Documentation 2026-07-22 20:02 UTC to 2026-07-23 03:02 UTC

53On June 11, 2026, we notified developers using older GPT-5 and o3 model snapshots of their deprecation and removal from the API on December 11, 2026.53On June 11, 2026, we notified developers using older GPT-5 and o3 model snapshots of their deprecation and removal from the API on December 11, 2026.

54 54 

55| Shutdown date | Model / system | Recommended replacement |55| Shutdown date | Model / system | Recommended replacement |

56| ------------- | ----------------------- | ----------------------- |56| ------------- | ----------------------- | ------------------------------------- |

57| Dec 11, 2026 | `gpt-5-2025-08-07` | `gpt-5.5` |57| Dec 11, 2026 | `gpt-5-2025-08-07` | `gpt-5.6-sol` |

58| Dec 11, 2026 | `gpt-5-mini-2025-08-07` | `gpt-5.4-mini` |58| Dec 11, 2026 | `gpt-5-mini-2025-08-07` | `gpt-5.6-terra` |

59| Dec 11, 2026 | `gpt-5-nano-2025-08-07` | `gpt-5.4-nano` |59| Dec 11, 2026 | `gpt-5-nano-2025-08-07` | `gpt-5.6-luna` |

60| Dec 11, 2026 | `gpt-5-pro-2025-10-06` | `gpt-5.5-pro` |60| Dec 11, 2026 | `gpt-5-pro-2025-10-06` | `gpt-5.6-sol` (`reasoning.mode: pro`) |

61| Dec 11, 2026 | `o3-2025-04-16` | `gpt-5.5` |61| Dec 11, 2026 | `o3-2025-04-16` | `gpt-5.6-sol` |

62| Dec 11, 2026 | `o3-pro-2025-06-10` | `gpt-5.5-pro` |62| Dec 11, 2026 | `o3-pro-2025-06-10` | `gpt-5.6-sol` (`reasoning.mode: pro`) |

63 63 

64### 2026-06-03: Reusable prompts64### 2026-06-03: Reusable prompts

65 65 

113 113 

114| Shutdown date | Model / system | Recommended replacement |114| Shutdown date | Model / system | Recommended replacement |

115| ------------- | --------------------- | ----------------------- |115| ------------- | --------------------- | ----------------------- |

116| Aug 10, 2026 | `gpt-5.2-chat-latest` | `gpt-5.5` |116| Aug 10, 2026 | `gpt-5.2-chat-latest` | `gpt-5.6-sol` |

117| Aug 10, 2026 | `gpt-5.3-chat-latest` | `gpt-5.5` |117| Aug 10, 2026 | `gpt-5.3-chat-latest` | `gpt-5.6-sol` |

118 118 

119### Update to OpenAI’s self-serve fine-tuning119### Update to OpenAI’s self-serve fine-tuning

120 120 

133To 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.133To 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.

134 134 

135| Shutdown date | Model snapshot | Substitute model |135| Shutdown date | Model snapshot | Substitute model |

136| ------------- | ---------------------------------------------------------------------- | ---------------------------- |136| ------------- | ---------------------------------------------------------------------- | ------------------------------------- |

137| 2026-07-23 | `computer-use-preview-2025-03-11` \| `computer-use-preview` | `gpt-5.4-mini` |137| July 23, 2026 | `computer-use-preview-2025-03-11` \| `computer-use-preview` | `gpt-5.6-terra` |

138| 2026-07-23 | `gpt-4o-mini-search-preview-2025-03-11` | `gpt-5.4-mini` |138| July 23, 2026 | `gpt-4o-mini-search-preview-2025-03-11` | `gpt-5.6-terra` |

139| 2026-07-23 | `gpt-4o-mini-tts-2025-03-20` | `gpt-4o-mini-tts-2025-12-15` |139| July 23, 2026 | `gpt-4o-mini-tts-2025-03-20` | `gpt-4o-mini-tts-2025-12-15` |

140| 2026-07-23 | `gpt-4o-search-preview-2025-03-11` | `gpt-5.4-mini` |140| July 23, 2026 | `gpt-4o-search-preview-2025-03-11` | `gpt-5.6-terra` |

141| 2026-07-23 | `gpt-5-chat-latest` | `gpt-5.5` |141| July 23, 2026 | `gpt-5-chat-latest` | `gpt-5.6-sol` |

142| 2026-07-23 | `gpt-5-codex` | `gpt-5.5` |142| July 23, 2026 | `gpt-5-codex` | `gpt-5.6-sol` |

143| 2026-07-23 | `gpt-5.1-chat-latest` | `gpt-5.5` |143| July 23, 2026 | `gpt-5.1-chat-latest` | `gpt-5.6-sol` |

144| 2026-07-23 | `gpt-5.1-codex` | `gpt-5.5` |144| July 23, 2026 | `gpt-5.1-codex` | `gpt-5.6-sol` |

145| 2026-07-23 | `gpt-5.1-codex-max` | `gpt-5.5` |145| July 23, 2026 | `gpt-5.1-codex-max` | `gpt-5.6-sol` |

146| 2026-07-23 | `gpt-5.1-codex-mini` | `gpt-5.4-mini` |146| July 23, 2026 | `gpt-5.1-codex-mini` | `gpt-5.6-terra` |

147| 2026-07-23 | `gpt-audio-mini-2025-10-06` | `gpt-audio-1.5` |147| July 23, 2026 | `gpt-audio-mini-2025-10-06` | `gpt-audio-1.5` |

148| 2026-07-23 | `gpt-realtime-mini-2025-10-06` | `gpt-realtime-mini` |148| July 23, 2026 | `gpt-realtime-mini-2025-10-06` | `gpt-realtime-2.1-mini` |

149| 2026-07-23 | `o3-deep-research-2025-06-26` \| `o3-deep-research` | `gpt-5.5-pro` |149| July 23, 2026 | `o3-deep-research-2025-06-26` \| `o3-deep-research` | `gpt-5.6-sol` |

150| 2026-07-23 | `o4-mini-deep-research-2025-06-26` \| `o4-mini-deep-research` | `gpt-5.5-pro` |150| July 23, 2026 | `o4-mini-deep-research-2025-06-26` \| `o4-mini-deep-research` | `gpt-5.6-sol` |

151| 2026-07-23 | `gpt-5.2-codex` | `gpt-5.5` |151| July 23, 2026 | `gpt-5.2-codex` | `gpt-5.6-sol` |

152| 2026-10-23 | `gpt-3.5-turbo-0125` \| `gpt-3.5-turbo`, `gpt-3.5-turbo-completions` | `gpt-5.4-mini` |152| 2026-10-23 | `gpt-3.5-turbo-0125` \| `gpt-3.5-turbo`, `gpt-3.5-turbo-completions` | `gpt-5.6-terra` |

153| 2026-10-23 | `gpt-4-0613` \| `gpt-4`, `gpt-4-0613-completions`, `gpt-4-completions` | `gpt-5.5` |153| 2026-10-23 | `gpt-4-0613` \| `gpt-4`, `gpt-4-0613-completions`, `gpt-4-completions` | `gpt-5.6-sol` |

154| 2026-10-23 | `gpt-4-1106-preview` | `gpt-5.5` |154| 2026-10-23 | `gpt-4-1106-preview` | `gpt-5.6-sol` |

155| 2026-10-23 | `gpt-4-turbo` \| `gpt-4-turbo-2024-04-09`, `gpt-4-turbo-completions` | `gpt-5.5` |155| 2026-10-23 | `gpt-4-turbo` \| `gpt-4-turbo-2024-04-09`, `gpt-4-turbo-completions` | `gpt-5.6-sol` |

156| 2026-10-23 | `gpt-4.1-nano` \| `gpt-4.1-nano-2025-04-14` | `gpt-5.4-nano` |156| 2026-10-23 | `gpt-4.1-nano` \| `gpt-4.1-nano-2025-04-14` | `gpt-5.6-luna` |

157| 2026-10-23 | `gpt-4o-2024-05-13` | `gpt-5.5` |157| 2026-10-23 | `gpt-4o-2024-05-13` | `gpt-5.6-sol` |

158| 2026-10-23 | `gpt-image-1` | `gpt-image-2` |158| 2026-10-23 | `gpt-image-1` | `gpt-image-2` |

159| 2026-10-23 | `o1-2024-12-17` \| `o1` | `gpt-5.5` |159| 2026-10-23 | `o1-2024-12-17` \| `o1` | `gpt-5.6-sol` |

160| 2026-10-23 | `o1-pro-2025-03-19` \| `o1-pro` | `gpt-5.5-pro` |160| 2026-10-23 | `o1-pro-2025-03-19` \| `o1-pro` | `gpt-5.6-sol` (`reasoning.mode: pro`) |

161| 2026-10-23 | `o3-mini-2025-01-31` \| `o3-mini` | `gpt-5.5` |161| 2026-10-23 | `o3-mini-2025-01-31` \| `o3-mini` | `gpt-5.6-sol` |

162| 2026-10-23 | `ft-o4-mini-2025-04-16` | `gpt-5.4-mini` |162| 2026-10-23 | `ft-o4-mini-2025-04-16` | `gpt-5.6-terra` |

163| 2026-10-23 | `o4-mini-2025-04-16` \| `o4-mini` | `gpt-5.4-mini` |163| 2026-10-23 | `o4-mini-2025-04-16` \| `o4-mini` | `gpt-5.6-terra` |

164 164 

165We are also removing fine-tuned versions as below:165We are also removing fine-tuned versions as below:

166 166 

1# Error codes1# Error codes

2 2 

3This guide includes an overview on error codes you might see from both the [API](https://developers.openai.com/api/docs/introduction) and our [official Python library](https://developers.openai.com/api/docs/libraries#python-library). Each error code mentioned in the overview has a dedicated section with further guidance.3This guide includes an overview on error codes you might see from both the [API](https://developers.openai.com/api/docs/introduction) and our [official Python library](https://developers.openai.com/api/docs/libraries#install-an-official-sdk). Each error code mentioned in the overview has a dedicated section with further guidance.

4 4 

5## API errors5## API errors

6 6 

86 86 

87429 - You exceeded your current quota, please check your plan and billing details87429 - You exceeded your current quota, please check your plan and billing details

88 88 

89This error message indicates that you hit your monthly [usage limit](https://platform.openai.com/settings/organization/limits) for the API, or for prepaid credits customers that you've consumed all your credits. You can view your maximum usage limit on the [limits page](https://platform.openai.com/settings/organization/limits). This could happen for several reasons, such as:89This error message indicates that the organization exhausted its prepaid credits, reached its OpenAI-approved monthly [usage limit](https://platform.openai.com/settings/organization/limits), or reached an enforced organization or project [spend limit](https://developers.openai.com/api/docs/guides/spend-limits).

90 90 

91- You are using a high-volume or complex service that consumes a lot of credits or tokens.91To resolve this error:

92- Your monthly budget is set too low for your organization’s usage.

93- Your monthly budget is set too low for your project's usage.

94 92 

95To resolve this error, please follow these steps:93- Compare [current usage](https://platform.openai.com/settings/organization/usage) with the organization's approved usage limit and applicable organization or project spend limits.

96 94- [Buy more credits](https://platform.openai.com/settings/organization/billing) or request a higher approved usage limit when needed.

97- Check your [current usage](https://platform.openai.com/settings/organization/usage) of your account, and compare that to your account's [limits](https://platform.openai.com/settings/organization/limits).95- Raise or remove the applicable hard spend limit if API traffic should resume before the monthly reset.

98- If you are on a free plan, consider [upgrading to a paid plan](https://platform.openai.com/settings/organization/billing) to get higher limits.

99- Reach out to your organization owner to increase the budgets for your project.

100 96 

101503 - The engine is currently overloaded, please try again later97503 - The engine is currently overloaded, please try again later

102 98 

38 38 

39Once you’ve entered your billing information, OpenAI sets an approved usage limit for your organization. Your quota limit will automatically increase as your usage on your platform increases and you move from one [usage tier](https://developers.openai.com/api/docs/guides/rate-limits#usage-tiers) to another. You can review your current usage limit in the [limits](https://platform.openai.com/settings/organization/limits) page in your account settings.39Once you’ve entered your billing information, OpenAI sets an approved usage limit for your organization. Your quota limit will automatically increase as your usage on your platform increases and you move from one [usage tier](https://developers.openai.com/api/docs/guides/rate-limits#usage-tiers) to another. You can review your current usage limit in the [limits](https://platform.openai.com/settings/organization/limits) page in your account settings.

40 40 

41If you’d like to be notified when your usage exceeds a certain dollar amount, you can set spend alerts on the [limits](https://platform.openai.com/settings/organization/limits) page. For stricter budget control, see the [spend limits guide](https://developers.openai.com/api/docs/guides/spend-limits).41Set spend alerts on the [limits](https://platform.openai.com/settings/organization/limits) page to send notifications when usage exceeds a certain dollar amount. To enforce a monthly cap, set a hard spend limit. Hard spend limits stop affected API traffic when tracked spend reaches the limit, so review the [spend limits guide](https://developers.openai.com/api/docs/guides/spend-limits) before enabling one in production.

42 42 

43### API keys43### API keys

44 44 

27- Rate limits are defined at the [organization level](https://developers.openai.com/api/docs/guides/production-best-practices) and at the project level, not user level.27- Rate limits are defined at the [organization level](https://developers.openai.com/api/docs/guides/production-best-practices) and at the project level, not user level.

28- Rate limits vary by the [model](https://developers.openai.com/api/docs/models) being used.28- Rate limits vary by the [model](https://developers.openai.com/api/docs/models) being used.

29- For long context models like GPT-5.5, there is a separate rate limit for long context requests. You can view these rate limits in [developer console](https://platform.openai.com/settings/organization/limits).29- For long context models like GPT-5.5, there is a separate rate limit for long context requests. You can view these rate limits in [developer console](https://platform.openai.com/settings/organization/limits).

30- You can set [spend limits](https://developers.openai.com/api/docs/guides/spend-limits) for the total amount an organization or project can spend on the API each month.30- OpenAI sets an approved monthly usage limit for each organization. This is separate from the [spend limits](https://developers.openai.com/api/docs/guides/spend-limits) that you can configure for an organization or project.

31- Some model families have shared rate limits. Any models listed under a "shared limit" in your [organizations limit page](https://platform.openai.com/settings/organization/limits) share a rate limit between them. For example, if the listed shared TPM is 3.5M, all calls to any model in the given "shared limit" list will count towards that 3.5M.31- Some model families have shared rate limits. Any models listed under a "shared limit" in your [organizations limit page](https://platform.openai.com/settings/organization/limits) share a rate limit between them. For example, if the listed shared TPM is 3.5M, all calls to any model in the given "shared limit" list will count towards that 3.5M.

32- Vector store ingestion is also rate limited per vector store ID. `/vector_stores/{vector_store_id}/files` and `/vector_stores/{vector_store_id}/file_batches` share a limit of 300 requests per minute for each vector store. For larger ingests, prefer `/vector_stores/{vector_store_id}/file_batches`.32- Vector store ingestion is also rate limited per vector store ID. `/vector_stores/{vector_store_id}/files` and `/vector_stores/{vector_store_id}/file_batches` share a limit of 300 requests per minute for each vector store. For larger ingests, prefer `/vector_stores/{vector_store_id}/file_batches`.

33 33 

1# Spend limits1# Spend limits

2 2 

3Spend limits help you control API costs by setting monthly budgets for your organization or for individual projects. You can use them as a soft budget for monitoring spend, or enforce a hard limit so API responses fail after spend reaches the limit.3Use spend alerts to track monthly API costs. To stop traffic after tracked spend reaches a configured amount, enforce a hard spend limit for your organization or an individual project.

4 4 

5## How spend limits work5Hard spend limits can interrupt production traffic. When tracked spend reaches

6 an applicable hard limit, affected API requests return a `429` error with the

7 `insufficient_quota` code. Enforcement is not instantaneous, so recorded spend

8 can slightly exceed the configured amount.

6 9 

7Spend limits are monthly limits measured in U.S. dollars. They can apply at two levels:10## Choose a spend control

8 11 

9- **Organization spend limits** apply across the organization.12Spend alerts and hard spend limits have different effects:

10- **Project spend limits** apply to a single project.

11 13 

12You can also enforce either level as a hard limit, which makes API responses fail after spend reaches the monthly limit.14| Control | What happens at the configured amount | Use it when you want to |

15| ---------------- | ------------------------------------------- | --------------------------------------------- |

16| Spend alert | Sends a notification; API traffic continues | Track spend without interrupting traffic |

17| Hard spend limit | Affected API requests return a `429` error | Enforce a monthly organization or project cap |

13 18 

14## Using hard limits19Spend alerts do not enforce a cap. They remain active when you add a hard spend limit, so you can use alerts for notification before a hard limit interrupts traffic.

15 20 

16A hard limit causes API responses to fail after the organization or project reaches its monthly spend limit. After spend reaches a hard limit, API responses return a `429` error until you increase the spend limit or the limit resets.21OpenAI also assigns your organization an approved monthly [usage limit based on its usage tier](https://developers.openai.com/api/docs/guides/rate-limits#usage-tiers). This OpenAI-approved usage limit is separate from the spend limits you configure.

17 22 

18Use hard limits when you need to prevent unexpected spend, such as for experiments, development projects, or customer-specific projects with fixed budgets.23## Configure a spend limit

19 24 

20## Configuring spend limits25You need permission to manage the applicable organization or project settings. For details, see [API Platform permissions](https://developers.openai.com/api/docs/guides/rbac).

21 26 

22 27 

23 28 

45 50 

46 51 

47 52 

53## Understand hard-limit behavior

54 

55Organization and project hard limits can both apply to a request:

56 

57- An organization hard limit applies to API traffic across all projects in the organization.

58- A project hard limit applies only to API traffic billed to that project.

59- Reaching either applicable hard limit causes affected requests to return `429` errors with the `insufficient_quota` code.

60- Raising or removing the reached limit allows traffic to resume after the update propagates. Otherwise, the limit resets with the next monthly cycle.

61 

62Enforcement is not instantaneous. The API Platform can process a small amount of extra usage while the limit state propagates, so recorded spend can slightly exceed the configured amount.

63 

48## Spend alerts64## Spend alerts

49 65 

50Use spend alerts to get notified before spend reaches the monthly limit. Add alerts at thresholds that give your team enough time to adjust usage, increase the limit, or investigate unexpected traffic.66Use spend alerts to get notified before spend reaches a hard limit. Add alerts at thresholds that allow time to adjust usage, raise the limit, or investigate unexpected traffic.

67 

68## Restore API traffic

69 

70If requests return quota-related `429` errors:

51 71 

52For broader usage analysis, review the [usage dashboard](https://platform.openai.com/settings/organization/usage). For request-rate constraints, see the [rate limits guide](https://developers.openai.com/api/docs/guides/rate-limits).721. Compare [current usage](https://platform.openai.com/settings/organization/usage) with the organization and project spend limits that apply to the request.

732. Raise or remove the reached hard limit if traffic should resume before the monthly reset.

743. If tracked spend is below every applicable hard limit, check whether the organization exhausted prepaid credits or reached its OpenAI-approved usage limit.

754. If the error reports a request or token rate limit instead of `insufficient_quota`, follow the [rate limit guide](https://developers.openai.com/api/docs/guides/rate-limits).