gemini-3-pro-preview-thinking-*
Google's gemini-3-pro-preview-thinking-* - compact and efficient with budget-friendly pricing. Google's advanced AI research.
Capability Radar
About gemini-3-pro-preview-thinking-*
"Cutting-edge multimodal capabilities"
gemini-3-pro-preview-thinking-* is Google's budget-friendly model featuring focused context window (32K). Cutting-edge multimodal capabilities, this model delivers industry-leading context windows.
⚡ Key Strengths
- Cutting-edge multimodal capabilities
- Best price-to-performance ratio
- Fast inference with efficient resource usage
- Advanced reasoning and problem-solving
- OpenAI SDK compatible
🎯 Best Use Cases
- Real-time chatbots and customer support
- High-volume content moderation
- Quick classification and tagging
- High-volume API processing
- Cost-sensitive production applications
Technical Specifications
Quick Start Guide
import OpenAI from "openai";
const openai = new OpenAI({
baseURL: "https://api.okrouter.com/v1",
apiKey: "<YOUR_OKROUTER_KEY>",
});
async function main() {
const completion = await openai.chat.completions.create({
model: "gemini-3-pro-preview-thinking-*",
messages: [
{ role: "user", content: "Hello! What can you do?" }
],
});
console.log(completion.choices[0].message);
}
main();Getting started with gemini-3-pro-preview-thinking-* is easy. Since OkRouter is fully compatible with the OpenAI SDK, you can use existing libraries to access this model immediately. gemini-3-pro-preview-thinking-* is fully compatible with the OpenAI Chat Completions API. distinctive features include Standard context handling and Text support.
Interactive Playground
Parameters Setup
Controls randomness: Lowering results in less random completions.
Return data chunks as they arrive
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.okrouter.com/v1",
apiKey: process.env.OKROUTER_API_KEY,
});
const completion = await client.chat.completions.create({
model: "gemini-3-pro-preview-thinking-*",
messages: [{ role: "user", content: "Hello world!" }],
temperature: 0.7,
stream: true,
});Frequently Asked Questions
?How much does gemini-3-pro-preview-thinking-* cost?
gemini-3-pro-preview-thinking-* costs $1.60 per 1M input tokens and $9.60 per 1M output tokens via OkRouter. This is 20% cheaper than OpenRouter with the same great performance.
?Is gemini-3-pro-preview-thinking-* compatible with OpenAI SDK?
Yes! gemini-3-pro-preview-thinking-* works seamlessly with all OpenAI SDKs (Python, JavaScript, Go, etc.). Simply change your base_url to api.okrouter.com and use your OkRouter API key. No code changes needed.
?What is gemini-3-pro-preview-thinking-* best used for?
gemini-3-pro-preview-thinking-* excels at real-time chatbots and customer support, high-volume content moderation, quick classification and tagging. It's budget-friendly and perfect for high-volume production workloads.