Price range ¥0.06 / 1M tokens
| Channel | Billing | Input | Output | Cache hit | Cache write |
|---|---|---|---|---|---|
| Azure-GPT | Token | ¥0.06 | ¥0.48 | - | - |
GPT-5 mini
gpt-5-miniA 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
Relays12 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
CNYUpdated: 2026-10-04T22:55:12.772+08:00
Input
~¥1.672/ 1M tokens
Output
~¥13.379/ 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
Price range ¥0.0425 / 1M tokens
| 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 | - |
Price range ¥0.875 / 1M tokens
| Channel | Billing | Input | Output | Cache hit | Cache write |
|---|---|---|---|---|---|
| official-cheap | Token | ¥0.875 | ¥7 | ¥0.0875 | - |
Price range ¥0.0325 - ¥0.035 / 1M tokens
CodeX-不降智
BillingToken
Input¥0.0325
Output¥0.26
Cache hit¥0.0032
Cache write-
GPT-Pro-不降智
BillingToken
Input¥0.0325
Output¥0.26
Cache hit¥0.0032
Cache write-
GPT-福利分组
BillingToken
Input¥0.035
Output¥0.28
Cache hit¥0.0035
Cache write-
| Channel | Billing | Input | Output | Cache hit | Cache write |
|---|---|---|---|---|---|
| CodeX-不降智 | Token | ¥0.0325 | ¥0.26 | ¥0.0032 | - |
| GPT-Pro-不降智 | Token | ¥0.0325 | ¥0.26 | ¥0.0032 | - |
| GPT-福利分组 | Token | ¥0.035 | ¥0.28 | ¥0.0035 | - |
Price range ¥1.69 / 1M tokens
| Channel | Billing | Input | Output | Cache hit | Cache write |
|---|---|---|---|---|---|
| GPT 工作流 | Token | ¥1.69 | ¥13.52 | ¥0.1691 | - |
Price range ¥0.022 - ¥0.11 / 1M tokens
Azure-Gpt-1
BillingToken
Input¥0.022
Output¥0.176
Cache hit¥0.0022
Cache write-
Azure-Gpt-2
BillingToken
Input¥0.05
Output¥0.4
Cache hit¥0.005
Cache write-
Azure-Gpt-3
BillingToken
Input¥0.11
Output¥0.88
Cache hit¥0.011
Cache write-
| Channel | Billing | Input | Output | Cache hit | Cache write |
|---|---|---|---|---|---|
| Azure-Gpt-1 | Token | ¥0.022 | ¥0.176 | ¥0.0022 | - |
| Azure-Gpt-2 | Token | ¥0.05 | ¥0.4 | ¥0.005 | - |
| Azure-Gpt-3 | Token | ¥0.11 | ¥0.88 | ¥0.011 | - |
Price range ¥1.75 / 1M tokens
| Channel | Billing | Input | Output | Cache hit | Cache write |
|---|---|---|---|---|---|
| 正价Openai | Token | ¥1.75 | ¥14 | ¥0.175 | - |
Price range ¥0.675 - ¥1.01 / 1M tokens
default
BillingToken
Input¥0.675
Output¥5.4
Cache hit¥0.0675
Cache write-
Plus
BillingToken
Input¥1.01
Output¥8.1
Cache hit¥0.1013
Cache write-
| Channel | Billing | Input | Output | Cache hit | Cache write |
|---|---|---|---|---|---|
| default | Token | ¥0.675 | ¥5.4 | ¥0.0675 | - |
| Plus | Token | ¥1.01 | ¥8.1 | ¥0.1013 | - |
Price range ¥0.075 - ¥0.25 / 1M tokens
特价azure
BillingToken
Input¥0.075
Output¥0.6
Cache hit¥0.0075
Cache write-
Azure
BillingToken
Input¥0.15
Output¥1.2
Cache hit¥0.015
Cache write-
AzurePlus
BillingToken
Input¥0.25
Output¥2
Cache hit¥0.025
Cache write-
| 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 | - |
Price range ¥0.2 / 1M tokens
| Channel | Billing | Input | Output | Cache hit | Cache write |
|---|---|---|---|---|---|
| openai-官key | Token | ¥0.2 | ¥1.6 | ¥0.02 | - |
How should GPT-5 mini relay pricing be compared?
This GPT-5 mini pricing page compares official pricing with public prices from 12 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, 08:14.
- 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.