GoogleVisionTool use

Gemini 3 Pro Preview pricing

Gemini 3 Pro is Google’s flagship frontier model for high-precision multimodal reasoning, combining strong performance across text, image, video, audio, and code with a 1M-token context window. Reasoning Details must be preserved when using multi-turn tool calling, see our docs here: https://openrouter.ai/docs/use-cases/reasoning-tokens#preserving-reasoning-blocks. It delivers state-of-the-art benchmark results in general reasoning, STEM problem solving, factual QA, and multimodal understanding,. This page tracks 5 listings in total. Highlighted lows are $2.00 per million input and $12.00 per million output (see table for which seller matches each).

1.0M context·5 providers·verified Apr 7, 2026
Best input$2.00per 1M tokens · Google Vertex
Best output$12.00per 1M tokens · Google Vertex

Pricing across providers

Use this table to read Gemini 3 Pro Preview list prices. We show 5 sources right now. Lowest input in the grid: Google Vertex. The chart below the table helps when output prices are much higher than input prices.

GV
Google Vertex
Input / 1M
$2.00
Output / 1M
$12.00
Cached in: $0.200
G
Googlenative
Input / 1M
$2.00
Output / 1M
$12.00
Cached in: $0.200
GC
Github Copilot
Input / 1M
N/A
Output / 1M
N/A
G
Gmi
Input / 1M
$2.00
Output / 1M
$12.00
O
Openrouter
Input / 1M
$2.00
Output / 1M
$12.00
Cached in: $0.200

Input vs output · per provider

Cost calculator

Pick any of the providers above and type how many tokens you expect per day, week, or year. We turn that into rough dollar totals for Gemini 3 Pro Preview.

Provider

In: $2.00/M·Out: $12.00/M·Cache: $0.200/M

0.200000¢ / req

0.600000¢ / req

Daily
$80
Monthly
$2.4K
Annual
$29.2K

Model specifications

These fields describe Gemini 3 Pro Preview as we store it (source: Google). They sit next to price so buyers can check limits and tools in one place.

Context window
1,048,576 tokens
Max output
65,535 tokens
Vision (images)
Yes
Tool / function calling
Yes
Streaming
No
Released
Nov 2025
Primary provider
Google
Model family
N/A

Compare Gemini 3 Pro Preview

Jump into a comparison when you want one table for two models instead of two tabs. 6 curated matches for Gemini 3 Pro Preview.

Frequently asked questions

Read these after the table if you want plain language around Gemini 3 Pro Preview rates. The short model note from our index: Gemini 3 Pro is Google’s flagship frontier model for high-precision multimodal reasoning, combining strong performance across text, image, video, audio, and code with a 1M-token context window. Reasoning Details must be ...

Gemini 3 Pro Preview costs $2.00 per million input tokens and $12.00 per million output tokens via the native API. Prompt caching reduces input costs to $0.20/M tokens.

Also from Google

Other models by Google with live pricing in our catalog.