Vorrangige Verarbeitung für API-Kunden
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.
| Preis pro 1 Million Eingabe-Tokens | Preis pro 1 Million Eingabe-Tokens (zwischengespeichert) | Preis pro 1 Million Output-Tokens | Uptime SLA3 | Latenz-SLA (Service Level Agreement)3 | |
|---|---|---|---|---|---|
GPT-5.6 Sol schließt Langzeit-Kontext aus1 | 10,00 $ | 1,00 $ | 60,00 $ | 99,9 % | 99 % > 80 Tokens pro Sekunde2 |
GPT-5.6 Terra schließt Langzeit-Kontext aus1 | 4,00 $ | 0,40 $ | 24,00 $ | 99,9 % | 99 % > 70 Tokens pro Sekunde2 |
GPT-5.6 Luna schließt Langzeit-Kontext aus1 | 0,40 $ | 0,04 $ | 2,40 $ | 99,9 % | 99 % > 100 Tokens pro Sekunde2 |
GPT-5.5 schließt Langzeit-Kontext aus1 | 12,50 $ | 1,250 $ | 75,00 $ | 99,9 % | 99 % > 50 Tokens pro Sekunde2 |
GPT-5.4 mini schließt Langzeit-Kontext aus1 | 1,50 $ | 0,150 $ | 9,00 $ | 99,9 % | 99 % > 100 Tokens pro Sekunde2 |
GPT-5.4 schließt Langzeit-Kontext aus1 | 5,00 $ | 0,500 $ | 30,00 $ | 99,9 % | 99 % > 50 Tokens pro Sekunde2 |
GPT-5.2 | 3,50 $ | 0,350 $ | 28,00 $ | 99,9 % | 99 % > 50 Tokens pro Sekunde2 |
GPT-5.1 | 2,50 $ | 0,250 $ | 20,00 $ | 99,9 % | 99 % > 50 Tokens pro Sekunde2 |
GPT-5 | 2,50 $ | 0,250 $ | 20,00 $ | 99,9 % | 99 % > 50 Tokens pro Sekunde2 |
GPT-5 mini | 0,45 $ | 0,045 $ | 3,60 $ | 99,9 % | 99 % > 80 Tokens pro Sekunde2 |
GPT-5.1 codex | 2,50 $ | 0,250 $ | 20,00 $ | 99,9 % | 99 % > 50 Tokens pro Sekunde2 |
GPT-5 codex | 2,50 $ | 0,250 $ | 20,00 $ | 99,9 % | 99 % > 50 Tokens pro Sekunde2 |
GPT-4.1 | 3,50 $ | 0,875 $ | 14,00 $ | 99,9 % | 99 % > 80 Tokens pro Sekunde2 |
GPT-4.1 mini | 0,70 $ | 0,175 $ | 2,80 $ | 99,9 % | 99 % > 90 Tokens pro Sekunde2 |
GPT-4.1 nano | 0,20 $ | 0,050 $ | 0,80 $ | 99,9 % | 99 % > 100 Tokens pro Sekunde2 |
GPT-4o gpt-4o-2024-11-20 gpt-4o-2024-08-06 | 4,25 $ | 2,125 $ | 17,00 $ | 99,9 % | 99 % > 80 Tokens pro Sekunde2 |
gpt-4o-2024-05-13 | 8,75 $ | — | 26,25 $ | 99,9 % | 99 % > 80 Tokens pro Sekunde2 |
GPT-4o mini | 0,25 $ | 0,125 $ | 1,00 $ | 99,9 % | 99 % > 90 Tokens pro Sekunde2 |
o3 | 3,50 $ | 0,875 $ | 14,00 $ | 99,9 % | 99 % > 80 Tokens pro Sekunde2 |
o4-mini | 2,00 $ | 0,500 $ | 8,00 $ | 99,9 % | 99 % > 90 Tokens pro Sekunde2 |
Funktionsweise
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.
Einschränkungen
- 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.