Google: Gemini 3.1 Pro (Preview)
google/gemini-3.1-pro-previewAvailable via Safeguard
Public cloudPrivate cloud
Released
February 19, 2026
Context
1,048,576 tokens
Input
$2 / 1M tokens
Output
$12 / 1M tokens
Overview
Google's current Pro model, offered as a preview, for multimodal understanding and agentic coding.
- Provider
Google
- Modality
- Text and image
- Input
- text, image, video, audio, file
- Output
- text
- Max output
- 65,536 tokens
- Weights
- Closed
- Supported parameters
- tools, structured_outputs, reasoning, web_searchProvider's model page, checked .
- Distillable
- NoLicence or terms, checked .
- Tags
- reasoning, coding, multimodal, preview
Data policy
- Prompts go to
- Google (Gemini Developer API)
- Retention
- Paid tier: prompts and responses not used to improve Google products, but logged for a limited period for abuse monitoring, free tier content may be used to improve products
- Zero data retention
- Not offered
- Region
- No region guarantee, data may be stored transiently or cached in any country where Google operates. Google points ZDR and enterprise processing needs to Vertex AI (Gemini Enterprise Agent Platform)
- Policy
- Google data policy
Summarised from the provider's published terms. The provider's own policy is what applies.
Where you can run it
How Gemini 3.1 Pro (Preview) can be deployed, bought and reached through Safeguard.
- Deployment
- Public cloudPrivate cloud
- Procurement
- Not published yet
- Inference regions
- Not published yet
Closed weights stay with the provider, so this model runs in the provider's cloud, never on-prem.
Pricing
| Provider | Input / 1M tokens | Output / 1M tokens | Context |
|---|---|---|---|
| $2 | $12 | 1.05M |
- Notes
- Preview model. Prompts <=200K tokens, over 200K: $4 in / $18 out. Output includes thinking tokens. No free tier.
- Source
- Google pricing , last verified November 2, 2026
No markup on model usage: you pay the provider's list price.
API
OpenAI-compatible. Your API key and access to this model are set up for your workspace when you choose Use with Safeguard.
from openai import OpenAI
client = OpenAI(
base_url="https://api.safeguard.sh/gpt/v1",
api_key="SAFEGUARD_API_KEY",
)
response = client.chat.completions.create(
model="google/gemini-3.1-pro-preview",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Base URL https://api.safeguard.sh/gpt/v1, model google/gemini-3.1-pro-preview.
Self-healing security runs on Safeguard.
Your first fix PR is minutes away.
No sales call required, even your agent can complete the purchase over MCP.