openai/gpt-6-luna
GPT-6 Luna is the lightweight model in the GPT-6 family and its lowest-cost option, built for high-volume work with a clear goal — summarization, extraction, routing, and straightforward Q&A. It keeps the 1.05M-token context window (922K max input), image input, tools, and reasoning effort from none through max. Prompt caching is supported, and cache reads bill at one tenth of input.
Kaynak: openai_2026_09_gpt6_g6l_x0.30 · Doğrulandı: 2026-09-23
Cache okuma $0.003/M · Cache yazma $0.0375/M
| Kademe | Girdi | Cache okuma | Cache yazma | Çıktı |
|---|---|---|---|---|
| Standard ≤272K | $0.03 | $0.003 | $0.0375 | $0.15 |
| Standard >272K | $0.06 | $0.006 | $0.075 | $0.225 |
API çağrısında her iki ID de kullanılabilir.
openai/gpt-6-lunaONEHOP_KEY yer tutucusunu API key'inizle değiştirin. Oluşturun →
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-6-luna",
messages=[{"role": "user", "content": "What is the meaning of life?"}],
)
print(completion.choices[0].message.content)OpenAI's new flagship — the strongest reasoning, coding, and agentic model in the GPT line.
$1.5/M↓ · $7.5/M↑
The balanced GPT-6 for interactive and agentic coding — near-Astra reliability at a fraction of the price.
$0.3/M↓ · $1.5/M↑
The upgraded GPT-6 Sol — near-Astra agentic coding and computer use, with cached input at 5% of the input price.
$0.3/M↓ · $1.5/M↑
Son 30 günde 3.625 istek