Skip to main content
Deep Infra logo

Gemini 2.5 Pro API pricing on Deep Infra

Every Deep Infra Gemini 2.5 Pro rate we track, compared against 6 providers serving the same model.

Input from /1M
$1.25
Output /1M
$10.00
Input price rank
#2 of 6
Last updated
November 21, 2026

The cheapest Gemini 2.5 Pro input price we currently track is $1.25/1M on Liquid Inference.

The cheapest Gemini 2.5 Pro output price is $9.98/1M on Liquid Inference.

Deep Infra Gemini 2.5 Pro rates

Prices per 1M tokens. Batch and cached-input rates are shown where the provider publishes them.

Deep Infra Gemini 2.5 Pro pricing by mode
ModeInputOutput
Standard$1.25/1M$10.00/1M

About Gemini 2.5 Pro

Creator
Google
Context
1.0M
Modalities
text, image, video, audio
Tool calling
Yes
Full Gemini 2.5 Pro details and every provider →Compare API pricing for every Gemini model →

Gemini 2.5 Pro on other providers

About Deep Infra

Deep Infra is an AI inference cloud that provides serverless APIs for 100+ models and dedicated GPU rentals. Features OpenAI-compatible endpoints, custom model deployments, and infrastructure optimized for scale.

Frequently Asked Questions

How much does Gemini 2.5 Pro cost on Deep Infra?

Deep Infra serves Gemini 2.5 Pro from $1.25 per 1M input tokens, across 1 tracked pricing mode. Prices are collected daily — see the table above for current input, output, and cached-input rates.

Is Deep Infra the cheapest way to run Gemini 2.5 Pro?

Deep Infra ranks #2 of 6 providers we track serving Gemini 2.5 Pro on input price. The cheapest input price right now is on Liquid Inference. The lowest output price is $9.98/1M on Liquid Inference. Rates change often, and throughput, latency and context limits differ between providers — check the comparison above before committing.

Does Deep Infra offer batch or cached pricing for Gemini 2.5 Pro?

We track 1 Gemini 2.5 Pro offering from Deep Infra. Batch and cached-input rates appear in the table above when the provider publishes them; blank cells mean we have no current figure for that mode.