gemini-3.1-pro-preview — API, Pricing & Context Window | Vivgrid

gemini-3.1-pro-preview is Google's high-end Gemini model, positioned for coding and complex multimodal reasoning. It accepts text, image, video, audio, and PDF within a ~1.05M-token context window.

On Vivgrid it runs as a globally centralized model. Because it relies on Google's global endpoint, regional acceleration is limited — but it remains available through the same unified API as the rest of the catalog.

Specifications

Pricing

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

Quick start

Call gemini-3.1-pro-preview 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-3.1-pro-preview",
    "messages": [
      { "role": "user", "content": "Say hello in English, Chinese and Spanish." }
    ],
    "stream": true
  }'

Ideal use cases

• Multimodal coding and reasoning agents
• Tasks blending long text with images, video, audio, or PDFs
• Large-context analysis up to ~1M tokens
• Workflows that benefit from Gemini's native multimodality

Related models

• gemini-3.5-flash — faster Gemini sibling
• gemini-3-pro-preview — the prior pro release
• gpt-5.5 — alternative flagship coding model