Home / Models / Google / Gemini 3.1 Pro Preview Custom Tools

Gemini 3.1 Pro Preview Custom Tools pricing and routing profile

Gemini 3.1 Pro Preview Custom Tools from Google lists at $2.00 per million input tokens and $12.00 per million output tokens, with a 1,048,576-token context window. Prices from OpenRouter's catalogue on 2026-09-28.

Input, per 1M tokens$2.00
Output, per 1M tokens$12.00
Cached input, per 1M$0.20
Context window1.05M
Confidence signalNot exposed

Tool callingStructured outputReasoning control

Cost per 1,000 requests

Request shapeList cost
Classification or routing (600 tokens in, 10 out)$1.32
Chat reply (2,000 in, 400 out)$8.80
Retrieval-augmented answer (8,000 in, 500 out)$22.00

Before prompt caching. Try your own shape in the cost calculator.

Can Gimbix route to it first?

Not as a first-answer model through OpenRouter: no host returns token log probabilities for Gemini 3.1 Pro Preview Custom Tools. It can still be the model Gimbix falls back to when a cheaper model is unsure.

Cheaper models that can answer first

Models priced below Gemini 3.1 Pro Preview Custom Tools that expose a confidence signal. Whether they answer your traffic as well is what a Gimbix pilot measures.

ModelInput / output per 1MCheaper on a chat reply
Grok 4.7$1.60 / $4.8042%
Qwen3.7 Max$1.48 / $4.4246%
GLM 5.1$1.40 / $4.4048%
Qwen3.6 Max Preview$1.03 / $6.1649%
Grok 4.3$1.25 / $2.5060%
Grok 4.20 Multi-Agent$1.25 / $2.5060%

Questions

How much does Gemini 3.1 Pro Preview Custom Tools cost?

Gemini 3.1 Pro Preview Custom Tools lists at $2.00 per million input tokens and $12.00 per million output tokens on OpenRouter as of 2026-09-28. A typical chat reply of 2,000 input and 400 output tokens costs about $8.80 per 1,000 requests.

What is the context window of Gemini 3.1 Pro Preview Custom Tools?

1,048,576 tokens.

Can a cheaper model replace Gemini 3.1 Pro Preview Custom Tools?

Sometimes. Gimbix proves it on your own traffic before routing: the cheaper model must match Gemini 3.1 Pro Preview Custom Tools on one half of your requests and make at most three answers worse on the other.