google/gemini-3.1-pro-preview
Google's GA flagship model. Ranks #1 on 12 of 18 tracked benchmarks. 2x+ reasoning improvement over Gemini 3 Pro. 1M-token context with strong coding, math, and multimodal input. Best for complex reasoning, advanced coding pipelines, and research-grade tasks.
Source : gemini_x0.5 · Vérifié le 2026-06-05
Lecture cache $0.1/M · Écriture cache —/M
| Palier | Entrée | Lecture cache | Écriture cache | Sortie |
|---|---|---|---|---|
| Standard ≤200K | $1 | $0.1 | — | $6 |
| Standard >200K | $2 | $0.2 | — | $9 |
Utilisez l'un ou l'autre des IDs pour appeler ce modèle via l'API.
google/gemini-3.1-pro-previewRemplacez 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="google/gemini-3.1-pro-preview",
messages=[{"role": "user", "content": "What is the meaning of life?"}],
)
print(completion.choices[0].message.content)92 requêtes · 30 derniers jours