Gemini 3.1 Pro Preview pricing, context window and limits
Gemini 3.1 Pro Preview costs $2 per million input tokens and $12 per million output tokens at Google Vertex AI list price. It accepts up to 1,048,576 tokens of context and returns up to 65,536 tokens.
- Model id
vertex/gemini-3.1-pro-preview - Snapshot
What does Gemini 3.1 Pro Preview cost?
| Input | $2 |
|---|---|
| Output | $12 |
| Cached input (read) | $0.2 |
| Cache write | — |
US dollars per million tokens. A dash means no price is published.
How much can Gemini 3.1 Pro Preview read and write?
| Context window | 1,048,576 |
|---|---|
| Max output | 65,536 |
What can Gemini 3.1 Pro Preview do?
| Vision (image input) | Yes |
|---|---|
| Tool calling | Yes |
| Structured output | Yes |
| Reasoning | Yes |
| Input | text, image, video, audio, pdf |
| Output | text |
What does a request to Gemini 3.1 Pro Preview cost?
| A typical request: 1,000 tokens in, 500 out | $0.008 |
|---|---|
| A long request: 10,000 tokens in, 1,000 out | $0.032 |
| 1,000 typical requests | $8 |
| 1 million tokens in and 1 million out | $14 |
Input read from the provider's prompt cache costs $0.2 per million tokens instead of $2, 90% less. A request that repeats a 1,000-token prompt from the cache costs $0.0062 instead of $0.008.
Among 12 Google Vertex AI models with a published price, Gemini 3.1 Pro Preview is the 11th cheapest by input price. Its context window is the largest of 12. List prices only; discounts, batch prices and prices above 200K tokens are not shown.
How do I call Gemini 3.1 Pro Preview through DVARA?
Configure the vertex-ai provider in the DVARA LLM Gateway and send the model id vertex/gemini-3.1-pro-preview. DVARA, the AI gateway, applies your policies, audit and cost attribution to the call. See LLM cost attribution and budgets.
In DVARA, if you haven't set your own price for a model, its calls are costed at the price in the catalogue that ships with your DVARA version. A price you set in Flightdeck always wins. You can switch catalogue prices off. Then a model with no price you set gets no cost record: its calls count against no budget and appear in no report, and the gateway records the model as unpriced. Every cost record says which price it used.
What should I check before relying on this data?
The weekly review marked this entry. A person saw each mark and kept the model listed.
- The provider charges more above 200K tokens of input; the table shows the base price.
Which other Google Vertex AI models are there?
- Gemini 3.1 Flash Lite$0.25 in · $1.5 out · 1.05M context
- Gemini 3.5 Flash$1.5 in · $9 out · 1.05M context
- Gemini 2.5 Pro$1.25 in · $10 out · 1.05M context
- Gemini 3.5 Flash Lite$0.3 in · $2.5 out · 1.05M context
- Gemini 2.5 Flash-Lite$0.1 in · $0.4 out · 1.05M context
- Gemini 3.6 Flash$0.75 in · $3.75 out · 1.05M context
- Gemini 2.5 Flash$0.3 in · $2.5 out · 1.05M context
- Gemini 3.7 Flash$0.75 in · $3.75 out · 1.05M context
- Gemini 3.8 Flash$0.75 in · $3.75 out · 1.05M context
- Gemini 4 Argon$2 in · $10 out · 1.05M context
- Gemini Embedding 001$0.15 in · $0 out · 2K context
Which models from other providers are similar to Gemini 3.1 Pro Preview?
These are the closest in context window and input price, one per provider.
- Gemini 3.1 Pro PreviewGoogle Gemini · $2 in · $12 out · 1.05M context
- GPT-4.1OpenAI · $2 in · $8 out · 1.05M context
- GPT-5.6 Terra (Global)Amazon Bedrock · $2 in · $12 out · 1.05M context
- Kimi K3.1 ProMoonshot AI · $1.9437 in · $10.1671 out · 1.05M context
- Claude Sonnet 5Anthropic · $2 in · $10 out · 1M context