Price range ¥0.0675 / 1M tokens
| Channel | Billing | Input | Output | Cache hit | Cache write |
|---|---|---|---|---|---|
| Azure-GPT | Token | ¥0.0675 | ¥0.54 | - | - |
GPT-5 Nano
gpt-5-nanoA lightweight GPT-5 model for routing, extraction, classification, and bulk jobs.
Tiny GPT-5 lane for routing, extraction, classification, and bulk jobs
400K context400K context
Released2025-08-07
Relays10 sites
text generationreasoningtool uselong context
Model information
- Model ID
- gpt-5-nano
- 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: 2026-10-04T22:55:12.834+08:00
Input
~¥0.3345/ 1M tokens
Output
~¥2.676/ 1M tokens
Cache read
~¥0.0334/ 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 ¥0.175 / 1M tokens
| Channel | Billing | Input | Output | Cache hit | Cache write |
|---|---|---|---|---|---|
| official-cheap | Token | ¥0.175 | ¥1.4 | ¥0.0175 | - |
Price range ¥0.013 - ¥0.02 / 1M tokens
GPT-Pro 稳定 不降智
BillingToken
Input¥0.013
Output¥0.104
Cache hit¥0.0013
Cache write-
GPT - Fast 高速组（fast双倍计费，Ultrafast八倍）
BillingToken
Input¥0.02
Output¥0.16
Cache hit¥0.002
Cache write-
GPT-VIP企业专线 不降智
BillingToken
Input¥0.02
Output¥0.16
Cache hit¥0.002
Cache write-
| Channel | Billing | Input | Output | Cache hit | Cache write |
|---|---|---|---|---|---|
| GPT-Pro 稳定 不降智 | Token | ¥0.013 | ¥0.104 | ¥0.0013 | - |
| GPT - Fast 高速组（fast双倍计费，Ultrafast八倍） | Token | ¥0.02 | ¥0.16 | ¥0.002 | - |
| GPT-VIP企业专线 不降智 | Token | ¥0.02 | ¥0.16 | ¥0.002 | - |
Price range ¥0.3381 / 1M tokens
| Channel | Billing | Input | Output | Cache hit | Cache write |
|---|---|---|---|---|---|
| GPT 工作流 | Token | ¥0.3381 | ¥2.7 | ¥0.0338 | - |
Price range ¥0.022 - ¥0.0588 / 1M tokens
Azure-Gpt-3
BillingToken
Input¥0.022
Output¥0.176
Cache hit¥0.0022
Cache write-
Azure-Gpt-4
BillingToken
Input¥0.044
Output¥0.352
Cache hit¥0.0044
Cache write-
Openai-Gpt-1
BillingToken
Input¥0.0588
Output¥0.4706
Cache hit¥0.0059
Cache write-
| Channel | Billing | Input | Output | Cache hit | Cache write |
|---|---|---|---|---|---|
| Azure-Gpt-3 | Token | ¥0.022 | ¥0.176 | ¥0.0022 | - |
| Azure-Gpt-4 | Token | ¥0.044 | ¥0.352 | ¥0.0044 | - |
| Openai-Gpt-1 | Token | ¥0.0588 | ¥0.4706 | ¥0.0059 | - |
Price range ¥0.35 / 1M tokens
| Channel | Billing | Input | Output | Cache hit | Cache write |
|---|---|---|---|---|---|
| 正价Openai | Token | ¥0.35 | ¥2.8 | ¥0.035 | - |
Price range ¥0.135 - ¥0.2025 / 1M tokens
default
BillingToken
Input¥0.135
Output¥1.08
Cache hit¥0.0135
Cache write-
Plus
BillingToken
Input¥0.2025
Output¥1.62
Cache hit¥0.0203
Cache write-
| Channel | Billing | Input | Output | Cache hit | Cache write |
|---|---|---|---|---|---|
| default | Token | ¥0.135 | ¥1.08 | ¥0.0135 | - |
| Plus | Token | ¥0.2025 | ¥1.62 | ¥0.0203 | - |
Price range ¥0.015 - ¥0.05 / 1M tokens
特价azure
BillingToken
Input¥0.015
Output¥0.12
Cache hit¥0.0015
Cache write-
Azure
BillingToken
Input¥0.03
Output¥0.24
Cache hit¥0.003
Cache write-
AzurePlus
BillingToken
Input¥0.05
Output¥0.4
Cache hit¥0.005
Cache write-
| Channel | Billing | Input | Output | Cache hit | Cache write |
|---|---|---|---|---|---|
| 特价azure | Token | ¥0.015 | ¥0.12 | ¥0.0015 | - |
| Azure | Token | ¥0.03 | ¥0.24 | ¥0.003 | - |
| AzurePlus | Token | ¥0.05 | ¥0.4 | ¥0.005 | - |
Price range ¥0.04 / 1M tokens
| Channel | Billing | Input | Output | Cache hit | Cache write |
|---|---|---|---|---|---|
| openai-官key | Token | ¥0.04 | ¥0.32 | ¥0.004 | - |
openai-mix
BillingToken
Input¥0.0525
Output¥0.42
Cache hit¥0.0053
Cache write-
openai-official-cheap
BillingToken
Input¥0.1855
Output¥1.48
Cache hit¥0.0186
Cache write-
azure
BillingToken
Input¥0.35
Output¥2.8
Cache hit¥0.035
Cache write-
| Channel | Billing | Input | Output | Cache hit | Cache write |
|---|---|---|---|---|---|
| openai-mix | Token | ¥0.0525 | ¥0.42 | ¥0.0053 | - |
| openai-official-cheap | Token | ¥0.1855 | ¥1.48 | ¥0.0186 | - |
| azure | Token | ¥0.35 | ¥2.8 | ¥0.035 | - |
How should GPT-5 Nano relay pricing be compared?
This GPT-5 Nano pricing page compares official pricing with public prices from 10 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.