Gemini 3 Pro
Pricing & Specs
Google (Gemini) · $2 input / $12 output per 1M tokens · 1.04858M context window
No longer offered on OpenMark
Gemini 3 Pro is no longer offered on OpenMark (deprecated or superseded upstream). Its specs are kept here for reference — if you're still running it in production, it's worth benchmarking current alternatives: newer models are often cheaper AND better on the same task.
Gemini 3 Pro API Pricing
| Tokens | Price |
|---|---|
| Input | $2 / 1M tokens |
| Output | $12 / 1M tokens |
| Cached input | $0.2 / 1M tokens |
Context caching : $0.20, prompts <= 200k tokens. $0.40, prompts > 200k. $4.50 / 1,000,000 tokens per hour (storage price)
What that means in practice
Gemini 3 Pro Specs
| Spec | Value |
|---|---|
| Context window | 1.04858M tokens |
| Max output tokens | 65.536K tokens |
| Input modalities | text, image, video, audio, PDF |
| Output modalities | text |
| Latency (measured by OpenMark) | ~2.7s median response |
| Reasoning model | Yes |
| Tool / function calling | Yes |
| JSON mode | Yes |
| Streaming | Yes |
| Prompt caching | Yes |
| Batch API | Yes |
Notes
Scheduled for discontinuation March 9, 2026. Migrate to gemini-3.1-pro (gemini-3.1-pro-preview).
FAQ
How much does Gemini 3 Pro cost?
Gemini 3 Pro costs $2 per 1M input tokens and $12 per 1M output tokens ($0.2 per 1M cached input tokens).
What is Gemini 3 Pro's context window?
Gemini 3 Pro has a 1.04858M-token context window. Maximum output is 65.536K tokens.
Can I test Gemini 3 Pro on my own task?
Gemini 3 Pro is no longer offered on OpenMark, but you can benchmark its current alternatives from Google (Gemini) and other providers on your own task — free tier available.
Still using Gemini 3 Pro?
It's been superseded. Benchmark its current alternatives on your actual
workload — you'll likely find something cheaper AND better. Free tier available.