跳至主要內容
OpenAI

API 客戶的優先處理服務

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.

每一百萬個輸入權杖的費用每一百萬個輸入權杖的費用 (快取)每一百萬個輸出權杖的費用正常運作時間 SLA3延遲 SLA3
GPT-5.6 Sol
不支援長段文字記憶力解功能1
US$10.00US$1.00US$60.0099.9%每秒 99% > 80 個權杖2
GPT-5.6 Terra
不支援長段文字記憶力解功能1
US$4.00US$0.40US$24.0099.9%每秒 99% > 70 個權杖2
GPT-5.6 Luna
不支援長段文字記憶力解功能1
US$0.40US$0.04US$2.4099.9%每秒 99% > 100 個權杖2
GPT-5.5
不支援長段文字記憶力解功能1
US$12.50US$1.250US$75.0099.9%每秒 99% > 50 個權杖2
GPT-5.4 mini
不支援長段文字記憶力解功能1
US$1.50US$0.150US$9.0099.9%每秒 99% > 100 個權杖2
GPT-5.4
不支援長段文字記憶力解功能1
US$5.00US$0.500US$30.0099.9%每秒 99% > 50 個權杖2
GPT-5.2
US$3.50US$0.350US$28.0099.9%每秒 99% > 50 個權杖2
GPT-5.1
US$2.50US$0.250US$20.0099.9%每秒 99% > 50 個權杖2
GPT-5
US$2.50US$0.250US$20.0099.9%每秒 99% > 50 個權杖2
GPT-5 mini
US$0.45US$0.045US$3.6099.9%每秒 99% > 80 個權杖2
GPT-5.1 codex
US$2.50US$0.250US$20.0099.9%每秒 99% > 50 個權杖2
GPT-5 codex
US$2.50US$0.250US$20.0099.9%每秒 99% > 50 個權杖2
GPT-4.1
US$3.50US$0.875US$14.0099.9%每秒 99% > 80 個權杖2
GPT-4.1 mini
US$0.70US$0.175US$2.8099.9%每秒 99% > 90 個權杖2
GPT-4.1 nano
US$0.20US$0.050US$0.8099.9%每秒 99% > 100 個權杖2
GPT-4o
gpt-4o-2024-11-20
gpt-4o-2024-08-06
US$4.25US$2.125US$17.0099.9%每秒 99% > 80 個權杖2
gpt-4o-2024-05-13
US$8.75US$26.2599.9%每秒 99% > 80 個權杖2
GPT-4o mini
US$0.25US$0.125US$1.0099.9%每秒 99% > 90 個權杖2
o3
US$3.50US$0.875US$14.0099.9%每秒 99% > 80 個權杖2
o4-mini
US$2.00US$0.500US$8.0099.9%每秒 99% > 90 個權杖2
1預估會使用超過 27.2 萬個提示詞 Token 的請求
2以每 5 分鐘為單位,計算第 50 百分位的請求延遲。客戶若已簽訂企業合約,且延遲 SLA 是以每分鐘計算第 50 百分位的請求延遲為準,則原來的 SLA 仍適用。
3僅適用於 Enterprise 方案客戶

運作方式

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.

限制說明

  • 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

定價

模型

速率限制

可靠性

政策