All models

Gemini and GemmaGoogleClosed weights

Gemini 3.1 Flash Lite.

Gemini 3.1 Flash Lite is Google's multimodal efficiency model for low latency and high volumes, with text, image, video, audio and PDF as input. It suits light agentic workflows and simple data extraction, with selectable thinking levels to balance cost and quality.

Get started → Providers and prices

base_url="https://api.noirdoc.de/v1" model="gemini-3.1-flash-lite"

  • Data centres in the EU
  • § 203 confidentiality
  • Zero retention
  • List prices

Details.

Where the model runs, which rules apply and what it can do.

  1. Data centres in the EU Google Vertex Contracting party: Google Cloud EMEA Limited · based in Dublin, Ireland
§ 203 German Criminal Code (StGB)
Confidentiality agreed with Google Vertex
Weights
Closed weights
Features
Tools, Vision, Reasoning and JSON
See how this looks in your account →
Map: Gemini 3.1 Flash Lite runs in data centres in the EU (Google Vertex).

Providers.

We offer Gemini 3.1 Flash Lite through these providers.

Provider § 203 model=
€ · 1M tokens Input Cache Read Cache Write Output
Google Vertex EU EU data residency via Vertex AI
§ 203 agreed
gemini-3.1-flash-lite
Input 0.25 Cache Read 0.025 Output 1.49

More models.

Google develops the proprietary Gemini series and publishes open models from the same line of research with Gemma.

All Gemini and Gemma models →
Model
€ · 1M tokens Input Cache Read Cache Write Output
Gemini 4 Argon Tools Vision Reasoning JSON Google's flagship of the Gemini 4 generation for long, multi-step tasks such as software engineering, mathematics and agents, with tiered reasoning and 1M tokens of context. Google Vertex Logo Google Vertex · EU
Input 2.00 Cache Read 0.10 Output 9.90
Gemini 3.8 Flash Tools Vision Reasoning JSON Google's Flash model of the current Gemini generation — built for speed and high throughput. Google Vertex Logo Google Vertex · EU
Input 1.49 Cache Read 0.149 Output 7.41
Gemini 3.5 Flash Lite Tools Vision Reasoning JSON Compact Flash variant for simple, very frequent tasks — tuned for low latency. Google Vertex Logo Google Vertex · EU
Input 0.30 Cache Read 0.03 Output 2.47

Get started.

Test selected models right away with €5 starter credit — every model from the first top-up. If you have questions first, talk to our sales team.

Sign in →
python · openai sdk api.noirdoc.de/v1 
import os
from openai import OpenAI

client = OpenAI(
    # one line, that's all
    base_url="https://api.noirdoc.de/v1",
    api_key=os.environ["NOIRDOC_API_KEY"],
)

response = client.chat.completions.create(
    model="gemini-3.1-flash-lite",  # provider & model
    messages=[{"role": "user", "content": "Hello"}],
)