Gemini 3.1 Pro
Pricing & Specs
Google (Gemini) · $2 input / $12 output per 1M tokens · 1.04858M context window
The per-token price never tells the full story. A typical task (1K input + 500 output tokens) on Gemini 3.1 Pro costs about $0.0080, roughly $8.00 per 1,000 runs. But if it needs 3x the tokens of a cheaper model to match quality on YOUR task, the economics flip. The only way to know is to benchmark it on your actual workload.
Gemini 3.1 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 3.1 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 |
| Reasoning model | Yes |
| Tool / function calling | Yes |
| JSON mode | Yes |
| Streaming | Yes |
| Prompt caching | Yes |
| Batch API | Yes |
FAQ
How much does Gemini 3.1 Pro cost?
Gemini 3.1 Pro costs $2 per 1M input tokens and $12 per 1M output tokens ($0.2 per 1M cached input tokens).
What is Gemini 3.1 Pro's context window?
Gemini 3.1 Pro has a 1.04858M-token context window. Maximum output is 65.536K tokens.
Can I test Gemini 3.1 Pro on my own task?
Yes. OpenMark lets you benchmark Gemini 3.1 Pro against 100+ models on your own task with real API calls, with no API keys needed, free tier available.
Is Gemini 3.1 Pro the right model for YOUR task?
Pricing tables can't answer that. Benchmark it against 100+ models
on your actual workload: real API calls, real costs. Free tier available.