gemini-2.5-pro — API, Pricing & Context Window | Vivgrid

gemini-2.5-pro is Google's widely used pro-tier multimodal model, valued for strong reasoning and a 1M-token context window spanning text, image, video, audio, and PDF. It remains a reliable choice for established multimodal applications.

Vivgrid serves gemini-2.5-pro as a globally centralized model through its unified, OpenAI-compatible API, easing migration to or from newer Gemini releases.

Specifications

Pricing

Pricing in USD per 1M tokens, matching the provider's rates.

Quick start

Call gemini-2.5-pro through Vivgrid's unified, OpenAI-compatible endpoint. Get an API key from the Vivgrid Console.

curl https://api.vivgrid.com/v1/chat/completions \
  -H "Authorization: Bearer $VIVGRID_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-2.5-pro",
    "messages": [
      { "role": "user", "content": "Say hello in English, Chinese and Spanish." }
    ],
    "stream": true
  }'

Ideal use cases

• Established multimodal reasoning applications
• Long-context analysis over mixed media
• Document, audio, and video understanding
• A stable baseline before adopting Gemini 3

Related models

• gemini-3-pro-preview — the next-gen pro model
• gemini-2.5-flash — faster, cheaper sibling
• gemini-3.1-pro-preview — latest pro release