Gemini 3.1 Pro Preview
Gemini 3.1 Pro Preview API pricing is $2 per million input tokens and $12 per million output tokens.
- Provider
- API model name
- gemini-3.1-pro-preview
- Status
- Current
- Input, $ per 1M tokens
- $2.00
- Cached input, $ per 1M tokens
- $0.20
- Output, $ per 1M tokens
- $12.00
- Sample request (10K in, 2K out), $
- $0.044
- Context window, tokens
- 1.05M
- Price checked on
- Official pricing page
- ai.google.dev
These rates on Google’s own API apply to prompts up to 200,000 tokens. Longer prompts cost $4 input and $18 output. Cached input is billed at $0.20 per million tokens, or $0.40 above 200,000 tokens. A request with 10,000 input tokens and 2,000 output tokens costs about $0.044 before caching or batch discounts. The API model name is gemini-3.1-pro-preview, and the context window is 1.05M tokens. Within Google’s current lineup, Gemini 3.5 Flash-Lite handles the same request for about $0.008.
- Max output, tokens
- 65.54K
- Input types
- Text, image, video, audio, PDF
- Open weights
- No
- Long-context pricing
- Prompts over 200K tokens: $4 input, $0.40 cached input, $18 output
- Sources
Page URL Checked Gemini Developer API pricing https://ai.google.dev/gemini-api/docs/pricing 2026-10-19 OpenRouter model listing (context and output limits) https://openrouter.ai/models 2026-09-29
Questions
How much does the Gemini 3.1 Pro Preview API cost?
What is the API model name for Gemini 3.1 Pro Preview?
gemini-3.1-pro-preview in API calls to Google. The context window is 1.05M tokens, and a response can run to 65,536 output tokens.What does one Gemini 3.1 Pro Preview request cost?
Does Gemini 3.1 Pro Preview cost more for long prompts?
Sources
Prices are read from each provider’s official pricing page: OpenAI, Anthropic, Google Gemini API, xAI, DeepSeek and Mistral AI. Context and output limits that a provider does not publish come from OpenRouter’s model listing. Each model’s Sources field lists the pages used and the date each was checked. How we check prices · Price change log