Back to models
Model · Google
Google

Gemini 3.8 Flash

google/gemini-3.8-flash
Try in Agents

Google's Gemini 3.8 Flash — customizable thinking configurations to trade quality against cost and latency

reasoningvisionvideoaudiocaching
Specs
Context
1M
Max output
66K
Provider
Google
Input
$0.750/ 1M tokens
Output
$3.75/ 1M tokens
Cache read
$0.075/ 1M tokens
Try it
Chat with Gemini 3.8 FlashTerramind API
⌘+Enter to run
Code
import { streamText } from "ai";
import { createOpenAICompatible } from "@ai-sdk/openai-compatible";

const terramind = createOpenAICompatible({
  name: "terramind",
  baseURL: "https://terramind.com/api/v1",
  apiKey: process.env.TERRAMIND_API_KEY!,
});

const result = streamText({
  model: terramind("gemini-3.8-flash"),
  prompt: "Why is the sky blue?",
});

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

Want to run this in your app? Grab an API key · Full chat reference

More by Google
ModelContextInOutCapabilities
Googlegoogle/gemini-2-5-pro1.0M$1.25$10.00
reasoningvisionvideo
Googlegoogle/gemini-3.1-pro-preview1.0M$2.00$12.00
reasoningvisionvideo
Googlegoogle/gemini-3.5-flash1M$1.50$9.00
reasoningvisionvideo
Googlegoogle/gemini-3.6-flash1M$0.750$3.75
reasoningvisionvideo
Googlegoogle/gemini-3.7-flash1M$0.750$3.75
reasoningvisionvideo
Googlegoogle/gemini-4-argon1M$4.00$20.00
reasoningvisionvideo
Googlegoogle/gemini-3.1-flash-lite1M$0.250$1.50
visionvideoaudio
Googlegoogle/gemini-3.5-flash-lite1M$0.300$2.50
visionvideoaudio