Models

gemini-2.5-pro β€” API, Pricing & Context Window | Vivgrid

gemini-2.5-pro on Vivgrid: Google's proven multimodal model with a 1M-token context window across text, image, video, audio and PDF.

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

ProviderGoogle
Model IDgemini-2.5-pro
Best forGeneral-purpose
Available onChat Completions
Context window1,048,576 tokens
ModalitiesText, Image, Video, Audio, PDF
Tool / function callingYes
Knowledge cutoff2025-01
Acceleration🌐 Global (Centralized)

Pricing

Pricing in USD per 1M tokens.

InputCached inputOutput
$1.25$0.31$10.00

What one request costs

The rates above applied to a 20K-token prompt with a 2K-token reply β€” a typical single agent turn, small enough that every request is billed at the base rate.

RequestCost
Cold prompt, nothing cached$0.0450
Warm prompt, 90% of the input served from cache$0.0281

API surfaces

The Vivgrid Console catalogs gemini-2.5-pro on one surface, all behind the same API key. The endpoint shown is the one the Console previews for that surface.

SurfacePrimary endpointUse it for
Chat Completions/chat/completionsAgent projects, where Vivgrid injects the model, system prompt and tools server-side, and Model API calls that name the model per request.

Quick start

Get an API key from the Vivgrid Console, then call gemini-2.5-pro directly.

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

On this page