Skip to content
LLMs
Google logo

Google: Gemini 3.1 Pro Preview

by Google

Google: Gemini 3.1 Pro Preview is a large language model from Google. It costs $2.00 per million input tokens and $12.00 per million output tokens. Its context window is 1.0M tokens.

ReasoningTool callingStructured outputPrompt cachingBatch tieraudio inputfile inputimage inputvideo input
Input / 1M tokens
$2.00
Output / 1M tokens
$12.00
Cached input / 1M
$0.200

On repeated prefixes

Context window
1.0M

tokens

This model also charges $0.014 per search request

That is $14.00 per 1,000 requests, billed on top of the token prices above. On a typical 1,000-in / 500-out exchange the tokens cost $0.008, so the search fee is 1.8× the token cost. Per-token rankings elsewhere ignore this entirely.

Who serves it cheapest

2 hosts serve Gemini 3.1 Pro Preview. Same weights, same API - the price difference is pure margin and routing.

Providers serving Google: Gemini 3.1 Pro Preview, cheapest first
ProviderInput / 1MOutput / 1MContextThroughputUptime 24h
GoogleCheapest$1.00$6.001.0M-5.0%
Google AI Studio$1.00$6.001.0M-99.8%

The spread between Google and Google AI Studio is about the same for identical weights. Quantization and context limits differ, so check both columns before switching.

Benchmarks

Independent scores published alongside the catalogue.

Intelligence index
30.4
Coding index
68.8
Agentic index
10.3

About Gemini 3.1 Pro Preview

Gemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enhanced software engineering performance, improved agentic reliability, and more efficient token usage across complex workflows. Building on the multimodal foundation...

Specifications

Google: Gemini 3.1 Pro Preview specifications
Model IDgoogle/gemini-3.1-pro-preview
ProviderGoogle
Context window1.0M tokens
Max output66K tokens
Input modalitiesaudio, file, image, text, video
Output modalitiestext
Knowledge cutoff-
Open weightsNo
ReleasedFebruary 19, 2026

Cheaper alternatives

Models that cost less than Gemini 3.1 Pro Preview while keeping at least half its context window and every input modality it supports.

Frequently asked

How much does Google: Gemini 3.1 Pro Preview cost?

$2.00 per million input tokens and $12.00 per million output tokens. Cached input reads cost $0.200 per million tokens.

What is the context window of Google: Gemini 3.1 Pro Preview?

1.0M tokens, with up to 66K tokens of output per request.

Does Google: Gemini 3.1 Pro Preview have extra fees beyond per-token pricing?

Yes. Google: Gemini 3.1 Pro Preview charges $0.014 per search request - $14.00 per 1,000 requests - on top of $2.00 per million input tokens and $12.00 per million output tokens. On a typical 1,000-input / 500-output exchange the search fee alone is 1.8× the token cost.

Which provider serves Google: Gemini 3.1 Pro Preview cheapest?

Google at $1.00 per million input tokens - about the same cheaper than Google AI Studio, the most expensive of the 2 hosts serving it.

Confirm against the source: Google official pricing.