GPT-5 mini

gpt-5-mini

A lightweight GPT-5 model for responsive agents, coding help, and everyday automation

Small GPT-5 for responsive agents, coding help, and everyday automation

400K context400K context

Released2025-08-07

Relays14 sites

code generationreasoningtool uselong context

Model information

Model ID: gpt-5-mini
Context: 400K
Max input: 272K
Max output: 128K
Knowledge cutoff: 2024-05-30
Open weights: Not supported
License: -
Release date: 2025-08-07

Input

Text: SupportedImage: SupportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Supported

Output

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

API capabilities

Reasoning: SupportedTool call: SupportedStructured output: UnknownTemperature: Not supported

OpenAI Official Pricing

CNY

Updated: 2026-10-04T22:55:12.772+08:00

Input

~¥1.672/ 1M tokens

Output

~¥13.372/ 1M tokens

Cache read

~¥0.1672/ 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

9527code

https://9527.codesToken billing

Price range ¥0.75 / 1M tokens

Cache hit¥0.075

Channel	Billing	Input	Output	Cache hit	Cache write
Azure-GPT	Token	¥0.75	¥6	¥0.075	-

找模型

api.zhaomoxing.comToken billing

Price range ¥0.06 / 1M tokens

Channel	Billing	Input	Output	Cache hit	Cache write
Azure-GPT	Token	¥0.06	¥0.48	-	-

智流 FluxLane

fluxlane.cnToken billing

Price range ¥0.75 / 1M tokens

Cache hit¥0.075

Channel	Billing	Input	Output	Cache hit	Cache write
Open Ai官转	Token	¥0.75	¥6	¥0.075	-

池中鱼

poolai.chatToken billing

Price range ¥0.0425 / 1M tokens

chatgpt pro x20-官冲超稳定满血

Cache hit¥0.0043

Channel	Billing	Input	Output	Cache hit	Cache write
chatgpt pro x20-官冲超稳定满血	Token	¥0.0425	¥0.34	¥0.0043	-

token2u

https://token2u.ai/r/hovyToken billing

Price range ¥0.875 / 1M tokens

Cache hit¥0.0875

Channel	Billing	Input	Output	Cache hit	Cache write
official-cheap	Token	¥0.875	¥7	¥0.0875	-

LinoRoute

linoroute.comToken billing

Price range ¥0.121 - ¥0.3235 / 1M tokens

Cache hit¥0.0121

Cache hit¥0.0242

Cache hit¥0.0324

Channel	Billing	Input	Output	Cache hit	Cache write
Azure-Gpt-3	Token	¥0.121	¥0.968	¥0.0121	-
Azure-Gpt-4	Token	¥0.242	¥1.94	¥0.0242	-
Openai-Gpt-1	Token	¥0.3235	¥2.59	¥0.0324	-

XycAi(星道智能)

https://xycai.us/Token billing

Price range ¥1.69 / 1M tokens

Cache hit¥0.1691

Channel	Billing	Input	Output	Cache hit	Cache write
GPT 工作流	Token	¥1.69	¥13.52	¥0.1691	-

ClaudeCN

claudecn.topToken billing

Price range ¥1.75 / 1M tokens

Cache hit¥0.175

Cache write¥2.19

Channel	Billing	Input	Output	Cache hit	Cache write
正价Openai	Token	¥1.75	¥14	¥0.175	¥2.19

RunAPI

https://runapi.hostToken billing

Price range ¥0.675 - ¥1.01 / 1M tokens

Cache hit¥0.0675

Cache hit¥0.1013

Channel	Billing	Input	Output	Cache hit	Cache write
default	Token	¥0.675	¥5.4	¥0.0675	-
Plus	Token	¥1.01	¥8.1	¥0.1013	-

AIGC Token

aigc-token.comToken billing

Price range ¥0.075 - ¥0.25 / 1M tokens

Cache hit¥0.0075

Cache hit¥0.015

Cache hit¥0.025

Channel	Billing	Input	Output	Cache hit	Cache write
特价azure	Token	¥0.075	¥0.6	¥0.0075	-
Azure	Token	¥0.15	¥1.2	¥0.015	-
AzurePlus	Token	¥0.25	¥2	¥0.025	-

How should GPT-5 mini relay pricing be compared?

This GPT-5 mini pricing page compares official pricing with public prices from 14 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.