메인 콘텐츠로 건너뛰기
OpenAI

API 고객을 위한 우선 처리

Fast mode offers reliable, high-speed performance with the flexibility to pay-as-you-go. For our latest frontier model, gpt-5.6-sol, you can access up to 2.5x faster speeds with Fast mode.

By choosing Fast mode, you can unlock:

  • Predictably low latency: Fast mode generates tokens faster and at a more consistent speed than the Standard processing service, even during peak demand.
  • Easy-to-use flexibility: Like Standard processing, Fast mode can be accessed on a flexible, pay-as-you-go basis instead of requiring advance provisioning.

Note: Priority processing was renamed Fast mode on July 30, 2026. You can use either service_tier: priority or service_tier: fast in your API requests.

입력 토큰 100만 개당 가격입력 토큰 100만 개당 가격(캐시됨)출력 토큰 100만 개당 가격가동 시간 SLA3레이턴시 SLA3
GPT-5.6 Sol
Long-Context 제외1
US$10.00US$1.00US$60.0099.9%99% > 80개의 토큰/초2
GPT-5.6 Terra
Long-Context 제외1
US$4.00US$0.40US$24.0099.9%99% > 70개의 토큰/초2
GPT-5.6 Luna
Long-Context 제외1
US$0.40US$0.04US$2.4099.9%99% > 100개의 토큰/초2
GPT-5.5
Long-Context 제외1
US$12.50US$1.250US$75.0099.9%99% > 50개의 토큰/초2
GPT-5.4 mini
Long-Context 제외1
US$1.50US$0.150US$9.0099.9%99% > 100개의 토큰/초2
GPT-5.4
Long-Context 제외1
US$5.00US$0.500US$30.0099.9%99% > 50개의 토큰/초2
GPT-5.2
US$3.50US$0.350US$28.0099.9%99% > 50개의 토큰/초2
GPT-5.1
US$2.50US$0.250US$20.0099.9%99% > 50개의 토큰/초2
GPT-5
US$2.50US$0.250US$20.0099.9%99% > 50개의 토큰/초2
GPT-5 mini
US$0.45US$0.045US$3.6099.9%99% > 80개의 토큰/초2
GPT-5.1 codex
US$2.50US$0.250US$20.0099.9%99% > 50개의 토큰/초2
GPT-5 codex
US$2.50US$0.250US$20.0099.9%99% > 50개의 토큰/초2
GPT-4.1
US$3.50US$0.875US$14.0099.9%99% > 80개의 토큰/초2
GPT-4.1 mini
US$0.70US$0.175US$2.8099.9%99% > 90개의 토큰/초2
GPT-4.1 nano
US$0.20US$0.050US$0.8099.9%99% > 100개의 토큰/초2
GPT-4o
gpt-4o-2024-11-20
gpt-4o-2024-08-06
US$4.25US$2.125US$17.0099.9%99% > 80개의 토큰/초2
gpt-4o-2024-05-13
US$8.75US$26.2599.9%99% > 80개의 토큰/초2
GPT-4o mini
US$0.25US$0.125US$1.0099.9%99% > 90개의 토큰/초2
o3
US$3.50US$0.875US$14.0099.9%99% > 80개의 토큰/초2
o4-mini
US$2.00US$0.500US$8.0099.9%99% > 90개의 토큰/초2
1프롬프트 토큰이 27만 2천 개를 초과할 것으로 예상되는 요청 수
25분마다 p50 요청 레이턴시로 계산됩니다. 기존 엔터프라이즈 계약에 1분마다 p50 요청 레이턴시로 계산되는 레이턴시 SLA가 포함된 고객은 기존의 SLA 역시 계속 적용됩니다.
3Enterprise 고객에게만 적용됩니다

작동 방식

Customers can direct traffic to Fast mode on a per request basis using the existing service_tier parameter, with the option service_tier = "fast".

Tokens served by Fast mode will be billed on a per-token basis, priced at a premium relative to Standard processing rates.

In addition to being configured at the request level, you can also default a project to Fast mode in Project settings > Default Service Tier: Fast. You can still override per request. Selecting Fast in your project settings is equivalent to selecting Priority.

제약사항

  • Fast mode rate limits are shared with other service tiers.
  • In rare cases, rapid increases to your Fast mode Tokens per Minute can lead to hitting ramp rate limits. If you exceed the ramp rate limit, then additional traffic may be sent to Standard processing instead.

Frequently asked questions

가격

모델

속도 제한

신뢰성

정책