Google · Model
Gemini 3.1 Pro Preview pricing, context window and specs
Gemini 3.1 Pro Preview costs $2 per million input tokens and $12 per million output tokens, and reads up to 1,048,576 tokens per request. By blended price it is the most expensive of Google’s 5 current models here.
- Input / 1M
- $2
- Output / 1M
- $12
- Cached / 1M
- $0.20
- Context
- 1,048,576
- Max output
- 65,536
- Released
- 2026-02-19
Estimate your cost with Gemini 3.1 Pro PreviewCompare all Google modelsCount tokens for Gemini 3.1 Pro Preview
Pricing
Gemini 3.1 Pro Preview API pricing
| Price per 1M tokens | Input | Output |
|---|---|---|
| Standard | $2 | $12 |
| Cached input (read) | $0.20 | – |
| Batch API | $1 | $6 |
| Prompts of 200,000+ tokens | $4 | $18 |
Output costs 6.0× the input price, so long replies drive the bill more than long prompts. If your requests share a long fixed prefix, such as a system prompt or tool definitions, caching cuts that part to 10% of the normal input price. Once a single prompt reaches 200,000 tokens, the whole request is billed at the higher long-context rate shown above.
Examples
What Gemini 3.1 Pro Preview costs in practice
| Workload | Tokens in / out | Requests/day | Per request | Per month |
|---|---|---|---|---|
| Support chatbot50% cached | 1,500 / 400 | 1,000 | $0.00645 | $196.19 |
| RAG app20% cached | 6,000 / 500 | 500 | $0.0158 | $240.90 |
| Coding agent80% cached | 40,000 / 2,000 | 200 | $0.0464 | $282.27 |
| Document summariserbatch | 8,000 / 600 | 300 | $0.0116 | $105.85 |
Change any number in the cost calculator.
Context
Context window
Gemini 3.1 Pro Preview accepts up to 1,048,576 tokens per request, roughly 786,432 English words or 1,573 pages. That budget is shared between your prompt and the reply, and a single reply is capped at 65,536 tokens.
Filling the whole window with one prompt costs about $4.19 at list price, so for repeated long-document work, retrieval (sending only the relevant parts) or prompt caching is usually much cheaper.
Check whether your text fits Gemini 3.1 Pro Preview’s window.
Features
Capabilities
- Image input
- Yes
- Tool / function calling
- Yes
- Reasoning mode
- Yes
- Prompt caching
- Yes
- Structured output
- Yes
- Open weights
- No
- Accepts
- audio, file, image, text, video
- Knowledge cutoff
- Not published
As declared by the provider’s API. It shows a feature exists, not how well it works.
API
Gemini 3.1 Pro Preview model ID
- OpenRouter
google/gemini-3.1-pro-preview- Google API
gemini-3.1-pro-preview(preview)gemini-3.1-pro-preview-customtools(preview)
Google lists Gemini 3.1 Pro Preview as current. Every Gemini model ID, with aliases and snapshots.
Where Gemini 3.1 Pro Preview sits in Google’s line-up
Ranked by blended price (three parts input to one part output, $4.50 per 1M for Gemini 3.1 Pro Preview), it is the most expensive of Google’s 5 current models here. One step down, Gemini 3.8 Flash costs $1.50 blended (67% less). It has the same published limits and features as Gemini 3.1 Pro Preview. See every Google model and price
| Model | Input / 1M | Output / 1M | Context | Released |
|---|---|---|---|---|
| Gemma 4 26B A4B | $0.0675 | $0.225 | 262,144 | 2026-04-03 |
| Gemma 4 31B | $0.09 | $0.34 | 262,144 | 2026-04-02 |
| Gemini 3.5 Flash Lite | $0.30 | $2.50 | 1,048,576 | 2026-07-21 |
| Gemini 3.8 Flash | $0.75 | $3.75 | 1,048,576 | 2026-09-02 |
| Gemini 3.1 Pro Preview (this page) | $2 | $12 | 1,048,576 | 2026-02-19 |
Google’s current models with a page here, cheapest first. Older and superseded models are listed on the provider page and in the comparison table.
History
Earlier versions of Gemini 3.1 Pro Preview
The previous model in this line is Gemini 2.5 Pro, first listed on 2025-06-17. Compared with it, Gemini 3.1 Pro Preview’s input price is 60% higher and its output price is 20% higher.
| Model | Input / 1M | Output / 1M | Context | Released |
|---|---|---|---|---|
| Gemini 2.5 Pro | $1.25 | $10 | 1,048,576 | 2025-06-17 |
Earlier releases with the same name and size in our data, newest first. Dates are when our source first listed each model.
Save
Cheaper alternatives
- GLM 4.6VZ.ai90% cheaper
- Qwen3.7 PlusQwen88% cheaper
- Command A+Cohere87% cheaper
- Seed-2.0-LiteByteDance Seed85% cheaper
- Gemini 3.5 Flash LiteGoogle81% cheaper
Current models from major providers, one per provider, that keep image input, tool calling, a reasoning mode, a usable context window and output limit. Compared by blended price.
Compare
Similarly priced models
- GPT-5.6 TerraOpenAI$2 / $12
- GLM 5.3 PrimeZ.ai$2.80 / $8.80
- Nova Premier 1.0Amazon$2.50 / $12.50
- Claude Sonnet 5.5Anthropic$2 / $10
- Qwen3.8 Max PrimeQwen$4 / $12
Current models from other major providers, closest blended price.
FAQ
Gemini 3.1 Pro Preview questions
How much does Gemini 3.1 Pro Preview cost?
Gemini 3.1 Pro Preview costs $2 per million input tokens and $12 per million output tokens, with cached input at $0.20. A typical chatbot reply (1,500 tokens in, 400 out) costs about $0.0078. Use the LLM cost calculator for your own workload.
What is Gemini 3.1 Pro Preview’s context window?
1,048,576 tokens, about 786,432 English words or 1,573 printed pages, shared between your prompt and the reply. A single reply can be up to 65,536 tokens.
Does Gemini 3.1 Pro Preview support prompt caching and batch requests?
Yes, cached input is billed at $0.20 per million tokens (10% of the normal input price). A batch API is available at $1 input and $6 output per million tokens.
What are cheaper alternatives to Gemini 3.1 Pro Preview?
With the same essentials (image input and tool calling), the cheapest options are GLM 4.6V (90% cheaper), Qwen3.7 Plus (88% cheaper), Command A+ (87% cheaper). Cheaper doesn’t mean equivalent, so test them on your own prompts.
What is the API model ID for Gemini 3.1 Pro Preview?
On OpenRouter it is google/gemini-3.1-pro-preview. In Google’s own API, use gemini-3.1-pro-preview; Google lists the model as current. The Gemini model ID list has every alias and snapshot. Pass the ID as the model value in each request.
What did Gemini 3.1 Pro Preview replace?
The previous Google model in the same line is Gemini 2.5 Pro, first listed on 2025-06-17. Compared with it, Gemini 3.1 Pro Preview’s input price is 60% higher and its output price is 20% higher. Prices are only part of the picture, so test the newer model on your own prompts before switching.
Is Gemini 3.1 Pro Preview open source?
No, Gemini 3.1 Pro Preview is only available through Google’s API and partners; its weights aren’t published.