Gemini 3.1 Pro Preview API pricing
As of October 16, 2026, Gemini 3.1 Pro Preview costs $2.00 per million input tokens and $12.00 per million output tokens on the Google API. Cached input is $0.20 per million.
It is the most expensive of 16 Gemini models tracked here, by blended price. The closest Standard-tier model from another provider is GPT-5.6 Terra (OpenAI) at $2.00 / $12.00, the same blended price. Same list price as Gemini Deep Research Max Preview, Gemini Deep Research Pro Preview, GPT-5.6 Terra. First listed in the LiteLLM price data on February 20, 2026. Prompts longer than 200K tokens are billed at $4.00 input / $18.00 output.
Input / 1M tokens$2.00
Output / 1M tokens$12.00
Context window1.05M
Max output66K
Every published rate
| Rate | Per 1M tokens |
|---|
| Input (standard) | $2.00 |
| Output (standard) | $12.00 |
| Cached input (read) | $0.20 |
| Batch input | $1.00 |
| Batch output | $6.00 |
| Input, prompts over 200K tokens | $4.00 |
| Output, prompts over 200K tokens | $18.00 |
What it costs in practice
| Task | Tokens | Per request | Per 1,000 requests |
|---|
| Chatbot reply | 1,000 in / 500 out | $0.008 | $8.00 |
| Summarize a long document | 20,000 in / 1,000 out | $0.05 | $52.00 |
| Coding agent step | 50,000 in / 2,000 out | $0.12 | $124 |
Standard rates, no caching or batch discount; prompts over 200K tokens are billed at the higher long-prompt rate. Compare your own numbers across all models →
Price history
Dates are when each change first appeared in the LiteLLM price data, usually within days of the provider's announcement.
Details
| Provider | Google |
| Price tier | Standard |
| Features | Vision, Reasoning, Prompt caching, Tool use, PDF input, Web search |
| API model names | gemini-3.1-pro-preview |
| Official pricing | ai.google.dev |
Models at a similar price
Other Google models