Gå til hovedindhold
OpenAI

Prioritetsbehandling for API-kunder

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.

Pris pr. 1 mio. input-tokensPris pr. 1 mio. input-tokens (cachelagret)Pris pr. 1 mio. output-tokensServiceniveauaftale for oppetid3Serviceniveauaftale for latenstid3
GPT-5.6 Sol
udelukker lang kontekst1
10,00 US$1,00 US$60,00 US$99,9 %99 % > 80 tokens pr. sekund2
GPT-5.6 Terra
udelukker lang kontekst1
4,00 US$0,40 US$24,00 US$99,9 %99 % > 70 tokens pr. sekund2
GPT-5.6 Luna
udelukker lang kontekst1
0,40 US$0,04 US$2,40 US$99,9 %99 % > 100 tokens pr. sekund2
GPT-5.5
udelukker lang kontekst1
12,50 US$1,250 US$75,00 US$99,9 %99 % > 50 tokens pr. sekund2
GPT-5.4 mini
udelukker lang kontekst1
1,50 US$0,150 US$9,00 US$99,9 %99 % > 100 tokens pr. sekund2
GPT-5.4
udelukker lang kontekst1
5,00 US$0,500 US$30,00 US$99,9 %99 % > 50 tokens pr. sekund2
GPT-5.2
3,50 US$0,350 US$28,00 US$99,9 %99 % > 50 tokens pr. sekund2
GPT-5.1
2,50 US$0,250 US$20,00 US$99,9 %99 % > 50 tokens pr. sekund2
GPT-5
2,50 US$0,250 US$20,00 US$99,9 %99 % > 50 tokens pr. sekund2
GPT-5 mini
0,45 US$0,045 US$3,60 US$99,9 %99 % > 80 tokens pr. sekund2
GPT-5.1 codex
2,50 US$0,250 US$20,00 US$99,9 %99 % > 50 tokens pr. sekund2
GPT-5 codex
2,50 US$0,250 US$20,00 US$99,9 %99 % > 50 tokens pr. sekund2
GPT-4.1
3,50 US$0,875 US$14,00 US$99,9 %99 % > 80 tokens pr. sekund2
GPT-4.1 mini
0,70 US$0,175 US$2,80 US$99,9 %99 % > 90 tokens pr. sekund2
GPT-4.1 nano
0,20 US$0,050 US$0,80 US$99,9 %99 % > 100 tokens pr. sekund2
GPT-4o
gpt-4o-2024-11-20
gpt-4o-2024-08-06
4,25 US$2,125 US$17,00 US$99,9 %99 % > 80 tokens pr. sekund2
gpt-4o-2024-05-13
8,75 US$26,25 US$99,9 %99 % > 80 tokens pr. sekund2
GPT-4o mini
0,25 US$0,125 US$1,00 US$99,9 %99 % > 90 tokens pr. sekund2
o3
3,50 US$0,875 US$14,00 US$99,9 %99 % > 80 tokens pr. sekund2
o4-mini
2,00 US$0,500 US$8,00 US$99,9 %99 % > 90 tokens pr. sekund2
1Anmodninger anslået til >272.000 prompt-tokens
2Beregnet som p50 anmodningslatenstid pr. 5 minutter. For kunder med eksisterende virksomhedsaftaler, der har serviceniveauaftaler for latenstid beregnet som p50 anmodningslatens på minutbasis, gælder de tidligere serviceniveauaftaler også stadig.
3Dette gælder kun Enterprise-kunder

Sådan fungerer det

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.

Begrænsninger

  • 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

Priser

Modeller

Brugsgrænser

Driftssikkerhed

Politikker