Gemini Ultra

Pricing

Simple, transparent token-based pricing. Pay only for what you use.

Input Tokens

$20

per 1M tokens

Output Tokens

$60

per 1M tokens

Capabilities

Core strengths and supported features of Gemini Ultra.

Reasoning

Analysis

Code

Vision

Performance

Context window capacity and inference speed characteristics.

Context Window

128K

Standard context window that handles most use cases including document analysis, code review, and lengthy conversations.

Speed: Deliberate

Extended processing for complex reasoning. Best for complex analytical tasks, research, and scenarios where thoroughness matters more than speed.

Quick Start

Get started with Gemini Ultra in just a few lines of code.

import OriginalPoint from "originalpoint";

const client = new OriginalPoint({
  apiKey: process.env.ORIGINALPOINT_API_KEY,
});

const response = await client.chat.completions.create({
  model: "gemini-ultra",
  messages: [
    {
      role: "user",
      content: "Hello, how can you help me today?",
    },
  ],
  max_tokens: 1024,
});

console.log(response.choices[0].message.content);

More from Google

Explore other models available from Google.

Gemini 2.5 Pro

Frontier

Google's most capable model with advanced reasoning and a massive context window. Excellent for complex research, long-document analysis, and multi-step problem solving.

1M contextFrom $4/1M4.7

Gemini 2.0 Flash

Economy

Ultra-fast model with excellent multimodal understanding. Optimized for speed-critical applications while maintaining strong quality.

1M contextFrom $0.075/1M4.5

Quick Overview