when OpenAI::Models::Responses::ResponseCompletedEvent3881 when OpenAI::Models::Responses::ResponseFailedEvent,

3882 puts("\nCompleted")3882 OpenAI::Models::Responses::ResponseIncompleteEvent

3883 response = event.response

3884 detail = response.error&.message || response.incomplete_details&.reason

3885 message = "Response #{response.status}"

3886 message += ": #{detail}" unless detail.to_s.empty?

3887 raise message

3883 end3888 end

3884end3889end

3890 

3891# Text deltas and response.output_text.done do not guarantee completion.

3892response = stream.get_final_response

3893refused = response.output.grep(OpenAI::Models::Responses::ResponseOutputMessage).any? do |message|

3894 message.content.any? { |part| part.is_a?(OpenAI::Models::Responses::ResponseOutputRefusal) }

3895end

3896puts(refused ? "\nRefused" : "\nCompleted")

3885```3897```

3886 3898 

3887 3899 

175<dependency>175<dependency>

176 <groupId>com.openai</groupId>176 <groupId>com.openai</groupId>

177 <artifactId>openai-java</artifactId>177 <artifactId>openai-java</artifactId>

178 <version>4.103.0</version>178 <version>4.104.0</version>

179</dependency>179</dependency>

180```180```

181 181 

25- [GPT-5.2](/api/docs/models/gpt-5.2.md): Previous flagship model for professional work with configurable reasoning effort25- [GPT-5.2](/api/docs/models/gpt-5.2.md): Previous flagship model for professional work with configurable reasoning effort

26- [GPT-5.2 Pro](/api/docs/models/gpt-5.2-pro.md): Previous pro model for professional work that produces smarter and more precise responses.26- [GPT-5.2 Pro](/api/docs/models/gpt-5.2-pro.md): Previous pro model for professional work that produces smarter and more precise responses.

27- [GPT-5.4](/api/docs/models/gpt-5.4.md): A more affordable model for coding and professional work.27- [GPT-5.4](/api/docs/models/gpt-5.4.md): A more affordable model for coding and professional work.

28- [GPT-5.4 Mini](/api/docs/models/gpt-5.4-mini.md): Our strongest mini model yet for coding, computer use, and subagents28- [GPT-5.4 mini](/api/docs/models/gpt-5.4-mini.md): Our strongest mini model yet for coding, computer use, and subagents

29- [GPT-5.4 Pro](/api/docs/models/gpt-5.4-pro.md): Version of GPT-5.4 that produces smarter and more precise responses.29- [GPT-5.4 Pro](/api/docs/models/gpt-5.4-pro.md): Version of GPT-5.4 that produces smarter and more precise responses.

30- [GPT-5.5](/api/docs/models/gpt-5.5.md): A new class of intelligence for coding and professional work.30- [GPT-5.5](/api/docs/models/gpt-5.5.md): A new class of intelligence for coding and professional work.

31- [GPT-5.5 Pro](/api/docs/models/gpt-5.5-pro.md): Version of GPT-5.5 that produces smarter and more precise responses.31- [GPT-5.5 Pro](/api/docs/models/gpt-5.5-pro.md): Version of GPT-5.5 that produces smarter and more precise responses.

34- [GPT-5.6 Sol](/api/docs/models/gpt-5.6-sol.md): GPT-5.6 flagship model for complex professional work34- [GPT-5.6 Sol](/api/docs/models/gpt-5.6-sol.md): GPT-5.6 flagship model for complex professional work

35- [GPT-5.6 Terra](/api/docs/models/gpt-5.6-terra.md): GPT-5.6 model that balances intelligence and cost35- [GPT-5.6 Terra](/api/docs/models/gpt-5.6-terra.md): GPT-5.6 model that balances intelligence and cost

36- [GPT-6 Astra](/api/docs/models/gpt-6-astra.md): Our most capable model for the most demanding work.36- [GPT-6 Astra](/api/docs/models/gpt-6-astra.md): Our most capable model for the most demanding work.

37- [GPT-6 Cyber](/api/docs/models/gpt-6-cyber.md): Investigate a vulnerability, reproduce it in an authorized test environment, or verify a fix.

37- [GPT-6 Luna](/api/docs/models/gpt-6-luna.md): Our most efficient model for focused, high-volume tasks.38- [GPT-6 Luna](/api/docs/models/gpt-6-luna.md): Our most efficient model for focused, high-volume tasks.

38- [GPT-6 Sol](/api/docs/models/gpt-6-sol.md): Built to power complex coding and agentic workflows.39- [GPT-6 Sol](/api/docs/models/gpt-6-sol.md): Built to power complex coding and agentic workflows.

39- [GPT-6-Cyber](/api/docs/models/gpt-6-cyber.md): Investigate a vulnerability, reproduce it in an authorized test environment, or verify a fix.

40- [GPT-6.1 Sol](/api/docs/models/gpt-6.1-sol.md): Near-Astra performance for complex work at a lower cost.40- [GPT-6.1 Sol](/api/docs/models/gpt-6.1-sol.md): Near-Astra performance for complex work at a lower cost.

41- [GPT-6.1 Terra](/api/docs/models/gpt-6.1-terra.md): A fast, efficient model for visual reasoning, precise computer use, and clear, natural writing.41- [GPT-6.1 Terra](/api/docs/models/gpt-6.1-terra.md): A fast, efficient model for visual reasoning, precise computer use, and clear, natural writing.

42- [GPT-Audio-1.5](/api/docs/models/gpt-audio-1.5.md): The best voice model for audio in, audio out with Chat Completions.42- [GPT-Audio-1.5](/api/docs/models/gpt-audio-1.5.md): The best voice model for audio in, audio out with Chat Completions.

51- [GPT-Realtime-1.5](/api/docs/models/gpt-realtime-1.5.md): The best voice model for audio in, audio out51- [GPT-Realtime-1.5](/api/docs/models/gpt-realtime-1.5.md): The best voice model for audio in, audio out

52- [GPT-Realtime-2](/api/docs/models/gpt-realtime-2.md): Reasoning model with tool use52- [GPT-Realtime-2](/api/docs/models/gpt-realtime-2.md): Reasoning model with tool use

53- [GPT-Realtime-2.1](/api/docs/models/gpt-realtime-2.1.md): Reasoning model with tool use53- [GPT-Realtime-2.1](/api/docs/models/gpt-realtime-2.1.md): Reasoning model with tool use

54- [GPT-Realtime-2.1 Mini](/api/docs/models/gpt-realtime-2.1-mini.md): Reasoning model with tool use54- [GPT-Realtime-2.1 mini](/api/docs/models/gpt-realtime-2.1-mini.md): Reasoning model with tool use

55- [GPT-Realtime-Translate](/api/docs/models/gpt-realtime-translate.md): Streaming speech-to-speech translation model55- [GPT-Realtime-Translate](/api/docs/models/gpt-realtime-translate.md): Streaming speech-to-speech translation model

56- [GPT-Realtime-Whisper](/api/docs/models/gpt-realtime-whisper.md): Streaming speech-to-text model for realtime transcription56- [GPT-Realtime-Whisper](/api/docs/models/gpt-realtime-whisper.md): Streaming speech-to-text model for realtime transcription

57- [GPT-Transcribe](/api/docs/models/gpt-transcribe.md): High-accuracy speech-to-text model for file and Realtime input transcription57- [GPT-Transcribe](/api/docs/models/gpt-transcribe.md): High-accuracy speech-to-text model for file and Realtime input transcription

30 30 

31- [GPT-Live-1](/api/docs/models/gpt-live-1.md): Our premier model for natural, expressive voice conversations with smooth interruption handling.31- [GPT-Live-1](/api/docs/models/gpt-live-1.md): Our premier model for natural, expressive voice conversations with smooth interruption handling.

32- [GPT-Realtime-2.1](/api/docs/models/gpt-realtime-2.1.md): Reasoning model with tool use32- [GPT-Realtime-2.1](/api/docs/models/gpt-realtime-2.1.md): Reasoning model with tool use

33- [GPT-Realtime-2.1 Mini](/api/docs/models/gpt-realtime-2.1-mini.md): Reasoning model with tool use33- [GPT-Realtime-2.1 mini](/api/docs/models/gpt-realtime-2.1-mini.md): Reasoning model with tool use

34- [GPT-Realtime-2](/api/docs/models/gpt-realtime-2.md): Reasoning model with tool use34- [GPT-Realtime-2](/api/docs/models/gpt-realtime-2.md): Reasoning model with tool use

35- [GPT-Realtime-Translate](/api/docs/models/gpt-realtime-translate.md): Streaming speech-to-speech translation model35- [GPT-Realtime-Translate](/api/docs/models/gpt-realtime-translate.md): Streaming speech-to-speech translation model

36- [GPT-Live-Transcribe](/api/docs/models/gpt-live-transcribe.md): Low-latency speech-to-text model for realtime transcription36- [GPT-Live-Transcribe](/api/docs/models/gpt-live-transcribe.md): Low-latency speech-to-text model for realtime transcription

43 43 

44Advanced cyber models for defenders44Advanced cyber models for defenders

45 45 

46- [GPT-6-Cyber](/api/docs/models/gpt-6-cyber.md): Investigate a vulnerability, reproduce it in an authorized test environment, or verify a fix.46- [GPT-6 Cyber](/api/docs/models/gpt-6-cyber.md): Investigate a vulnerability, reproduce it in an authorized test environment, or verify a fix.

47- [GPT-5.6 Cyber](/api/docs/models/gpt-5.6-cyber.md): Cybersecurity model for authorized vulnerability research and security testing.47- [GPT-5.6 Cyber](/api/docs/models/gpt-5.6-cyber.md): Cybersecurity model for authorized vulnerability research and security testing.

48 48 

49## Life sciences49## Life sciences

79- [GPT-5.5 Pro](/api/docs/models/gpt-5.5-pro.md): Version of GPT-5.5 that produces smarter and more precise responses.79- [GPT-5.5 Pro](/api/docs/models/gpt-5.5-pro.md): Version of GPT-5.5 that produces smarter and more precise responses.

80- [GPT-5.4](/api/docs/models/gpt-5.4.md): A more affordable model for coding and professional work.80- [GPT-5.4](/api/docs/models/gpt-5.4.md): A more affordable model for coding and professional work.

81- [GPT-5.4 Pro](/api/docs/models/gpt-5.4-pro.md): Version of GPT-5.4 that produces smarter and more precise responses.81- [GPT-5.4 Pro](/api/docs/models/gpt-5.4-pro.md): Version of GPT-5.4 that produces smarter and more precise responses.

82- [GPT-5.4 Mini](/api/docs/models/gpt-5.4-mini.md): Our strongest mini model yet for coding, computer use, and subagents82- [GPT-5.4 mini](/api/docs/models/gpt-5.4-mini.md): Our strongest mini model yet for coding, computer use, and subagents

83- [GPT-5.2](/api/docs/models/gpt-5.2.md): Previous flagship model for professional work with configurable reasoning effort83- [GPT-5.2](/api/docs/models/gpt-5.2.md): Previous flagship model for professional work with configurable reasoning effort

84- [GPT-5.2 Pro](/api/docs/models/gpt-5.2-pro.md): Previous pro model for professional work that produces smarter and more precise responses.84- [GPT-5.2 Pro](/api/docs/models/gpt-5.2-pro.md): Previous pro model for professional work that produces smarter and more precise responses.

85- [omni-moderation](/api/docs/models/omni-moderation-latest.md): Identify potentially harmful content in text and images85- [omni-moderation](/api/docs/models/omni-moderation-latest.md): Identify potentially harmful content in text and images

95Includes models that have already shut down.95Includes models that have already shut down.

96 96 

97- [GPT-Image-2](/api/docs/models/gpt-image-2.md): Deprecated. State-of-the-art image generation model97- [GPT-Image-2](/api/docs/models/gpt-image-2.md): Deprecated. State-of-the-art image generation model

98- [GPT-Image-1.5](/api/docs/models/gpt-image-1.5.md): Deprecated. Our previous image generation model98- [GPT Image 1.5](/api/docs/models/gpt-image-1.5.md): Deprecated. Our previous image generation model

99- [chatgpt-image-latest](/api/docs/models/chatgpt-image-latest.md): Deprecated. Previous image model used in ChatGPT.99- [chatgpt-image-latest](/api/docs/models/chatgpt-image-latest.md): Deprecated. Previous image model used in ChatGPT.

100- [GPT-Image-1](/api/docs/models/gpt-image-1.md): Shut down. Retired image generation model100- [GPT Image 1](/api/docs/models/gpt-image-1.md): Shut down. Retired image generation model

101- [GPT-Image-1 Mini](/api/docs/models/gpt-image-1-mini.md): Deprecated. A cost-efficient version of GPT Image 1101- [GPT Image 1 mini](/api/docs/models/gpt-image-1-mini.md): Deprecated. A cost-efficient version of GPT Image 1

102- [GPT-Realtime](/api/docs/models/gpt-realtime.md): Deprecated. Model capable of realtime text and audio inputs and outputs102- [GPT-Realtime](/api/docs/models/gpt-realtime.md): Deprecated. Model capable of realtime text and audio inputs and outputs

103- [GPT-Audio](/api/docs/models/gpt-audio.md): Deprecated. For audio inputs and outputs with Chat Completions API103- [GPT-Audio](/api/docs/models/gpt-audio.md): Deprecated. For audio inputs and outputs with Chat Completions API

104- [GPT-4o Transcribe](/api/docs/models/gpt-4o-transcribe.md): Deprecated. Speech-to-text model powered by GPT-4o104- [GPT-4o Transcribe](/api/docs/models/gpt-4o-transcribe.md): Deprecated. Speech-to-text model powered by GPT-4o

105- [GPT-4o Mini Transcribe](/api/docs/models/gpt-4o-mini-transcribe.md): Deprecated. Speech-to-text model powered by GPT-4o Mini105- [GPT-4o Mini Transcribe](/api/docs/models/gpt-4o-mini-transcribe.md): Deprecated. Speech-to-text model powered by GPT-4o mini

106- [GPT-4o Transcribe Diarize](/api/docs/models/gpt-4o-transcribe-diarize.md): Deprecated. Transcription model that identifies who's speaking when106- [GPT-4o Transcribe Diarize](/api/docs/models/gpt-4o-transcribe-diarize.md): Deprecated. Transcription model that identifies who's speaking when

107- [TTS-1](/api/docs/models/tts-1.md): Deprecated. Text-to-speech model optimized for speed107- [TTS-1](/api/docs/models/tts-1.md): Deprecated. Text-to-speech model optimized for speed

108- [TTS-1 HD](/api/docs/models/tts-1-hd.md): Deprecated. Text-to-speech model optimized for quality108- [TTS-1 HD](/api/docs/models/tts-1-hd.md): Deprecated. Text-to-speech model optimized for quality

109- [Whisper](/api/docs/models/whisper-1.md): Deprecated. General-purpose speech recognition model109- [Whisper](/api/docs/models/whisper-1.md): Deprecated. General-purpose speech recognition model

110- [GPT-Realtime Mini](/api/docs/models/gpt-realtime-mini.md): Deprecated. A cost-efficient version of GPT-Realtime110- [GPT-Realtime mini](/api/docs/models/gpt-realtime-mini.md): Deprecated. A cost-efficient version of GPT-Realtime

111- [GPT-Audio Mini](/api/docs/models/gpt-audio-mini.md): Deprecated. A cost-efficient version of GPT Audio111- [GPT-Audio mini](/api/docs/models/gpt-audio-mini.md): Deprecated. A cost-efficient version of GPT Audio

112- [GPT-4o Audio](/api/docs/models/gpt-4o-audio-preview.md): Shut down. GPT-4o models capable of audio inputs and outputs112- [GPT-4o Audio](/api/docs/models/gpt-4o-audio-preview.md): Shut down. GPT-4o models capable of audio inputs and outputs

113- [GPT-4o Mini Audio](/api/docs/models/gpt-4o-mini-audio-preview.md): Shut down. Smaller model capable of audio inputs and outputs113- [GPT-4o Mini Audio](/api/docs/models/gpt-4o-mini-audio-preview.md): Shut down. Smaller model capable of audio inputs and outputs

114- [GPT-4o Realtime](/api/docs/models/gpt-4o-realtime-preview.md): Shut down. Model capable of realtime text and audio inputs and outputs114- [GPT-4o Realtime](/api/docs/models/gpt-4o-realtime-preview.md): Shut down. Model capable of realtime text and audio inputs and outputs

115- [GPT-4o Mini Realtime](/api/docs/models/gpt-4o-mini-realtime-preview.md): Shut down. Smaller realtime model for text and audio inputs and outputs115- [GPT-4o Mini Realtime](/api/docs/models/gpt-4o-mini-realtime-preview.md): Shut down. Smaller realtime model for text and audio inputs and outputs

116- [GPT-4o Mini TTS](/api/docs/models/gpt-4o-mini-tts.md): Deprecated. Text-to-speech model powered by GPT-4o Mini116- [GPT-4o mini TTS](/api/docs/models/gpt-4o-mini-tts.md): Deprecated. Text-to-speech model powered by GPT-4o mini

117- [Daybreak Red](/api/docs/models/gpt-daybreak-red-latest.md): Deprecated. An alias for advanced cybersecurity models for authorized vulnerability research and security testing.117- [Daybreak Red](/api/docs/models/gpt-daybreak-red-latest.md): Deprecated. An alias for advanced cybersecurity models for authorized vulnerability research and security testing.

118- [Daybreak Blue](/api/docs/models/gpt-daybreak-blue-latest.md): Deprecated. An alias for flagship general-purpose models with safeguards for defensive cybersecurity work.118- [Daybreak Blue](/api/docs/models/gpt-daybreak-blue-latest.md): Deprecated. An alias for flagship general-purpose models with safeguards for defensive cybersecurity work.

119- [GPT-5.4 nano](/api/docs/models/gpt-5.4-nano.md): Deprecated. Our cheapest GPT-5.4-class model for simple high-volume tasks119- [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

120- [GPT-5.3-Codex](/api/docs/models/gpt-5.3-codex.md): Deprecated. The most capable agentic coding model to date.120- [GPT-5.3-Codex](/api/docs/models/gpt-5.3-codex.md): Deprecated. The most capable agentic coding model to date.

121- [GPT-5.1](/api/docs/models/gpt-5.1.md): Deprecated. The best model for coding and agentic tasks with configurable reasoning effort121- [GPT-5.1](/api/docs/models/gpt-5.1.md): Deprecated. The best model for coding and agentic tasks with configurable reasoning effort

122- [GPT-5](/api/docs/models/gpt-5.md): Deprecated. Previous intelligent reasoning model for coding and agentic tasks with configurable reasoning effort122- [GPT-5](/api/docs/models/gpt-5.md): Deprecated. Previous intelligent reasoning model for coding and agentic tasks with configurable reasoning effort

123- [GPT-5 Mini](/api/docs/models/gpt-5-mini.md): Deprecated. Strong intelligence for cost sensitive, low latency, high volume workloads123- [GPT-5 mini](/api/docs/models/gpt-5-mini.md): Deprecated. Strong intelligence for cost sensitive, low latency, high volume workloads

124- [GPT-5 nano](/api/docs/models/gpt-5-nano.md): Deprecated. Fastest, most cost-efficient version of GPT-5124- [GPT-5 nano](/api/docs/models/gpt-5-nano.md): Deprecated. Fastest, most cost-efficient version of GPT-5

125- [GPT-5 Pro](/api/docs/models/gpt-5-pro.md): Deprecated. Version of GPT-5 that produces smarter and more precise responses125- [GPT-5 pro](/api/docs/models/gpt-5-pro.md): Deprecated. Version of GPT-5 that produces smarter and more precise responses

126- [o3-pro](/api/docs/models/o3-pro.md): Deprecated. Version of o3 with more compute for better responses126- [o3-pro](/api/docs/models/o3-pro.md): Deprecated. Version of o3 with more compute for better responses

127- [o3](/api/docs/models/o3.md): Deprecated. Reasoning model for complex tasks, succeeded by GPT-5127- [o3](/api/docs/models/o3.md): Deprecated. Reasoning model for complex tasks, succeeded by GPT-5

128- [GPT-4.1](/api/docs/models/gpt-4.1.md): Deprecated. Smartest non-reasoning model128- [GPT-4.1](/api/docs/models/gpt-4.1.md): Deprecated. Smartest non-reasoning model

129- [GPT-4.1 Mini](/api/docs/models/gpt-4.1-mini.md): Deprecated. Smaller, faster version of GPT-4.1129- [GPT-4.1 mini](/api/docs/models/gpt-4.1-mini.md): Deprecated. Smaller, faster version of GPT-4.1

130- [GPT-4o Mini](/api/docs/models/gpt-4o-mini.md): Deprecated. Fast, affordable small model for focused tasks130- [GPT-4o mini](/api/docs/models/gpt-4o-mini.md): Deprecated. Fast, affordable small model for focused tasks

131- [GPT-5.3 Chat](/api/docs/models/gpt-5.3-chat-latest.md): Shut down. GPT-5.3 Instant model used in ChatGPT131- [GPT-5.3 Chat](/api/docs/models/gpt-5.3-chat-latest.md): Shut down. GPT-5.3 Instant model used in ChatGPT

132- [GPT-5.2 Chat](/api/docs/models/gpt-5.2-chat-latest.md): Shut down. GPT-5.2 model used in ChatGPT132- [GPT-5.2 Chat](/api/docs/models/gpt-5.2-chat-latest.md): Shut down. GPT-5.2 model used in ChatGPT

133- [GPT-5.2-Codex](/api/docs/models/gpt-5.2-codex.md): Shut down. Our most intelligent coding model optimized for long-horizon, agentic coding tasks.133- [GPT-5.2-Codex](/api/docs/models/gpt-5.2-codex.md): Shut down. Our most intelligent coding model optimized for long-horizon, agentic coding tasks.

134- [o3-deep-research](/api/docs/models/o3-deep-research.md): Shut down. Retired deep research model134- [o3-deep-research](/api/docs/models/o3-deep-research.md): Shut down. Retired deep research model

135- [o4-mini-deep-research](/api/docs/models/o4-mini-deep-research.md): Shut down. Retired deep research model135- [o4-mini-deep-research](/api/docs/models/o4-mini-deep-research.md): Shut down. Retired deep research model

136- [GPT-4.1 nano](/api/docs/models/gpt-4.1-nano.md): Shut down. Fastest, most cost-efficient version of GPT-4.1136- [GPT-4.1 nano](/api/docs/models/gpt-4.1-nano.md): Shut down. Fastest, most cost-efficient version of GPT-4.1

137- [o4-mini](/api/docs/models/o4-mini.md): Shut down. Fast, cost-efficient reasoning model, succeeded by GPT-5 Mini137- [o4-mini](/api/docs/models/o4-mini.md): Shut down. Fast, cost-efficient reasoning model, succeeded by GPT-5 mini

138- [o1-pro](/api/docs/models/o1-pro.md): Shut down. Version of o1 with more compute for better responses138- [o1-pro](/api/docs/models/o1-pro.md): Shut down. Version of o1 with more compute for better responses

139- [computer-use-preview](/api/docs/models/computer-use-preview.md): Shut down. Specialized model for computer use tool139- [computer-use-preview](/api/docs/models/computer-use-preview.md): Shut down. Specialized model for computer use tool

140- [GPT-4o Mini Search Preview](/api/docs/models/gpt-4o-mini-search-preview.md): Shut down. Fast, affordable small model for web search140- [GPT-4o mini search preview](/api/docs/models/gpt-4o-mini-search-preview.md): Shut down. Fast, affordable small model for web search

141- [GPT-4o Search Preview](/api/docs/models/gpt-4o-search-preview.md): Shut down. GPT model for web search in Chat Completions141- [GPT-4o search preview](/api/docs/models/gpt-4o-search-preview.md): Shut down. GPT model for web search in Chat Completions

142- [GPT-4.5 Preview](/api/docs/models/gpt-4.5-preview.md): Shut down. Deprecated large model.142- [GPT-4.5 Preview](/api/docs/models/gpt-4.5-preview.md): Shut down. Deprecated large model.

143- [o3-mini](/api/docs/models/o3-mini.md): Shut down. A small model alternative to o3143- [o3-mini](/api/docs/models/o3-mini.md): Shut down. A small model alternative to o3

144- [o1](/api/docs/models/o1.md): Shut down. Previous full o-series reasoning model144- [o1](/api/docs/models/o1.md): Shut down. Previous full o-series reasoning model

145- [o1-mini](/api/docs/models/o1-mini.md): Shut down. A small model alternative to o1145- [o1-mini](/api/docs/models/o1-mini.md): Shut down. A small model alternative to o1

146- [o1 Preview](/api/docs/models/o1-preview.md): Shut down. Preview of our first o-series reasoning model146- [o1-preview](/api/docs/models/o1-preview.md): Shut down. Preview of our first o-series reasoning model

147- [GPT-4o](/api/docs/models/gpt-4o.md): Deprecated. Fast, intelligent, flexible GPT model147- [GPT-4o](/api/docs/models/gpt-4o.md): Deprecated. Fast, intelligent, flexible GPT model

148- [GPT-4 Turbo](/api/docs/models/gpt-4-turbo.md): Shut down. An older high-intelligence GPT model148- [GPT-4 Turbo](/api/docs/models/gpt-4-turbo.md): Shut down. An older high-intelligence GPT model

149- [babbage-002](/api/docs/models/babbage-002.md): Shut down. Replacement for the GPT-3 ada and babbage base models149- [babbage-002](/api/docs/models/babbage-002.md): Shut down. Replacement for the GPT-3 ada and babbage base models

150- [ChatGPT-4o](/api/docs/models/chatgpt-4o-latest.md): Shut down. GPT-4o model used in ChatGPT150- [ChatGPT-4o](/api/docs/models/chatgpt-4o-latest.md): Shut down. GPT-4o model used in ChatGPT

151- [GPT-5.1-Codex](/api/docs/models/gpt-5.1-codex.md): Shut down. A version of GPT-5.1 optimized for agentic coding in Codex.151- [GPT-5.1-Codex](/api/docs/models/gpt-5.1-codex.md): Shut down. A version of GPT-5.1 optimized for agentic coding in Codex.

152- [GPT-5.1-Codex-Max](/api/docs/models/gpt-5.1-codex-max.md): Shut down. A version of GPT-5.1-codex optimized for long running tasks.152- [GPT-5.1-Codex-Max](/api/docs/models/gpt-5.1-codex-max.md): Shut down. A version of GPT-5.1-Codex optimized for long running tasks.

153- [GPT-5.1-Codex Mini](/api/docs/models/gpt-5.1-codex-mini.md): Shut down. Smaller, more cost-effective, less-capable version of GPT-5.1-Codex153- [GPT-5.1-Codex-Mini](/api/docs/models/gpt-5.1-codex-mini.md): Shut down. Smaller, more cost-effective, less-capable version of GPT-5.1-Codex

154- [GPT-5-Codex](/api/docs/models/gpt-5-codex.md): Shut down. A version of GPT-5 optimized for agentic coding in Codex154- [GPT-5-Codex](/api/docs/models/gpt-5-codex.md): Shut down. A version of GPT-5 optimized for agentic coding in Codex

155- [codex-mini-latest](/api/docs/models/codex-mini-latest.md): Shut down. Fast reasoning model optimized for the Codex CLI155- [codex-mini-latest](/api/docs/models/codex-mini-latest.md): Shut down. Fast reasoning model optimized for the Codex CLI

156- [davinci-002](/api/docs/models/davinci-002.md): Shut down. Replacement for the GPT-3 curie and davinci base models156- [davinci-002](/api/docs/models/davinci-002.md): Shut down. Replacement for the GPT-3 curie and davinci base models

157- [GPT-3.5 Turbo](/api/docs/models/gpt-3.5-turbo.md): Shut down. Legacy GPT model for cheaper chat and non-chat tasks157- [GPT-3.5 Turbo](/api/docs/models/gpt-3.5-turbo.md): Shut down. Legacy GPT model for cheaper chat and non-chat tasks

158- [GPT-4](/api/docs/models/gpt-4.md): Shut down. An older high-intelligence GPT model158- [GPT-4](/api/docs/models/gpt-4.md): Shut down. An older high-intelligence GPT model

159- [GPT-4 Turbo Preview](/api/docs/models/gpt-4-turbo-preview.md): Shut down. An older fast GPT model159- [GPT-4 Turbo preview](/api/docs/models/gpt-4-turbo-preview.md): Shut down. An older fast GPT model

160- [GPT-5.1 Chat](/api/docs/models/gpt-5.1-chat-latest.md): Shut down. GPT-5.1 model used in ChatGPT160- [GPT-5.1 Chat](/api/docs/models/gpt-5.1-chat-latest.md): Shut down. GPT-5.1 model used in ChatGPT

161- [GPT-5 Chat](/api/docs/models/gpt-5-chat-latest.md): Shut down. GPT-5 model used in ChatGPT161- [GPT-5 Chat](/api/docs/models/gpt-5-chat-latest.md): Shut down. GPT-5 model used in ChatGPT

162- [text-moderation](/api/docs/models/text-moderation-latest.md): Shut down. Previous generation text-only moderation model162- [text-moderation](/api/docs/models/text-moderation-latest.md): Shut down. Previous generation text-only moderation model

185<dependency>185<dependency>

186 <groupId>com.openai</groupId>186 <groupId>com.openai</groupId>

187 <artifactId>openai-java</artifactId>187 <artifactId>openai-java</artifactId>

188 <version>4.103.0</version>188 <version>4.104.0</version>

189</dependency>189</dependency>

190```190```

191 191