Model API
Gemini 3.8 Flash API
Gemini 3.8 Flash API on Aiduct. Input tokens: $1.50 / 1M input tokens. 1,048,576 token context. View model parameters, pricing and integration examples.
Model ID
gemini-3.8-flash
Provider
Capability
chat, vision, tools, thinking, structured-output
Status
Available
Pricing and limits
Input tokens
$1.50 / 1M input tokens
Output tokens
$7.50 / 1M output tokens
Cached input
$0.15 / 1M cached input tokens
Rates are in USD for the stated unit. Model options and additional usage can affect the final charge. Check the live catalog before integrating.
- Context length
- 1,048,576
- Max output
- 65,536
- Release date
- 2026-09-02
Use this model
import OpenAI from "openai";
const client = new OpenAI({
apiKey: process.env.AIDUCT_API_KEY,
baseURL: "https://api.aiduct.ai/v1",
});
const response = await client.chat.completions.create({
model: "gemini-3.8-flash",
messages: [{ role: "user", content: "Say hello in one sentence." }],
});Supported parameters
messagestemperaturetop_pmax_tokensstreamstoptoolstool_choiceresponse_formatuserthinking