Gemini 3.1 Pro Preview API Cost Calculator

Google's Gemini 3.1 Pro Preview: $2/M input · $12/M output · $0.2/M cached input. Price your own workload below.

Prompts over 200K tokens: $4 in / $18 out. Cache storage $4.50/MTok/hour.

Presets:

What Gemini 3.1 Pro Preview costs in practice

WorkloadInputOutputCost
Short chat message500250$0.0040
10-page document + summary7,000500$0.020
Agent / coding session50,00010,000$0.220
1M tokens in + 1M out1,000,0001,000,000$14.00

Gemini 3.1 Pro Preview vs nearest rivals

Closest-priced alternatives on a mixed 10K-input / 2K-output request:

ModelInput $/MTokOutput $/MTokMixed request
Gemini 3.1 Pro Preview$2$12$0.044
Claude Sonnet 5$2$10$0.040
GPT-5.6 Terra$2$12$0.044
GPT-4o$2.5$10$0.045

Frequently asked questions

How much does the Gemini 3.1 Pro Preview API cost?

Gemini 3.1 Pro Preview costs $2 per million input tokens and $12 per million output tokens, with cached input at $0.2 per million (90% off). Note: Prompts over 200K tokens: $4 in / $18 out. Cache storage $4.50/MTok/hour.

How much does a typical chat message cost with Gemini 3.1 Pro Preview?

A short chat message (about 500 input and 250 output tokens) costs roughly $0.0040 with Gemini 3.1 Pro Preview. At 1,000 such requests a day, that is about $120.00 per month.

Is Gemini 3.1 Pro Preview cheap compared to similar models?

Gemini 3.1 Pro Preview has the #17 cheapest input rate of the 26 models we track. On a mixed workload (10K input / 2K output), it costs $0.044 per request, versus $0.040 for Claude Sonnet 5 and $0.045 for GPT-4o.

Related

Compare all models at once ·Count tokens in your prompt

Last updated 2026-08-03. Prices verified againstGoogle's official pricing page; see themethodology.