Gemini 2.5 Pro

gemini-2.5-pro

A proven reasoning model for coding, math, and multimodal analysis

Google's proven reasoning model for coding, math, and multimodal analysis

1M context1M context

Released2025-06-17

Relays20 sites

reasoningcode generationmultimodal

Model information

Model ID: gemini-2.5-pro
Context: 1M
Max input: -
Max output: 65.5K
Knowledge cutoff: 2025-01
Open weights: Not supported
License: -
Release date: 2025-06-17

Input

Text: SupportedImage: SupportedAudio: SupportedVideo: SupportedPDF: SupportedFile: Supported

Output

Text: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported

API capabilities

Reasoning: SupportedTool call: SupportedStructured output: UnknownTemperature: Supported

Google Official Pricing

CNY

Updated: 2026-10-04T22:55:11.555+08:00

Input

~¥8.358/ 1M tokens

Output

~¥66.861/ 1M tokens

Cache read

~¥0.8358/ 1M tokens

Relay Comparison

Compare token, per-request, or per-second pricing by relay channel.

Unit: token prices are ¥ / 1M tokens; per-request and per-second rows use their shown unit

词易

chiyicn.comToken billing

Price range ¥0.5 - ¥1 / 1M tokens

Cache hit¥0.05

Cache write¥0.5

Gemini - Ultra特惠 - Vertex|官转（4模型稳定可用）

Channel	Billing	Input	Output	Cache hit	Cache write
Gmini - 特惠	Token	¥0.5	¥4	¥0.05	¥0.5
Gemini - Ultra特惠 - Vertex\|官转（4模型稳定可用）	Token	¥1	¥8	¥0.1	¥1

天枢

tian-shu.netToken billing

Price range ¥0.525 / 1M tokens

Cache hit¥0.0525

Channel	Billing	Input	Output	Cache hit	Cache write
gemini	Token	¥0.525	¥4.2	¥0.0525	-

智流 FluxLane

fluxlane.cnToken billing

Price range ¥0.5 - ¥3.13 / 1M tokens

Cache hit¥0.05

Cache hit¥0.3125

Channel	Billing	Input	Output	Cache hit	Cache write
Gemini CLI	Token	¥0.5	¥4	¥0.05	-
Gemini Vertex	Token	¥3.13	¥25	¥0.3125	-

sudocode.us

sudocode.usToken billing

Price range ¥6.69 / 1M tokens

Cache hit¥0.669

Channel	Billing	Input	Output	Cache hit	Cache write
特供2	Token	¥6.69	¥53.52	¥0.669	-

Volt

https://voltapi.ai/Token billing

Price range ¥0.75 / 1M tokens

Gemini（OpenAI 协议）

Cache hit¥0.075

Cache write¥0.75

Channel	Billing	Input	Output	Cache hit	Cache write
Gemini（OpenAI 协议）	Token	¥0.75	¥6	¥0.075	¥0.75

UU API

uuapi.ioToken billing

Price range ¥3.5 / 1M tokens

GEMINI官方直连-带生图

Cache hit¥0.35

Cache write¥3.5

Channel	Billing	Input	Output	Cache hit	Cache write
GEMINI官方直连-带生图	Token	¥3.5	¥28	¥0.35	¥3.5

元初AI

ai.yuanc.icuToken billing

Price range ¥0.25 / 1M tokens

Gemini 反重力

Cache hit¥0.025

Cache write¥0.25

Channel	Billing	Input	Output	Cache hit	Cache write
Gemini 反重力	Token	¥0.25	¥2	¥0.025	¥0.25

LinoRoute

linoroute.comToken billing

Price range ¥0.825 - ¥2.48 / 1M tokens

Vertex-Gemini-2

Cache hit¥0.0825

Vertex-Gemini-3

Cache hit¥0.2475

Channel	Billing	Input	Output	Cache hit	Cache write
Vertex-Gemini-2	Token	¥0.825	¥6.6	¥0.0825	-
Vertex-Gemini-3	Token	¥2.48	¥19.8	¥0.2475	-

RunAPI

https://runapi.hostToken billing

Price range ¥1.82 - ¥5.47 / 1M tokens

Cache hit¥0.1822

Cache hit¥0.3645

Cache hit¥0.5467

Channel	Billing	Input	Output	Cache hit	Cache write
discounts	Token	¥1.82	¥14.58	¥0.1822	-
default	Token	¥3.65	¥29.16	¥0.3645	-
Plus	Token	¥5.47	¥43.74	¥0.5467	-

Modelsell

modelsell.comToken billing

Price range ¥4.25 - ¥5.95 / 1M tokens

Google AI Studio

Cache hit¥0.425

Cache hit¥0.595

Channel	Billing	Input	Output	Cache hit	Cache write
Google AI Studio	Token	¥4.25	¥34	¥0.425	-
Google Vertex	Token	¥5.95	¥47.6	¥0.595	-

How should Gemini 2.5 Pro relay pricing be compared?

This Gemini 2.5 Pro pricing page compares official pricing with public prices from 20 listed AI gateways. Token prices are shown in CNY per 1M tokens, while per-request, per-second, and per-character rows use the unit shown in the table. Last updated: 11/08/2026, 08:15.

Data sources: Public price catalogs, official pricing records, and monitoring results.
Metric definitions: Uptime means successful probe response rate, fake-rate signals possible model mismatch or abnormal output risk, and latency is average API response time.
Risk note: Relay gateways are third-party services. Pricing, billing, privacy, and stability can change; start with a small top-up and verify reliability before continued use.