Elaborazione Prioritaria per i clienti 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.
| Prezzo per 1M token di input | Prezzo per 1M token di input (memorizzati nella cache) | Prezzo per 1M token di output | SLA di uptime3 | SLA di latenza3 | |
|---|---|---|---|---|---|
GPT-5.6 Sol esclude il contesto lungo1 | 10,00 USD | 1,00 USD | 60,00 USD | 99,9% | 99% > 80 token al secondo2 |
GPT-5.6 Terra esclude il contesto lungo1 | 4,00 USD | 0,40 USD | 24,00 USD | 99,9% | 99% > 70 token al secondo2 |
GPT-5.6 Luna esclude il contesto lungo1 | 0,40 USD | 0,04 USD | 2,40 USD | 99,9% | 99% > 100 token al secondo2 |
GPT-5.5 esclude il contesto lungo1 | 12,50 USD | 1,250 USD | 75,00 USD | 99,9% | 99% > 50 token al secondo2 |
GPT-5.4 mini esclude il contesto lungo1 | 1,50 USD | 0,150 USD | 9,00 USD | 99,9% | 99% > 100 token al secondo2 |
GPT-5.4 esclude il contesto lungo1 | 5,00 USD | 0,500 USD | 30,00 USD | 99,9% | 99% > 50 token al secondo2 |
GPT-5.2 | 3,50 USD | 0,350 USD | 28,00 USD | 99,9% | 99% > 50 token al secondo2 |
GPT-5.1 | 2,50 USD | 0,250 USD | 20,00 USD | 99,9% | 99% > 50 token al secondo2 |
GPT-5 | 2,50 USD | 0,250 USD | 20,00 USD | 99,9% | 99% > 50 token al secondo2 |
GPT-5 mini | 0,45 USD | 0,045 USD | 3,60 USD | 99,9% | 99% > 80 token al secondo2 |
GPT-5.1 codex | 2,50 USD | 0,250 USD | 20,00 USD | 99,9% | 99% > 50 token al secondo2 |
GPT-5 codex | 2,50 USD | 0,250 USD | 20,00 USD | 99,9% | 99% > 50 token al secondo2 |
GPT-4.1 | 3,50 USD | 0,875 USD | 14,00 USD | 99,9% | 99% > 80 token al secondo2 |
GPT-4.1 mini | 0,70 USD | 0,175 USD | 2,80 USD | 99,9% | 99% > 90 token al secondo2 |
GPT-4.1 nano | 0,20 USD | 0,050 USD | 0,80 USD | 99,9% | 99% > 100 token al secondo2 |
GPT-4o gpt-4o-2024-11-20 gpt-4o-2024-08-06 | 4,25 USD | 2,125 USD | 17,00 USD | 99,9% | 99% > 80 token al secondo2 |
gpt-4o-2024-05-13 | 8,75 USD | — | 26,25 USD | 99,9% | 99% > 80 token al secondo2 |
GPT-4o mini | 0,25 USD | 0,125 USD | 1,00 USD | 99,9% | 99% > 90 token al secondo2 |
o3 | 3,50 USD | 0,875 USD | 14,00 USD | 99,9% | 99% > 80 token al secondo2 |
o4-mini | 2,00 USD | 0,500 USD | 8,00 USD | 99,9% | 99% > 90 token al secondo2 |
Come funziona
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.
Limiti
- 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.