openai/gpt-6-astra
GPT-6 Astra is OpenAI's new flagship, built for the hardest reasoning, coding, and long-running agent work. It takes text and image input, holds a 1.05M-token context window (922K max input), writes up to 128K output tokens, and exposes five reasoning-effort levels from low through max. Prompt caching is supported, and cache reads bill at one tenth of input.
Source : openai_2026_10_gpt_x0.15 · Vérifié le 2026-10-12
Lecture cache $0.15/M · Écriture cache $1.875/M
| Palier | Entrée | Lecture cache | Écriture cache | Sortie |
|---|---|---|---|---|
| Standard ≤272K | $1.5 | $0.15 | $1.875 | $7.5 |
| Standard >272K | $3 | $0.3 | $3.75 | $11.25 |
Utilisez l'un ou l'autre des IDs pour appeler ce modèle via l'API.
openai/gpt-6-astraYou can use these names directly in the request model field.
Remplacez 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-6-astra",
messages=[{"role": "user", "content": "What is the meaning of life?"}],
)
print(completion.choices[0].message.content)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↑
The fastest, lowest-cost GPT-6 for high-volume, well-defined tasks.
$0.03/M↓ · $0.15/M↑
18 255 requêtes · 30 derniers jours