Alex GetmanMga maagang senyal sa AI
FIL

GPT-5.4

OpenAI

Inilabas Na-update
Context window
1M
1,050,000 token
Pinakamahabang output
128K
128,000 token
Input / Output
teksto, larawan → teksto

Takdang panahon

  1. · Magagamit sa API · link sa ebidensiya · link sa ebidensiya · link sa ebidensiya
  2. · Update sa produkto · link sa ebidensiya
Presyo ng input / output · USD / 1 milyong token
ModeloMga link sa ebidensiyaPresyo ng input / output
gpt-5.4
batch · long context
openai
Hindi available ang ruta ng API
$2.50 (Input > 272,000 token) / $11.25 (Input > 272,000 token)
gpt-5.4
batch · short context
openai
Hindi available ang ruta ng API
$1.25 (Input ≤ 272,000 token) / $7.50 (Input ≤ 272,000 token)
gpt-5.4
fast · short context
openai
Hindi available ang ruta ng API
$5.00 (Input ≤ 272,000 token) / $30.00 (Input ≤ 272,000 token)
gpt-5.4
flex · long context
openai
Hindi available ang ruta ng API
$2.50 (Input > 272,000 token) / $11.25 (Input > 272,000 token)
gpt-5.4
flex · short context
openai
Hindi available ang ruta ng API
$1.25 (Input ≤ 272,000 token) / $7.50 (Input ≤ 272,000 token)
gpt-5.4
standard · long context
openai
Hindi available ang ruta ng API
$5.00 (Input > 272,000 token) / $22.50 (Input > 272,000 token)
gpt-5.4
standard · short context
openai
Hindi available ang ruta ng API
$2.50 (Input ≤ 272,000 token) / $15.00 (Input ≤ 272,000 token)
  1. · Mga link sa ebidensiya · OpenAI · official articles
  2. · Kumpirmadong paggamit · OpenAI · official articles · Introducing GPT-5.4
  3. · Mga link sa ebidensiya · OpenAI · official articles
    Sipi
    GPT‑5.4 was tested with a longer, updated blocklist
  4. · Mga link sa ebidensiya · OpenAI · official articles
    Sipi
    GPT‑5.4 could not
  5. · Pagkakalista sa katalogo · GitHub · openai/openai-node · code
    Sipi
    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-
  6. · Pagkakalista sa katalogo · GitHub · openai/codex · code
    Sipi
    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,
  7. · Pagkakalista sa katalogo · GitHub · openai/openai-agents-python · code
    Sipi
    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
  8. · Pagkakalista sa katalogo · GitHub · openai/codex · code
    Sipi
    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

    Hindi pinatutunayan ng pagbanggit na ito sa code ang isang ginagamit na identifier ng modelo.

  9. · Pagkakalista sa katalogo · GitHub · openai/codex · code
    Sipi
    , ) .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"), ("

    Hindi pinatutunayan ng pagbanggit na ito sa code ang isang ginagamit na identifier ng modelo.

  10. · Pagkakalista sa katalogo · GitHub · openai/openai-agents-python · code
    Sipi
    , 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

    Hindi pinatutunayan ng pagbanggit na ito sa code ang isang ginagamit na identifier ng modelo.

  11. · Pagkakalista sa katalogo · GitHub · openai/openai-python · code
    Sipi
    -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
  12. · Pagkakalista sa katalogo · GitHub · openai/openai-agents-js · code
    Sipi
    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',
  13. · Mga link sa ebidensiya · OpenAI · Model release notes
    Sipi
    GPT‑5.4 Thinking also has improved context window management that supports its ability to think for longer
  14. · Mga link sa ebidensiya · OpenAI · Codex changelog
    Sipi
    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
  15. · Mga link sa ebidensiya · OpenAI · ChatGPT release notes
    Sipi
    GPT‑5.4 Thinking also has improved context window management that supports its ability to think for longer
  16. · Mga link sa ebidensiya · GitHub · openai/codex · PR
    Sipi
    #44930 Embed friendly instructions in bundled GPT-5.4 and GPT-5.5
  17. · Mga post ni Alex · Alex Getman
    Sipi
    Using GPT 5.6 Luna Max, you get the power of March’s flagship GPT 5.4 xhigh for one thirteenth of its price.

Mga senyal 2

Mga espesipikasyon

Ang GPT-5.4 ay isang modelo mula sa OpenAI, na inilabas noong 2026-03-05. Ang context window ay 1,050,000 token. Ang pinakamahabang output ay 128,000 token.

Context window
1,050,000
Pinakamahabang output
128,000
Input
teksto · larawan
Output
teksto

Mga tanong

Gaano kalaki ang context window ng GPT-5.4?

Ang context window ay 1,050,000 token. Ang pinakamahabang output ay 128,000 token.

Kailan inilabas ang GPT-5.4?

Noong 2026-03-05.