Gemini 3.1 Flash Lite

Google's multimodal model, served through one OpenAI-compatible endpoint with transparent per-token pricing and project-scoped API keys.

GoogleMultimodal Model

Get started Documentation

MODEL SPEC

Developed by: Google
Model family: Gemini 3.1 Flash Lite
Size: —
Architecture: Transformer
Context window: 1M tokens
Max output: 66K tokens
License: Provider license

Overview

Gemini 3.1 Flash Lite is a multimodal model from Google, available through the Inference.net serverless API. Use the same OpenAI-compatible request shape across the catalog and switch models by changing a single identifier.

The API supports streaming responses and project-scoped credentials. Usage, token volume, and spend appear in the dashboard automatically, so the model can move from evaluation to production without a second integration path.

QUICKSTARTGet API key

import OpenAI from 'openai'

const client = new OpenAI({
  baseURL: 'https://api.inference.net/v1',
  apiKey: process.env.INFERENCE_API_KEY,
})

const completion = await client.chat.completions.create({
  model: 'gemini-3.1-flash-lite',
  messages: [{ role: 'user', content: 'Hello' }],
})

PROMPT CACHING

No special request field is needed. Keep the prompt prefix stable and byte-identical across calls.
As a practical target, use roughly 9,000 tokens in the stable prefix; this is not a guaranteed provider minimum.
Check usage.prompt_tokens_details.cached_tokens in the response to confirm cache reads.

AGENT INTEGRATIONSView all