Models

Gemini 3.5 Flash-Lite

Model id: gemini/models/gemini-3.5-flash-lite

  • Cost
  • Fast
  • Vision
  • Multimodal
  • Audio
  • Long context
  • Translation

Google’s cost-efficient Gemini 3.5 Flash-Lite tier for high-volume agentic and translation work.

Best for

high-throughput chat, routing, and simple processing at low cost.

Provider
Google Gemini
Context window
1,048,576
Release date
2026-07-21
Reasoning effort
minimallowmediumhighDefault: medium

Pricing

Input
$0.463 / 1M
Output
$3.858 / 1M
Cached input
$0.0463 / 1M

Web search

Per successful search
$0.0216 / search

Billed on top of tokens when the model uses web search.

Amounts in Canadian dollars, converted at the Bank of Canada indicative rate (2026-07-31).

Performance

Reading

Last 7 days

Not enough data to display the chart.

Activity

Tokens

Top 5 tools · last 7 days

Not enough data to display tool activity.

Availability

Availability (%)

Last 7 days

Operational probes
100% over 7 days
Samples
8,607

View service status

Quick start

Call the API with a tonia_ key and the exact model id below.

curl

curl https://pass.tonia.ca:8443/v1/chat/completions \
  -H "Authorization: Bearer $TONIA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini/models/gemini-3.5-flash-lite",
    "messages": [{"role":"user","content":"Bonjour"}]
  }'

Python (OpenAI SDK)

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://pass.tonia.ca:8443/v1",
    api_key=os.environ["TONIA_API_KEY"],
)
response = client.chat.completions.create(
    model="gemini/models/gemini-3.5-flash-lite",
    messages=[{"role": "user", "content": "Bonjour"}],
)

TypeScript (OpenAI SDK)

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://pass.tonia.ca:8443/v1",
  apiKey: process.env.TONIA_API_KEY,
});

const response = await client.chat.completions.create({
  model: "gemini/models/gemini-3.5-flash-lite",
  messages: [{ role: "user", content: "Bonjour" }],
});

On the OpenAI-compatible bridge (Cursor, Cline, and similar tools), Gemini models use the gemini/models/ prefix (for example gemini/models/gemini-3.6-flash).

Create a key in the portal