Prioritāra apstrāde API klientiem
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.
| Cena par 1 miljonu ievades tekstvienību | Cena par 1 miljonu ievades tekstvienību (kešatmiņā) | Cena par 1<br/>miljonu izvades tekstvienību | Darbspējas laika pakalpojumu līmeņa nolīgums (SLA)3 | Latentuma pakalpojumu līmeņa nolīgums3 | |
|---|---|---|---|---|---|
GPT-5.6 Sol izslēdz garo kontekstu1 | 10,00 $ | 1,00 $ | 60,00 $ | 99,9% | 99% > 80 tokeni sekundē2 |
GPT-5.6 Terra izslēdz garo kontekstu1 | 4,00 $ | 0,40 $ | 24,00 $ | 99,9% | 99% > 70 tokeni sekundē2 |
GPT-5.6 Luna izslēdz garo kontekstu1 | 0,40 $ | 0,04 $ | 2,40 $ | 99,9% | 99% > 100 tokeni sekundē2 |
GPT-5.5 izslēdz garo kontekstu1 | 12,50 $ | 1,250 $ | 75,00 $ | 99,9% | 99% > 50 tokeni sekundē2 |
GPT-5.4 mini izslēdz garo kontekstu1 | 1,50 $ | 0,150 $ | 9,00 $ | 99,9% | 99% > 100 tokeni sekundē2 |
GPT-5.4 izslēdz garo kontekstu1 | 5,00 $ | 0,500 $ | 30,00 $ | 99,9% | 99% > 50 tokeni sekundē2 |
GPT-5.2 | 3,50 $ | 0,350 $ | 28,00 $ | 99,9% | 99% > 50 tokeni sekundē2 |
GPT-5.1 | 2,50 $ | 0,250 $ | 20,00 $ | 99,9% | 99% > 50 tokeni sekundē2 |
GPT-5 | 2,50 $ | 0,250 $ | 20,00 $ | 99,9% | 99% > 50 tokeni sekundē2 |
GPT-5 mini | 0,45 $ | 0,045 $ | 3,60 $ | 99,9% | 99% > 80 tokeni sekundē2 |
GPT-5.1 codex | 2,50 $ | 0,250 $ | 20,00 $ | 99,9% | 99% > 50 tokeni sekundē2 |
GPT-5 codex | 2,50 $ | 0,250 $ | 20,00 $ | 99,9% | 99% > 50 tokeni sekundē2 |
GPT-4.1 | 3,50 $ | 0,875 $ | 14,00 $ | 99,9% | 99% > 80 tokeni sekundē2 |
GPT-4.1 mini | 0,70 $ | 0,175 $ | 2,80 $ | 99,9% | 99% > 90 tokeni sekundē2 |
GPT-4.1 nano | 0,20 $ | 0,050 $ | 0,80 $ | 99,9% | 99% > 100 tokeni sekundē2 |
GPT-4o gpt-4o-2024-11-20 gpt-4o-2024-08-06 | 4,25 $ | 2,125 $ | 17,00 $ | 99,9% | 99% > 80 tokeni sekundē2 |
gpt-4o-2024-05-13 | 8,75 $ | — | 26,25 $ | 99,9% | 99% > 80 tokeni sekundē2 |
GPT-4o mini | 0,25 $ | 0,125 $ | 1,00 $ | 99,9% | 99% > 90 tokeni sekundē2 |
o3 | 3,50 $ | 0,875 $ | 14,00 $ | 99,9% | 99% > 80 tokeni sekundē2 |
o4-mini | 2,00 $ | 0,500 $ | 8,00 $ | 99,9% | 99% > 90 tokeni sekundē2 |
Kā tas darbojas
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.
Ierobežojumi.
- 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.