Gemini 3.1 Flash Lite

Gemini 3.1 Flash Lite outperforms 2.5 Flash Lite on overall quality and lands close to 2.5 Flash performance across key capability areas. It is a workhorse model for high-volume use cases, with improvements across audio input/ASR, RAG snippet ranking, translation, data extraction, and code completion.

Context 1M·Max out 65K

Quickstart

import { streamText } from 'ai';
import { createOpenAICompatible } from '@ai-sdk/openai-compatible';

const blackbox = createOpenAICompatible({
  name: 'blackbox',
  apiKey: process.env.BLACKBOX_API_KEY!,
  baseURL: 'https://api.blackbox.ai/v1',
});

const result = streamText({
  model: blackbox('blackboxai/google/gemini-3.1-flash-lite'),
  prompt: 'Why is the sky blue?',
});

for await (const chunk of result.textStream) {
  process.stdout.write(chunk);
}

Specs & pricing

Input $/M: $0.25
Output $/M: $1.50
Context window: 1M
Max output: 65K
Supported parameters: tool-usevisionjson-modestreamingweb-search

Related models

Model	Type	Context	Input $/M
Gemini 3.5 Flash	Text	1M	$1.50
Gemini 3.1 Pro	Text	1.0M	$2
Gemma 4 26B	Text	262.1K	$0.13
Gemma 4 31B	Text	262.1K	$0.14
Blackbox Pro	Text	400K	$1.75