openai/gpt-5.6-luna
The efficient GPT-5.6 model for high-volume assistants, extraction, routing, and coding tasks. It keeps the 1.05M-token context window, vision, tools, configurable reasoning, persisted reasoning, and explicit prompt caching at the lowest price in the family.
Source : openai_2026_08_luna_x0.30 · Vérifié le 2026-08-29
Lecture cache $0.006/M · Écriture cache $0.075/M
| Palier | Entrée | Lecture cache | Écriture cache | Sortie |
|---|---|---|---|---|
| Standard ≤272K | $0.06 | $0.006 | $0.075 | $0.36 |
| Standard >272K | $0.12 | $0.012 | $0.15 | $0.54 |
Utilisez l'un ou l'autre des IDs pour appeler ce modèle via l'API.
openai/gpt-5.6-lunaRemplacez le placeholder ONEHOP_KEY par votre API key. Créer →
from openai import OpenAI
client = OpenAI(
base_url="https://api.onehop.ai/v1",
api_key="<ONEHOP_KEY>",
)
completion = client.chat.completions.create(
model="openai/gpt-5.6-luna",
messages=[{"role": "user", "content": "What is the meaning of life?"}],
)
print(completion.choices[0].message.content)12 129 requêtes · 30 derniers jours