# GPT-5.4

GPT-5.4 is een AI-model van OpenAI, uitgebracht op 2026-03-05. Het contextvenster is 1.050.000 tokens. De maximale uitvoer is 128.000 tokens.

- Ontwikkelaar: OpenAI
- Id: gpt-5.4
- Volgens berichten: 2026-03-05T00:00:00.000Z
- Uitgebracht: 2026-03-05T00:00:00.000Z
- Ontdekking: 2026-10-07T16:22:11.205Z
  - [bronlink](https://github.com/truefoundry/models/blob/main/providers/microsoft-foundry/gpt-5.4.yaml)
- Status: Uitgebracht
- Beschikbaarheid API: 2026-03-05
  - [bronlink](https://developers.openai.com/api/docs/changelog)
  - [bronlink](https://developers.openai.com/api/docs/changelog)
  - [bronlink](https://openai.com/index/introducing-gpt-5-4)
- Productupdate: 2026-03-05
  - [bronlink](https://developers.openai.com/codex/changelog/#codex-2026-03-05)
- Canoniek: https://alexgetman.com/nl/models/openai/gpt-5-4/

## Vragen

### Wat is het contextvenster van GPT-5.4?

Het contextvenster is 1.050.000 tokens. De maximale uitvoer is 128.000 tokens.

### Wanneer werd GPT-5.4 uitgebracht?

2026-03-05.

## Tijdlijn

- 2026-07-30T19:11:33.858Z · [Alex Getman](https://alexgetman.com/133/using-gpt-5-6-luna-max-you-get-the-power-of-march-s-flagship-gpt-5-4-xhigh-for-o/)
> Using GPT 5.6 Luna Max, you get the power of March’s flagship GPT 5.4 xhigh for one thirteenth of its price.
- 2026-09-11T22:39:47.331Z · [GitHub · openai/codex · PR](https://github.com/openai/codex/pull/44930)
> #44930 Embed friendly instructions in bundled GPT-5.4 and GPT-5.5
- 2026-10-07T18:13:28.058Z · [OpenAI · ChatGPT release notes](https://help.openai.com/en/articles/6825453-chatgpt-release-notes)
> GPT‑5.4 Thinking also has improved context window management that supports its ability to think for longer
- 2026-10-07T19:17:54.872Z · [OpenAI · Codex changelog](https://developers.openai.com/codex/changelog/#codex-2026-03-05)
> Introducing GPT-5.4 in Codex GPT-5.4 is now available in Codex as OpenAI's most capable and efficient frontier model for professional work
- 2026-11-05T14:39:16.565Z · [OpenAI · Model release notes](https://help.openai.com/en/articles/9624314-model-release-notes)
> GPT‑5.4 Thinking also has improved context window management that supports its ability to think for longer
- 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)
> 
> 
>   return [...new Set([normalized, withoutPinnedDate])];
> }
> 
> const SANDBOX_CONTEXT_WINDOWS_1M = new Set([
>   'gpt-6-astra',
>   'gpt-6-sol',
>   'gpt-6-luna',
>   'gpt-6.1-sol',
>   'gpt-5.6',
>   'gpt-5.6-sol',
>   'gpt-5.6-terra',
>   'gpt-5.6-luna',
>   'gpt-5.4',
>   'gpt-5.4-2026-03-05',
>   'gpt-5.4-pro',
>   'gpt-5.4-pro-2026-03-05',
>   'gpt-4.1',
>   'gpt-4.1-2025-04-14',
>   'gpt-4.1-mini',
>   'gpt-4.1-mini-2025-04-14',
>   'gpt-4.1-nano',
>   'gpt-4.1-nano-2025-04-14',
> ]);
> 
> const SANDBOX_CONTEXT_WINDOWS_400K = 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',
>   
- 2026-11-10T17:58:16.002Z · [GitHub · openai/openai-python · code](https://github.com/openai/openai-python/blob/0ebd00647f6088fb100b03440c6c4554bbab549d/src/openai/types/beta/beta_responses_client_event.py)
> -sol",
>             "gpt-6.1-terra",
>             "gpt-6-sol",
>             "gpt-6-luna",
>             "gpt-5.6-sol",
>             "gpt-5.6-terra",
>             "gpt-5.6-luna",
>             "gpt-5.5",
>             "gpt-5.5-2026-04-23",
>             "gpt-5.4",
>             "gpt-5.4-mini",
>             "gpt-5.4-nano",
>             "gpt-5.4-mini-2026-03-17",
>             "gpt-5.4-nano-2026-03-17",
>             "gpt-5.3-chat-latest",
>             "gpt-5.2",
>             "gpt-5.2-2025-12-11",
>             "gpt-5.2-chat-latest",
>             "gpt-5.2-pro",
>             "gpt-5.2-pro-2025-12-11",
>             "gpt-5.1",
>             "gpt-5.1-2025-11-13",
>             "gpt-5.1-codex",
>             "gpt-5.1-mini",
>             "gpt-5.1-chat-latest",
>             "gpt-5",
>             "gpt-5-mini",
>             "gpt-5-nano",
>             "gpt-5-2025-08-07",
>             "gpt-5-mini-2025-08-07",
>             "gpt-5-n
- 2026-11-10T17:59:50.472Z · [GitHub · openai/openai-agents-python · code](https://github.com/openai/openai-agents-python/blob/d68961657843c7d81dfc25834484f8aac2957eb3/src/agents/memory/openai_responses_compaction_session.py)
> , history[:], False)
> 
> 
> def _strip_orphaned_assistant_ids(
>     items: list[TResponseInputItem],
> ) -> list[TResponseInputItem]:
>     """Remove ``id`` from assistant messages when their paired reasoning items are missing.
> 
>     Some models (e.g. gpt-5.4) return compacted output that retains assistant
>     message IDs even after stripping the reasoning items those IDs reference.
>     Sending these orphaned IDs back to ``responses.create`` causes a 400 error
>     because the API expects the paired reasoning item for each assistant message
>     ID.  This function detects and removes those orphaned IDs so the compacted
>     history can be used safely.
>     """
>     if not items:
>         return items
> 
>     has_reasoning = any(
>         isinstance(item, dict) and item.get("type") == "reasoning" for item in items
>     )
>     if has_reasoning:
>         return items
> 
>     cleaned: list[TResponseInputIt
Deze codeverwijzing bevestigt geen modelidentificatie die daadwerkelijk wordt gebruikt.
- 2026-11-10T18:00:44.369Z · [GitHub · openai/codex · code](https://github.com/openai/codex/blob/82e6bacb9c6950d3b56cb153847fa80bdd698053/codex-rs/core/src/session/tests.rs)
> ,
>     )
>     .expect("in-memory metrics client")
> }
> 
> #[test]
> fn extension_metrics_preserve_session_metadata_tags() {
>     let metrics = test_metrics_client();
>     let session_telemetry = SessionTelemetry::new(
>         ThreadId::new(),
>         "gpt-5.4",
>         "gpt-5.4",
>         /*account_id*/ None,
>         /*account_email*/ None,
>         Some(TelemetryAuthMode::Chatgpt),
>         "test_originator".to_string(),
>         /*log_user_prompts*/ false,
>         "tty".to_string(),
>         SessionSource::Cli,
>     )
>     .with_metrics_service_name("test_service")
>     .with_metrics(metrics.clone());
>     let extension_metrics = super::extension_metrics::from_session_telemetry(session_telemetry);
> 
>     extension_metrics.histogram(
>         "codex.test.extension",
>         /*value*/ 7,
>         &[
>             ("component", "skills"),
>             ("app.version", "extension-version"),
>             ("
Deze codeverwijzing bevestigt geen modelidentificatie die daadwerkelijk wordt gebruikt.
- 2026-11-10T18:00:44.369Z · [GitHub · openai/codex · code](https://github.com/openai/codex/blob/627b579219d492b5445d6d433d3110eb53e507dc/codex-rs/app-server/tests/suite/v2/external_agent_config.rs)
> root.join(".mcp.json"),
>         r#"{"mcpServers":{"repository-server":{"command":"repository-server"}}}"#,
>     )?;
>     std::fs::write(&global_config, "model = \"gpt-5.4\"\n")?;
> 
>     let home_dir = codex_home.path().display().to_string();
>     let mut mcp = TestAppServer::builder()
>         .with_codex_home(codex_home.path())
>         .without_auto_env()
>         .with_env_overrides(&[("HOME", Some(home_dir.as_str()))])
>         .build_initialized_with_timeout(DEFAULT_TIMEOUT)
>         .awa
Deze codeverwijzing bevestigt geen modelidentificatie die daadwerkelijk wordt gebruikt.
- 2026-11-10T20:40:17.231Z · [GitHub · openai/openai-agents-python · code](https://github.com/openai/openai-agents-python/blob/d68961657843c7d81dfc25834484f8aac2957eb3/src/agents/models/openai_responses.py)
> eturn isinstance(model, str) and model.startswith("computer-use-preview")
> 
>     @classmethod
>     def _is_ga_computer_model(cls, model: str | ChatModel | None) -> bool:
>         return isinstance(model, str) and (
>             model.startswith("gpt-5.4") or model.startswith("gpt-5.5")
>         )
> 
>     @classmethod
>     def resolve_computer_tool_model(
>         cls,
>         *,
>         request_model: str | ChatModel | None,
>         tools: Sequence[Tool] | None,
>     ) -> str | ChatModel | None:
>         if not cls._has_computer_tool(tools):
>             return None
>         return request_model
> 
>     @classmethod
>     def _should_use_preview_computer_tool(
>         cls,
>         *,
>         model: str | ChatModel | None,
>         tool_choice: Literal["auto", "required", "none"] | str | MCPToolChoice | None,
>     ) -> bool:
>         # Choose the computer tool wire shape from the effective request m
- 2026-11-11T17:30:32.898Z · [GitHub · openai/codex · code](https://github.com/openai/codex/blob/e58bf8f5233b51e7cd1679d947e3028c1ed91b06/codex-rs/tui/src/app/startup_prompts.rs)
> ope fallback migration metadata
>     // to the owning provider, since other providers may still support the same model slug.
>     let (target_model, current_name, target_name) = match (model_provider_id, model) {
>         (OPENAI_PROVIDER_ID, "gpt-5.4") => ("gpt-6-sol", "GPT-5.4", "GPT-6 Sol"),
>         (AMAZON_BEDROCK_PROVIDER_ID, "openai.gpt-5.4") => (
>             "openai.gpt-6-sol",
>             "GPT-5.4 on Amazon Bedrock",
>             "GPT-6 Sol on Amazon Bedrock",
>         ),
>         (OPENAI_PROVIDER_ID, "gpt-5.4-mini") => ("gpt-6-luna", "GPT-5.4 Mini", "GPT-6 Luna"),
>         _ => return None,
>     };
>     let availability = if model == "openai.gpt-5.4" {
>         "no longer offered in Codex"
>     } else {
>         "no longer available"
>     };
>     Some(ModelUpgrade {
>         id: target_model.to_string(),
>         migration_config_key: model.to_string(),
>         model_link: None,
>    
- 2026-11-12T18:45:20.401Z · [GitHub · openai/openai-node · code](https://github.com/openai/openai-node/blob/b579bcb3e586d22269ffe6fe504653a0e05acbe8/src/resources/beta/responses/responses.ts)
> replacements.
>    */
>   model:
>     | 'gpt-6-astra'
>     | 'gpt-6.1-sol'
>     | 'gpt-6.1-terra'
>     | 'gpt-6-sol'
>     | 'gpt-6-luna'
>     | 'gpt-5.6-sol'
>     | 'gpt-5.6-terra'
>     | 'gpt-5.6-luna'
>     | 'gpt-5.5'
>     | 'gpt-5.5-2026-04-23'
>     | 'gpt-5.4'
>     | 'gpt-5.4-mini'
>     | 'gpt-5.4-nano'
>     | 'gpt-5.4-mini-2026-03-17'
>     | 'gpt-5.4-nano-2026-03-17'
>     | 'gpt-5.3-chat-latest'
>     | 'gpt-5.2'
>     | 'gpt-5.2-2025-12-11'
>     | 'gpt-5.2-chat-latest'
>     | 'gpt-5.2-pro'
>     | 'gpt-5.2-pro-2025-12-11'
>     | 'gpt-5.1'
>     | 'gpt-5.1-2025-11-13'
>     | 'gpt-5.1-codex'
>     | 'gpt-5.1-mini'
>     | 'gpt-5.1-chat-latest'
>     | 'gpt-5'
>     | 'gpt-5-mini'
>     | 'gpt-5-nano'
>     | 'gpt-5-2025-08-07'
>     | 'gpt-5-mini-2025-08-07'
>     | 'gpt-5-nano-2025-08-07'
>     | 'gpt-5-chat-latest'
>     | 'gpt-4.1'
>     | 'gpt-4.1-mini'
>     | 'gpt-4.1-nano'
>     | 'gpt-4.1-2025-04-14'
>     | 'gpt-4.1-mini-
- 2026-11-13T22:06:17.930Z · [OpenAI · official articles](https://openai.com/index/introducing-gpt-5-5)
> GPT‑5.4 could not
- 2026-11-13T22:47:01.410Z · [OpenAI · official articles](https://openai.com/index/introducing-gpt-5-4)
> GPT‑5.4 was tested with a longer, updated blocklist
**Bevestigd gebruik**
- 2026-11-13T22:47:01.410Z · [OpenAI · official articles · Introducing GPT-5.4](https://openai.com/index/introducing-gpt-5-4)
- 2026-11-13T23:07:16.876Z · [OpenAI · official articles](https://openai.com/index/chatgpt-for-excel)

## Bronlinks

- [editorial](https://alexgetman.com/133/using-gpt-5-6-luna-max-you-get-the-power-of-march-s-flagship-gpt-5-4-xhigh-for-o/)
- [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-5.4)
- [openai-pricing](https://developers.openai.com/api/docs/pricing)
- [openai-codex-changelog](https://developers.openai.com/codex/changelog/#codex-2026-03-05)
- [GitHub · openai/codex · code](https://github.com/openai/codex/blob/627b579219d492b5445d6d433d3110eb53e507dc/codex-rs/app-server/tests/suite/v2/external_agent_config.rs)
- [GitHub · openai/codex · code](https://github.com/openai/codex/blob/82e6bacb9c6950d3b56cb153847fa80bdd698053/codex-rs/core/src/session/tests.rs)
- [GitHub · openai/codex · code](https://github.com/openai/codex/blob/e58bf8f5233b51e7cd1679d947e3028c1ed91b06/codex-rs/tui/src/app/startup_prompts.rs)
- [GitHub · openai/codex · PR](https://github.com/openai/codex/pull/44930)
- [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/memory/openai_responses_compaction_session.py)
- [GitHub · openai/openai-agents-python · code](https://github.com/openai/openai-agents-python/blob/d68961657843c7d81dfc25834484f8aac2957eb3/src/agents/models/openai_responses.py)
- [GitHub · openai/openai-node · code](https://github.com/openai/openai-node/blob/b579bcb3e586d22269ffe6fe504653a0e05acbe8/src/resources/beta/responses/responses.ts)
- [GitHub · openai/openai-python · code](https://github.com/openai/openai-python/blob/0ebd00647f6088fb100b03440c6c4554bbab549d/src/openai/types/beta/beta_responses_client_event.py)
- [truefoundry-azure](https://github.com/truefoundry/models/blob/main/providers/microsoft-foundry/gpt-5.4.yaml)
- [OpenAI · ChatGPT release notes](https://help.openai.com/en/articles/6825453-chatgpt-release-notes)
- [OpenAI · Model release notes](https://help.openai.com/en/articles/9624314-model-release-notes)
- [models.dev · catalogue](https://models.dev/#databricks-gpt-5-4)
- [models.dev · catalogue](https://models.dev/#gpt-5-4)
- [models.dev · catalogue](https://models.dev/#gpt-5.4)
- [models.dev · catalogue](https://models.dev/#gpt-5.4:free)
- [openai-articles](https://openai.com/index/chatgpt-for-excel)
- [openai-articles](https://openai.com/index/introducing-gpt-5-4)
- [openai-articles](https://openai.com/index/introducing-gpt-5-5)
- [OpenCode · discovery](https://opencode.ai/data/openai/gpt-5-4)
- [OpenRouter](https://openrouter.ai/openai/gpt-5.4)
- [OpenRouter](https://openrouter.ai/openai/gpt-5.4:batch)
- [Arena · leaderboards](https://platform.openai.com/docs/models/gpt-5.4)
- [Vercel AI Gateway](https://vercel.com/ai-gateway)
- [VoxelBench · leaderboard](https://voxelbench.ai/leaderboard)

## Signalen

- [GPT-5.4: Catalogusvermelding](https://alexgetman.com/nl/signals/2026/10/21/gpt-5-4/)
- [GPT-5.4: Catalogusvermelding](https://alexgetman.com/nl/signals/2026/09/11/gpt-5-4/)