GPT-5.4 Mini

gpt-5.4-mini

A strong small GPT for coding subagents, quick tool use, and high-volume work.

Strong small GPT for coding subagents, quick tool use, and high-volume work

400K context400K context

Released2026-03-17

Relays36 sites

code generationtool usereasoning

Model information

Model ID: gpt-5.4-mini
Context: 400K
Max input: 272K
Max output: 128K
Knowledge cutoff: 2025-08-31
Open weights: Not supported
License: -
Release date: 2026-03-17

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: Supported

OpenAI Official Pricing

CNY

Updated: 2026-10-04T22:55:12.956+08:00

Input

~¥5.017/ 1M tokens

Output

~¥30.102/ 1M tokens

Cache read

~¥0.5017/ 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

ToTokens

totokens.ccToken billing

Price range ¥0.09 - ¥0.1485 / 1M tokens

Cache hit¥0.009

gpt-plus-优惠

Cache hit¥0.0134

Cache hit¥0.0149

Channel	Billing	Input	Output	Cache hit	Cache write
gpt系列	Token	¥0.09	¥0.54	¥0.009	-
gpt-plus-优惠	Token	¥0.1335	¥0.801	¥0.0134	-
高精尖	Token	¥0.1485	¥0.891	¥0.0149	-

合聚API

hejuapi.comToken billing

Price range ¥5.25 / 1M tokens

Cache hit¥0.525

Channel	Billing	Input	Output	Cache hit	Cache write
GPT 官方 API	Token	¥5.25	¥31.5	¥0.525	-

sidrune

https://sidrune.ai/Token billing

Price range ¥0.15 - ¥0.375 / 1M tokens

Cache hit¥0.015

GPT-Pro优选-余额

Cache hit¥0.0225

GPT-OpenAI官Key逆-余额

Cache hit¥0.0375

Channel	Billing	Input	Output	Cache hit	Cache write
GPT-Pro-余额	Token	¥0.15	¥0.9	¥0.015	-
GPT-Pro优选-余额	Token	¥0.225	¥1.35	¥0.0225	-
GPT-OpenAI官Key逆-余额	Token	¥0.375	¥2.25	¥0.0375	-

灵算

https://lingsuan.siToken billing

Price range ¥0.1 - ¥0.3 / 1M tokens

cx-稳定官池

Channel	Billing	Input	Output	Cache hit	Cache write
cx-pro	Token	¥0.1	¥0.9	¥0	-
cx-稳定官池	Token	¥0.1	¥0.6	¥0	-
cx-vip专线	Token	¥0.3	¥1.8	¥0	-

云渡

https://yundu.lolToken billing

Price range ¥0.1 / 1M tokens

Channel	Billing	Input	Output	Cache hit	Cache write
codex	Token	¥0.1	¥0.6	-	-
codex-pro	Token	¥0.1	¥0.8	-	-

词易

chiyicn.comToken billing

Price range ¥0.1 / 1M tokens

codex - plus号池 - 特惠 - 85+缓（禁止破甲，蒸馏，发现直接封号）

Cache hit¥0.015

codex - pro号池 - 稳定 - 90+缓（禁止破甲，蒸馏，发现直接封号）

Cache hit¥0.0195

codex - 福利版 - 低缓存

Cache hit¥0.0105

Channel	Billing	Input	Output	Cache hit	Cache write
codex - plus号池 - 特惠 - 85+缓（禁止破甲，蒸馏，发现直接封号）	Token	¥0.1	¥0.9	¥0.015	-
codex - pro号池 - 稳定 - 90+缓（禁止破甲，蒸馏，发现直接封号）	Token	¥0.1	¥1.1	¥0.0195	-
codex - 福利版 - 低缓存	Token	¥0.1	¥0.6	¥0.0105	-

OmniaKey

omniakey.comToken billing

Price range ¥1.31 / 1M tokens

Cache hit¥0.13

Cache write¥2.06

Channel	Billing	Input	Output	Cache hit	Cache write
default	Token	¥1.31	¥7.88	¥0.13	¥2.06

木易(MueMod)

muemod.topToken billing

Price range ¥0.1 - ¥0.3 / 1M tokens

Channel	Billing	Input	Output	Cache hit	Cache write
cx-pro	Token	¥0.1	¥0.9	¥0	-
cx-福利	Token	¥0.1	¥0.6	¥0	-
cx-vip专线	Token	¥0.3	¥1.8	¥0	-

tokenshop

tokenshop.homesToken billing

Price range ¥0.0367 - ¥0.0938 / 1M tokens

Cache hit¥0.0037

【不弱智】- 上限0.15

Cache hit¥0.0094

Channel	Billing	Input	Output	Cache hit	Cache write
福利	Token	¥0.0367	¥0.2205	¥0.0037	-
【不弱智】- 上限0.15	Token	¥0.0938	¥0.5625	¥0.0094	-

找模型

api.zhaomoxing.comToken billing

Price range ¥0.5625 / 1M tokens

Cache hit¥0.0563

Channel	Billing	Input	Output	Cache hit	Cache write
Azure-GPT	Token	¥0.5625	¥3.38	¥0.0563	-

How should GPT-5.4 Mini relay pricing be compared?

This GPT-5.4 Mini pricing page compares official pricing with public prices from 36 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: 10/23/2026, 08:16.

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.