Gemini 3.1 Pro Preview Custom Tools

Provider: Google AI US Official API price

Input price
$2.00
/ 1M tokens
Output price
$12.00
/ 1M tokens
Cache price
$0.20
/ 1M tokens (read)
Context
1.05M tokens
Max output 66K tokens

Overview

Google AI's Gemini 3.1 Pro Preview Custom Tools is positioned as a flagship or reasoning specialist model. It targets advanced, complex multimodal applications, leveraging its extensive context window and sophisticated capabilities.

Strengths

  • Exceptional 1M+ token context window for processing extensive information.
  • Robust multimodal capabilities supporting both vision and audio inputs.
  • Advanced programmatic control via function-calling and reliable JSON mode.
  • Demonstrates strong reasoning abilities through its 'thinking' capability.
  • Capable of generating very long responses, up to 65,536 tokens.

Best use cases

  • Automating complex workflows by integrating with custom tools and systems.
  • Analyzing large multimodal documents, including images and audio transcripts.
  • Developing sophisticated AI agents requiring precise, structured JSON output.
  • Processing and summarizing extensive codebases or lengthy legal documents.
  • Building applications that require deep reasoning across diverse input types.

Pricing position

With an input price of $2/M tokens and an output price of $12/M tokens, Gemini 3.1 Pro is Google AI's most expensive model listed. Its input price matches peers like GPT-4.1 and Sonar Reasoning Pro, but its output price of $12/M is notably higher than those peers ($8/M) and Mistral Large models ($6/M). It is significantly more costly than Google's Gemma series and Gemini 2.0 Flash Lite, which offer much lower prices for simpler tasks.

Caveats

Being a 'Preview' model, its stability or general availability might be limited. The high output price of $12/M makes it less economical for applications requiring frequent, long text generation compared to similarly priced peers. For simpler text-only tasks or shorter contexts, Google's Gemma models or Gemini 2.0 Flash Lite offer more cost-effective alternatives.

Notes drafted by an LLM from the figures on this page (2026-05-21) and rewritten when the price changes.

Key facts

Price basis
Official API price
Max output
66K tokens
Listed on OpenRouter
2026-02-25
Tracked since
2026-05-08
Last updated
2026-11-10

Features

Image inputAudioFunction callingJSON outputReasoning

Monthly cost estimate

Scale Input (M) Output (M) Monthly
0.1M (hobby) 0.1 0.05 $0.80
1M (small app) 1 0.5 $8.00
10M (mid scale) 10 5 $80.00
100M (large) 100 50 $800.00

※ Cache and batch discounts not factored in. Detailed calculator

Official resources

Other models from Google AI

Similar-priced models

Source: OpenRouter API (google/gemini-3.1-pro-preview-customtools)