U bood nuxurka ugu muhiimsan
OpenAI

Habaynka Mudnaanta leh ee Macaamiisha API

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.

Qiimaha 1M-kii token ee gelintaQiimaha halkii 1M token ee gelinta (cached)Qiimaha halkii 1M ee token ee soo saarkaHelitaanka SLA-ga3Daahitaanka SLA3
GPT-5.6 Sol
ka saartay macnaha guud ee dheer1
US$10.00US$1.00US$60.0099.9%99% > 80 token-yo ilbiriqsigiiba2
GPT-5.6 Terra
ka saartay macnaha guud ee dheer1
US$4.00US$0.40US$24.0099.9%99% > 70 token-yo ilbiriqsigiiba2
GPT-5.6 Luna
ka saartay macnaha guud ee dheer1
US$0.40US$0.04US$2.4099.9%99% > 100 token-yo ilbiriqsigiiba2
GPT-5.5
ka saartay macnaha guud ee dheer1
US$12.50US$1.250US$75.0099.9%99% > 50 token-yo ilbiriqsigiiba2
GPT-5.4 mini
ka saartay macnaha guud ee dheer1
US$1.50US$0.150US$9.0099.9%99% > 100 token-yo ilbiriqsigiiba2
GPT-5.4
ka saartay macnaha guud ee dheer1
US$5.00US$0.500US$30.0099.9%99% > 50 token-yo ilbiriqsigiiba2
GPT-5.2
US$3.50US$0.350US$28.0099.9%99% > 50 token-yo ilbiriqsigiiba2
GPT-5.1
US$2.50US$0.250US$20.0099.9%99% > 50 token-yo ilbiriqsigiiba2
GPT-5
US$2.50US$0.250US$20.0099.9%99% > 50 token-yo ilbiriqsigiiba2
GPT-5 mini
US$0.45US$0.045US$3.6099.9%99% > 80 token-yo ilbiriqsigiiba2
GPT-5.1 codex
US$2.50US$0.250US$20.0099.9%99% > 50 token-yo ilbiriqsigiiba2
GPT-5 codex
US$2.50US$0.250US$20.0099.9%99% > 50 token-yo ilbiriqsigiiba2
GPT-4.1
US$3.50US$0.875US$14.0099.9%99% > 80 token-yo ilbiriqsigiiba2
GPT-4.1 mini
US$0.70US$0.175US$2.8099.9%99% > 90 token-yo ilbiriqsigiiba2
GPT-4.1 nano
US$0.20US$0.050US$0.8099.9%99% > 100 token-yo ilbiriqsigiiba2
GPT-4o
gpt-4o-2024-11-20
gpt-4o-2024-08-06
US$4.25US$2.125US$17.0099.9%99% > 80 token-yo ilbiriqsigiiba2
gpt-4o-2024-05-13
US$8.75US$26.2599.9%99% > 80 token-yo ilbiriqsigiiba2
GPT-4o mini
US$0.25US$0.125US$1.0099.9%99% > 90 token-yo ilbiriqsigiiba2
o3
US$3.50US$0.875US$14.0099.9%99% > 80 token-yo ilbiriqsigiiba2
o4-mini
US$2.00US$0.500US$8.0099.9%99% > 90 token-yo ilbiriqsigiiba2
1Codsiyada waxaa lagu qiyaasay >272K token weydiin ah
2Waxaa loo xisaabiyay sida codsiga p50 oo dib u dhac ah 5 daqiiqo kasta. Macaamiisha leh heshiisyada ganacsi ee jira ee leh SLA-yada dib-u-dhaca ee loo xisaabiyay inay yihiin codsiyada dib-u-dhaca p50 ee ku salaysan daqiiqaddii, SLA-yadii hore ayaa sidoo kale wali khuseeya.
3Tani waxay khusaysaa macaamiisha Ganacsiga oo keliya

Sida ay u shaqeyso

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.

Xaddidaadaha

  • 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

Qiimaynta

Moodooyinka

Xaddidaadaha heerka

Kalsoonida

Xeerarka