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.
來源：openai_x0.05 · 核驗於 2026-07-10
快取讀取 $0.005/M · 快取寫入 $0.0625/M
| 檔位 | 輸入 | 快取讀取 | 快取寫入 | 輸出 |
|---|---|---|---|---|
| Standard ≤272K | $0.05 | $0.005 | $0.0625 | $0.3 |
| Standard >272K | $0.1 | $0.01 | $0.125 | $0.45 |
API 呼叫時用任一 ID 都可以。
openai/gpt-5.6-luna把 ONEHOP_KEY 佔位符替換為你的 API Key。 建立 →
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)OpenAI's flagship GPT-5.6 for the hardest reasoning, coding, and agentic work.
$0.25/M↓ · $1.5/M↑
Balanced GPT-5.6 quality and cost for production workloads.
$0.125/M↓ · $0.75/M↑
OpenAI GPT-5.5 — flagship, 1M context, top reasoning & agentic coding.
$0.5/M↓ · $3/M↑
OpenAI GPT-5.4 — strong general model, 1M context, lower cost than 5.5.
$0.25/M↓ · $1.5/M↑
OpenAI GPT-5.4 mini — fast, cheapest GPT-5 text route.
$0.075/M↓ · $0.45/M↑