Google
Online
New
Gemini 3.1 Flash Lite
Fast, ultra low-cost multimodal model for high-volume tasks.
Model ID: tokenfast/gemini-3.1-flash-lite
Specifications
Context Window
1M tokens
Max Output
8.2K tokens
Input Price
$0.23 / 1M
Output Price
$1.35 / 1M
Capabilities
Chat
Code
Vision
Functions
JSON Mode
Price Comparison
See how much you save compared to official pricing.
| Metric | Official Price | Our Price | Savings |
|---|---|---|---|
| Input (per 1M tokens) | $0.25 | $0.23 | 10% off |
| Output (per 1M tokens) | $1.50 | $1.35 | 10% off |
Quick Start
Use this model via our OpenAI-compatible API endpoint.
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.yourdomain.com/v1",
apiKey: "sk-your-api-key",
});
const response = await client.chat.completions.create({
model: "tokenfast/gemini-3.1-flash-lite",
messages: [
{ role: "user", content: "Hello! What can you help me with?" },
],
max_tokens: 1024,
});
console.log(response.choices[0].message.content);Pricing Summary
Input$0.23 / 1M
Output$1.35 / 1M
Provider
Google DeepMind's Gemini family of multimodal AI models with industry-leading context windows.
Related Models
More from Google