# GPT-5.3 Codex

GPT-5.3 Codex — модель OpenAI, выпущенная 05 февр. 2026. Контекстное окно — 400 000 токенов. Максимальная длина ответа — 128 000 токенов.

- Разработчик: OpenAI
- Id: gpt-5.3-codex
- По сообщениям: 2026-02-05T00:00:00.000Z
- Релиз: 2026-02-05T00:00:00.000Z
- Обнаружение: 2026-09-17T17:42:08.188Z
  - [ссылка на источник](https://developers.openai.com/api/docs/changelog)
- Статус: Релиз
- Обновление продукта: 2026-02-05
  - [ссылка на источник](https://openai.com/index/introducing-gpt-5-3-codex/)
- Доступность в API: 2026-02-24
  - [ссылка на источник](https://developers.openai.com/api/docs/changelog)
- Обновление продукта: 2026-02-09
  - [ссылка на источник](https://developers.openai.com/codex/changelog/#codex-2026-02-09)
- Канонический адрес: https://alexgetman.com/ru/models/openai/gpt-5-3-codex/

## Вопросы

### Какое контекстное окно у GPT-5.3 Codex?

Контекстное окно — 400 000 токенов. Максимальная длина ответа — 128 000 токенов.

### Когда вышла GPT-5.3 Codex?

Дата релиза — 05 февр. 2026.

## Хронология

- 2026-09-17T17:42:08.188Z · [OpenAI · API changelog](https://developers.openai.com/api/docs/changelog)
> Released gpt-5.3-codex to the Responses API
- 2026-10-07T19:17:54.872Z · [OpenAI · Codex changelog](https://developers.openai.com/codex/changelog/#codex-2026-02-09)
> GPT-5.3-Codex in Cursor and VS Code Starting today, GPT-5.3-Codex is available natively in Cursor and VS Code
- 2026-11-10T17:58:10.980Z · [GitHub · openai/openai-agents-js · code](https://github.com/openai/openai-agents-js/blob/7589b9c40120b89a7d2d28a5a60b4defe1ed7bf5/packages/agents-core/src/sandbox/capabilities/compaction.ts)
> new Set([
>   'gpt-5',
>   'gpt-5-codex',
>   'gpt-5-mini',
>   'gpt-5-nano',
>   'gpt-5-pro',
>   'gpt-5.1',
>   'gpt-5.1-codex',
>   'gpt-5.1-codex-max',
>   'gpt-5.1-codex-mini',
>   'gpt-5.2',
>   'gpt-5.2-codex',
>   'gpt-5.2-codex-cyber',
>   'gpt-5.2-pro',
>   'gpt-5.3-codex',
>   'gpt-5.3-codex-spark',
>   'gpt-5.4-mini',
>   'gpt-5.4-nano',
> ]);
> 
> const SANDBOX_CONTEXT_WINDOWS_200K = new Set([
>   'codex-mini-latest',
>   'o1',
>   'o1-2024-12-17',
>   'o1-pro',
>   'o3',
>   'o3-2025-04-16',
>   'o3-mini',
>   'o3-pro',
>   'o3-deep-research',
>   'o4-mini',
>   'o4-mini-2025-04-16',
>   'o4-mini-deep-research',
> ]);
> 
> const SANDBOX_CONTEXT_WINDOWS_128K = new Set([
>   'gpt-4o',
>   'gpt-4o-2024-08-06',
>   'gpt-4o-mini',
>   'gpt-4o-mini-2024-07-18',
>   'gpt-5-chat-latest',
>   'gpt-5.1-chat-latest',
>   'gpt-5.2-chat-latest',
>   'gpt-5.3-chat-latest',
> ]);
> 
- 2026-11-10T17:58:16.002Z · [GitHub · openai/openai-python · code](https://github.com/openai/openai-python/blob/0ebd00647f6088fb100b03440c6c4554bbab549d/api_reference/openapi.transformed.yml)
>  "incomplete_details": null
>           }
>     MessagePhase:
>       type: string
>       description: |
>         Labels an `assistant` message as intermediate commentary (`commentary`) or the final answer (`final_answer`).
>         For models like `gpt-5.3-codex` and beyond, when sending follow-up requests, preserve and resend
>         phase on all assistant messages — dropping it can degrade performance. Not used for user messages.
>       enum:
>       - commentary
>       - final_answer
>     MessageRequestContentTextObject:
>       title: Text
>       type: object
>       description: The text content that is part of a message.
>       properties:
>         type:
>           description: Always `text`.
>           type: string
>           enum:
>           - text
>           x-stainless-const: true
>         text:
>           type: string
>           description: Text content to be sent to the model
>       required:
>     
Это упоминание в коде не подтверждает рабочий идентификатор модели.
- 2026-11-10T17:58:16.002Z · [GitHub · openai/openai-python · code](https://github.com/openai/openai-python/blob/141a89aa7fbb7f13a979bda930831a5fe38bc3a4/api_reference/openapi.transformed.yml)
> 
>         phase:
>           anyOf:
>           - $ref: '#/components/schemas/MessagePhase-2'
>             description: Labels an `assistant` message as intermediate commentary (`commentary`) or the final answer (`final_answer`). For models like `gpt-5.3-codex` and beyond, when sending follow-up requests, preserve and resend phase on all assistant messages — dropping it can degrade performance. Not used for user messages.
>           - type: 'null'
>       type: object
>       required:
>       - type
>       - id
>       - status
>       - role
>       - content
>       title: Message
>       description: A message to or from the model.
>     DirectToolCallCaller:
>       properties:
>         type:
>           type: string
>           enum:
>           - direct
>           default: direct
>           x-stainless-const: true
>       type: object
>       required:
>       - type
>     ProgramToolCallCaller:
>       properties:
>      
Это упоминание в коде не подтверждает рабочий идентификатор модели.
- 2026-11-10T17:59:50.472Z · [GitHub · openai/openai-agents-python · code](https://github.com/openai/openai-agents-python/blob/d68961657843c7d81dfc25834484f8aac2957eb3/src/agents/sandbox/capabilities/compaction.py)
> 1-codex",
>             "gpt-5.1-codex-max",
>             "gpt-5.1-codex-mini",
>             "gpt-5.2",
>             "gpt-5.2-2025-12-11",
>             "gpt-5.2-codex",
>             "gpt-5.2-pro",
>             "gpt-5.2-pro-2025-12-11",
>             "gpt-5.3-codex",
>             "gpt-5.4-mini",
>             "gpt-5.4-mini-2026-03-17",
>             "gpt-5.4-nano",
>             "gpt-5.4-nano-2026-03-17",
>         ),
>         400_000,
>     ),
>     **_model_context_windows(
>         (
>             "codex-mini-latest",
>             "o1",
>             "o1-2024-12-17",
>             "o1-pro",
>             "o1-pro-2025-03-19",
>             "o3",
>             "o3-2025-04-16",
>             "o3-deep-research",
>             "o3-deep-research-2025-06-26",
>             "o3-mini",
>             "o3-mini-2025-01-31",
>             "o3-pro",
>             "o3-pro-2025-06-10",
>             "o4-mini",
>             "o4-mini-2025-04-16",
>   
- 2026-11-10T18:00:44.369Z · [GitHub · openai/codex · code](https://github.com/openai/codex/blob/82e6bacb9c6950d3b56cb153847fa80bdd698053/codex-rs/core/src/session/mod.rs)
>  while requested model was {requested_model}");
> 
>         let warning_message = format!(
>             "Your account was flagged for potentially high-risk cyber activity and this request was routed to gpt-5.2 as a fallback. To regain access to gpt-5.3-codex, apply for trusted access: {CYBER_VERIFY_URL} or learn more: {CYBER_SAFETY_URL}"
>         );
> 
>         self.send_event(
>             turn_context,
>             EventMsg::ModelReroute(ModelRerouteEvent {
>                 from_model: requested_model.clone(),
>                 to_model: server_model.clone(),
>                 reason: ModelRerouteReason::HighRiskCyberActivity,
>             }),
>         )
>         .await;
> 
>         self.send_event(
>             turn_context,
>             EventMsg::Warning(WarningEvent {
>                 message: warning_message.clone(),
>             }),
>         )
>         .await;
>         true
>     }
> 
>     pub(crate) async 
Это упоминание в коде не подтверждает рабочий идентификатор модели.
- 2026-11-10T18:00:44.369Z · [GitHub · openai/codex · code](https://github.com/openai/codex/blob/627b579219d492b5445d6d433d3110eb53e507dc/codex-rs/core/tests/suite/remote_models.rs)
> ty::List,
>         /*priority*/ 1_000,
>         TruncationPolicyConfig::bytes(/*limit*/ 10_000),
>     );
>     let specific = test_remote_model_with_policy(
>         "gpt-5.3-codex",
>         ModelVisibility::List,
>         /*priority*/ 1_000,
>         TruncationPolicyConfig::bytes(/*limit*/ 10_000),
>     );
>     let specific = ModelInfo {
>         display_name: "GPT 5.3 Codex".to_string(),
>         model_messages: Some(ModelMessages {
>             instructions_template: Some("use specific prefix".to_st
Это упоминание в коде не подтверждает рабочий идентификатор модели.
- 2026-11-12T18:45:20.401Z · [GitHub · openai/openai-node · code](https://github.com/openai/openai-node/blob/b579bcb3e586d22269ffe6fe504653a0e05acbe8/api_reference/openapi.transformed.yml)
>  "incomplete_details": null
>           }
>     MessagePhase:
>       type: string
>       description: |
>         Labels an `assistant` message as intermediate commentary (`commentary`) or the final answer (`final_answer`).
>         For models like `gpt-5.3-codex` and beyond, when sending follow-up requests, preserve and resend
>         phase on all assistant messages — dropping it can degrade performance. Not used for user messages.
>       enum:
>       - commentary
>       - final_answer
>     MessageRequestContentTextObject:
>       title: Text
>       type: object
>       description: The text content that is part of a message.
>       properties:
>         type:
>           description: Always `text`.
>           type: string
>           enum:
>           - text
>           x-stainless-const: true
>         text:
>           type: string
>           description: Text content to be sent to the model
>       required:
>     
Это упоминание в коде не подтверждает рабочий идентификатор модели.
- 2026-11-13T22:47:01.410Z · [OpenAI · official articles](https://openai.com/index/introducing-gpt-5-4)
> Over recent months, we’ve continued improving the safeguards we introduced with GPT‑5.3‑Codex while preparing GPT‑5.4 for deployment
- 2026-11-13T23:47:52.113Z · [OpenAI · official articles](https://openai.com/index/introducing-gpt-5-3-codex)
**Подтверждённое использование**
- 2026-11-13T23:47:52.113Z · [OpenAI · official articles · Introducing GPT-5.3-Codex](https://openai.com/index/introducing-gpt-5-3-codex)
> How we used Codex to train and deploy GPT‑5.3‑Codex

## Ссылки на источники

- [Artificial Analysis · benchmarks](https://artificialanalysis.ai/models)
- [openai-api-changelog](https://developers.openai.com/api/docs/changelog)
- [review](https://developers.openai.com/api/docs/models/gpt-5.3-codex)
- [openai-pricing](https://developers.openai.com/api/docs/pricing)
- [openai-codex-changelog](https://developers.openai.com/codex/changelog/#codex-2026-02-09)
- [GitHub · openai/codex · code](https://github.com/openai/codex/blob/627b579219d492b5445d6d433d3110eb53e507dc/codex-rs/core/tests/suite/remote_models.rs)
- [GitHub · openai/codex · code](https://github.com/openai/codex/blob/82e6bacb9c6950d3b56cb153847fa80bdd698053/codex-rs/core/src/session/mod.rs)
- [GitHub · openai/openai-agents-js · code](https://github.com/openai/openai-agents-js/blob/7589b9c40120b89a7d2d28a5a60b4defe1ed7bf5/packages/agents-core/src/sandbox/capabilities/compaction.ts)
- [GitHub · openai/openai-agents-python · code](https://github.com/openai/openai-agents-python/blob/d68961657843c7d81dfc25834484f8aac2957eb3/src/agents/sandbox/capabilities/compaction.py)
- [GitHub · openai/openai-node · code](https://github.com/openai/openai-node/blob/b579bcb3e586d22269ffe6fe504653a0e05acbe8/api_reference/openapi.transformed.yml)
- [GitHub · openai/openai-python · code](https://github.com/openai/openai-python/blob/0ebd00647f6088fb100b03440c6c4554bbab549d/api_reference/openapi.transformed.yml)
- [GitHub · openai/openai-python · code](https://github.com/openai/openai-python/blob/141a89aa7fbb7f13a979bda930831a5fe38bc3a4/api_reference/openapi.transformed.yml)
- [models.dev · catalogue](https://models.dev/#gpt-5-3-codex)
- [models.dev · catalogue](https://models.dev/#gpt-5.3-codex)
- [models.dev · catalogue](https://models.dev/#gpt-5.3-codex-xhigh)
- [openai-articles](https://openai.com/index/introducing-gpt-5-3-codex)
- [review](https://openai.com/index/introducing-gpt-5-3-codex/)
- [openai-articles](https://openai.com/index/introducing-gpt-5-4)
- [OpenCode · discovery](https://opencode.ai/data/openai/gpt-5-3-codex)
- [OpenRouter](https://openrouter.ai/openai/gpt-5.3-codex)
- [OpenAI · deprecations](https://platform.openai.com/docs/deprecations)

## Сигналы

- [GPT-5.3 Codex: Обновление продукта](https://alexgetman.com/ru/signals/2026/10/21/gpt-5-3-codex/)
- [GPT-5.3 Codex: Обновление продукта](https://alexgetman.com/ru/signals/2026/09/11/gpt-5-3-codex-xhigh/)