Google DeepMind Models on XALEN

Google AI research lab. Gemini and Gemma models on XALEN.

Founded: 2010 · HQ: London / Mountain View · 4 models available

Available Models

Gemini 2.5 Pro

Frontier

Google frontier model with massive 2M context window.

Params: ~1.5T Context: 2M Input: $0.07 Output: $0.21 Latency: ~600ms

Gemini 2.5 Flash

Fast

Fastest Gemini with 1M context.

Params: ~200B Context: 1M Input: $0.015 Output: $0.06 Latency: ~200ms

Gemini 2.0 Flash

Fast

Previous-gen Gemini flash model at very low cost.

Params: ~100B Context: 1M Input: $0.01 Output: $0.04 Latency: ~150ms

Gemma 3 27B

Open Source

Google efficient open model with fast inference.

Params: 27B Context: 128K Input: $0.03 Output: $0.05 Latency: ~180ms

Quick Start

import XALEN from 'xalen-sdk';

const client = new XALEN({ apiKey: 'xln_test_YOUR_KEY' });

const response = await client.chat.completions.create({
  model: 'gemini-2-5-pro',
  messages: [{ role: 'user', content: 'Hello!' }]
});

Start Using Google DeepMind Models

All models available through a single API. No separate accounts needed.

Get API Key

Last updated: 2026-05-21.