GPT-5.6 Luna
OpenAI
- 컨텍스트 창
- 1M 1,050,000 토큰
- 최대 출력
- 128K 128,000 토큰
- 입력 / 출력
- 텍스트, 이미지 → 텍스트
API 요금
USD / 토큰 100만 개
| 입력 | 출력 | 캐시 입력 |
|---|---|---|
|
|
|
타임라인
- · API 제공 · 근거 링크
입력/출력 가격 · USD / 토큰 100만 개
| 모델 | 근거 링크 | 입력/출력 가격 |
|---|---|---|
gpt-5.6-lunabatch · long context | openai API 경로를 사용할 수 없음 | $0.20 (입력 > 272,000 토큰) / $0.90 (입력 > 272,000 토큰) |
gpt-5.6-lunabatch · short context | openai API 경로를 사용할 수 없음 | $0.10 (입력 ≤ 272,000 토큰) / $0.60 (입력 ≤ 272,000 토큰) |
gpt-5.6-lunafast · long context | openai API 경로를 사용할 수 없음 | $0.80 (입력 > 272,000 토큰) / $3.60 (입력 > 272,000 토큰) |
gpt-5.6-lunafast · short context | openai API 경로를 사용할 수 없음 | $0.40 (입력 ≤ 272,000 토큰) / $2.40 (입력 ≤ 272,000 토큰) |
gpt-5.6-lunaflex · long context | openai API 경로를 사용할 수 없음 | $0.20 (입력 > 272,000 토큰) / $0.90 (입력 > 272,000 토큰) |
gpt-5.6-lunaflex · short context | openai API 경로를 사용할 수 없음 | $0.10 (입력 ≤ 272,000 토큰) / $0.60 (입력 ≤ 272,000 토큰) |
gpt-5.6-lunastandard · long context | openai API 경로를 사용할 수 없음 | $0.40 (입력 > 272,000 토큰) / $1.80 (입력 > 272,000 토큰) |
gpt-5.6-lunastandard · short context | openai API 경로를 사용할 수 없음 | $0.20 (입력 ≤ 272,000 토큰) / $1.20 (입력 ≤ 272,000 토큰) |
gpt-5.6-lunastandard · 텍스트 | opencode-go | $0.20 / $1.20 |
openai/gpt-5.6-luna-prostandard | openrouter | $0.20 / $1.20 |
openai/gpt-5.6-luna-pro:batchbatch | openrouter | $0.10 / $0.60 |
- · 사용 확인 · OpenAI · official articles · How we detect frontier model misalignment
- · 카탈로그 등록 · GitHub · openai/openai-node · code
발췌
ai.com/api/docs/deprecations for details and * recommended 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' | 'gp
- · 카탈로그 등록 · GitHub · openai/openai-agents-python · code
발췌
""" model: str | Model | None = None """The model implementation to use when invoking the LLM. By default, if not set, the agent will use the default model configured in `agents.models.get_default_model()` (currently "gpt-5.6-luna"). """ model_settings: ModelSettings = field(default_factory=_default_agent_model_settings) """Configures model-specific tuning parameters (e.g. temperature, top_p). Accepts a ``ModelSettings`` instance or a dictionary containing its fields. """ input_guardrails: list[InputGuardrail[TContext]] = field(default_factory=list) """A list of checks that run in parallel to the agent's execution, before generating a response. Runs only if the agent is the first agent in the chain. """ output_guardrails: list[OutputGuardrail[TContext]] = field(default_factory=list) """A list of checks that run
- · 카탈로그 등록 · GitHub · openai/codex · code
발췌
").plan_type("pro"), AuthCredentialsStoreMode::File, )?; let config = load_default_config_for_test(&codex_home).await; let models = [MODEL, "gpt-5.6-luna", "gpt-6.1-sol"] .into_iter() .map(|slug| { let mut info = codex_core::test_support::construct_model_info_offline(slug, &config); if slug == MODEL { info.auto_review_model_override = Some("gpt-6.1-sol".to_owned()); } info })
이 코드 참조는 실제로 사용되는 모델 식별자를 입증하지 않습니다.
- · 카탈로그 등록 · GitHub · openai/codex · code
발췌
se super::BedrockEndpoint; const GPT_5_BEDROCK_CONTEXT_WINDOW: i64 = 272_000; const GPT_5_6_SOL_OPENAI_MODEL_ID: &str = "gpt-5.6-sol"; const GPT_5_6_TERRA_OPENAI_MODEL_ID: &str = "gpt-5.6-terra"; const GPT_5_6_LUNA_OPENAI_MODEL_ID: &str = "gpt-5.6-luna"; const GPT_6_1_SOL_OPENAI_MODEL_ID: &str = "gpt-6.1-sol"; const GPT_6_1_TERRA_OPENAI_MODEL_ID: &str = "gpt-6.1-terra"; const GPT_6_SOL_OPENAI_MODEL_ID: &str = "gpt-6-sol"; const GPT_6_LUNA_OPENAI_MODEL_ID: &str = "gpt-6-luna"; const GPT_6_ASTRA_OPENAI_MODEL_ID: &str = "gpt-6-astra"; const GPT_5_5_OPENAI_MODEL_ID: &str = "gpt-5.5"; pub(crate) fn static_model_catalog() -> ModelsResponse { let catalog = ModelsResponse { models: vec![ bedrock_model( bundled_openai_model(GPT_6_1_SOL_OPENAI_MODEL_ID), AMAZON_BEDROCK_GPT_6_1_SOL_MODEL_ID, "GPT-6.1 Sol",
- · 카탈로그 등록 · GitHub · openai/openai-agents-python · code
발췌
#third-party-adapters) | ## OpenAI モデル {#openai-models} OpenAI のみを使用するほとんどのアプリでは、デフォルトの OpenAI プロバイダーで文字列のモデル名を使用し、Responses モデル経路を維持する方法を推奨します。 [`Agent`][agents.agent.Agent] でモデルを指定しない場合、Agents SDK はコスト重視で大量処理を行うエージェントワークフロー向けに、デフォルトで [`gpt-5.6-luna`](https://developers.openai.com/api/docs/models/gpt-5.6-luna) を `reasoning.effort="none"` および `verbosity="low"` とともに使用します。最先端の能力が必要なアプリケーションでは、`model="gpt-5.6-sol"` を明示的に設定し、ワークロードに適した `model_settings` を選択できます。 `gpt-5.6-sol` などの別のモデルへ切り替える場合、エージェントを設定する方法は 2 つあります。 ### デフォルトモデル {#default-model} まず、カスタムモデルを設定していないすべてのエージェントで特定のモデルを一貫して使用する場合は、エージェントを実行する前に `OPENAI_DEFAULT_MODEL` 環境変数を設定します。 ```bash export OPENAI_DEFAULT_MODEL=gpt-5.6-sol python3 my_awesome_agent.py ``` 次に、`RunConfig` を使用して、実行単位のデフォルトモデルを設定できます。エージェントにモデルを設定していない場合、この実行のモデルが使用されます。 ```python from agents import Agent, RunConfig, Runner agent = Agent( name="
이 코드 참조는 실제로 사용되는 모델 식별자를 입증하지 않습니다.
- · 카탈로그 등록 · GitHub · openai/openai-python · code
발췌
" model: Union[ Literal[ "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",
- · 카탈로그 등록 · GitHub · openai/openai-agents-js · code
발췌
t5ReasoningSettingsRequired(getDefaultModel()); } /** * Returns the default model name. */ export function getDefaultModel(): string { const env = loadEnv(); return ( env[OPENAI_DEFAULT_MODEL_ENV_VARIABLE_NAME]?.toLowerCase() ?? 'gpt-5.6-luna' ); } /** * Returns the default model settings. * GPT-5-and-newer reasoning models receive model-specific defaults when known. * Otherwise, returns the legacy default model settings. */ export function getDefaultModelSettings(model?: string): ModelSettings { const _model = model ?? getDefaultModel(); if (isGpt5OrNewerReasoningModel(_model)) { const effort = getDefaultReasoningEffort(_model); if (effort !== undefined) { return { reasoning: { effort }, text: { verbosity: 'low' }, }; } return { // Keep the shared text verbosity default, but omit reasoning.effort for //
- · 근거 링크 · OpenAI · ChatGPT release notes
발췌
GPT‑5.6 Luna will become the default model for Free and Go users this week
- · Alex의 게시물 · Alex Getman
발췌
GPT-6 Luna may already be in A/B testing. Some GPT-5.6 Luna requests are being served as GPT-6 Luna behind the scenes.
- · Alex의 게시물 · Alex Getman
발췌
⚡️ OpenAI added Luna Reserve after you hit your usage limits The official docs now mention Luna Reserve. Selected Plus and Pro accounts can keep working in Codex and ChatGPT Work with GPT 5.6 Luna after hitting their regular usage limit. Luna Reserve has its own separate limit and isn't available to everyone yet.
- · Alex의 게시물 · Alex Getman
발췌
GPT 5.6 Luna is now a native subagent It can now work alongside Sol and Terra. Until now, Luna was on the previous subagent system, so users had to rely on workarounds to plug it in.
- · Alex의 게시물 · Alex Getman
발췌
Over the last few days, I burned through around 1.5 billion tokens using GPT-5.6 Luna. At first, I ran it on Max reasoning because that’s what everyone was recommending. Later I switched to xHigh. Max costs about twice as much as xHigh and, from what I can tell, also takes about twice as long to think. My main takeaway is that the model is genuinely very good. For short and medium tasks, I often had Claude Opus 5 double check Luna’s work, and most of the time it agreed with the result. Longer tasks are a different story. Luna can overthink things, lose track of what it was doing at the beginning, handle the middle well, and then fail to finish the last part properly. On these longer task
- · Alex의 게시물 · Alex Getman
발췌
⚡️ GPT 5.6 Luna is becoming the default model for ChatGPT Free and Go users Starting next week, it will also come with unlimited text chats and a new Think button for harder questions.
- · Alex의 게시물 · Alex Getman
발췌
⚡️ Alibaba released Qwen 3.8 Max The new 2.4T parameter flagship benchmarks in the same league as GPT-5.6 Sol, Claude Opus 4.8 and Fable 5. API pricing is $2/M input and $6/M output, roughly half the cost of GPT-5.6 Terra and Claude Sonnet. Now it’s up to users to see whether Qwen can beat DeepSeek-V4-Flash and GPT-5.6 Luna on price to performance.
- · Alex의 게시물 · Alex Getman
발췌
Yesterday GPT 5.6 Luna pushed the Pareto frontier for intelligence and cost. Today DeepSeek V4 Flash did it again and pushed it even further.
- · Alex의 게시물 · Alex Getman
발췌
Using GPT 5.6 Luna Max, you get the power of March’s flagship GPT 5.4 xhigh for one thirteenth of its price.
시그널 2
사양
GPT-5.6 Luna: OpenAI의 AI 모델, 출시일 2026-07-09. 컨텍스트 윈도는 1,050,000 토큰입니다. 최대 출력은 128,000 토큰입니다. 토큰 100만 개당 요금은 입력 $0.20, 출력 $1.20입니다.
- 컨텍스트 창
- 1,050,000
- 최대 출력
- 128,000
- 입력
- 텍스트 · 이미지
- 출력
- 텍스트
- 입력 · USD / 토큰 100만 개
- $0.20
- 출력 · USD / 토큰 100만 개
- $1.20
- 캐시 입력 · USD / 토큰 100만 개
- $0.02
자주 묻는 질문
GPT-5.6 Luna의 컨텍스트 창 크기는 얼마인가요?
컨텍스트 윈도는 1,050,000 토큰입니다. 최대 출력은 128,000 토큰입니다.
GPT-5.6 Luna의 가격은 얼마인가요?
토큰 100만 개당 요금은 입력 $0.20, 출력 $1.20입니다. 캐시 입력은 100만 개당 $0.02입니다.
GPT-5.6 Luna의 출시일은 언제인가요?
2026-07-09.