Google's latest multimodal model, supporting image and video in text or chat prompts.
Optimized for language tasks including:
Usage of Gemini is subject to Google's Gemini Terms of Use.
#multimodal
To get started, you can use Gemini Pro 1.5 via API like this:
fetch("https://openrouter.ai/api/v1/chat/completions", {
method: "POST",
headers: {
"Authorization": `Bearer ${OPENROUTER_API_KEY}`,
"HTTP-Referer": `${YOUR_SITE_URL}`, // Optional, for including your app on openrouter.ai rankings.
"X-Title": `${YOUR_SITE_NAME}`, // Optional. Shows in rankings on openrouter.ai.
"Content-Type": "application/json"
},
body: JSON.stringify({
"model": "google/gemini-pro-1.5",
"messages": [
{
"role": "user",
"content": [
{
"type": "text",
"text": "What's in this image?"
},
{
"type": "image_url",
"image_url": {
"url": "https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg"
}
}
]
}
]
})
});You can also use OpenRouter with OpenAI's client API:
import OpenAI from "openai"
const openai = new OpenAI({
baseURL: "https://openrouter.ai/api/v1",
apiKey: $OPENROUTER_API_KEY,
defaultHeaders: {
"HTTP-Referer": $YOUR_SITE_URL, // Optional, for including your app on openrouter.ai rankings.
"X-Title": $YOUR_SITE_NAME, // Optional. Shows in rankings on openrouter.ai.
}
})
async function main() {
const completion = await openai.chat.completions.create({
model: "google/gemini-pro-1.5",
messages: [
{
"role": "user",
"content": [
{
"type": "text",
"text": "What's in this image?"
},
{
"type": "image_url",
"image_url": {
"url": "https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg"
}
}
]
}
]
})
console.log(completion.choices[0].message)
}
main()See the Request docs for all possible parameters, and Parameters for recommended values.