| Channel | Billing | Input | Output | Cache hit | Cache write |
|---|---|---|---|---|---|
| hvoy | Token | ¥0.6 | ¥1.8 | ¥0.02 | - |
DeepSeek
DeepSeek V4 Flash
A faster, more economical option
DeepSeek V4 Flash was an economical fast model with 1M context. It is officially retired: the deepseek-v4-flash name still works, but requests are served by DeepSeek V4.1 Flash and billed at Flash pricing.
Context window1M
Released2026-04
Relays68 sites
Economical API serviceNear-Pro reasoningStrong simple-agent performanceLower latency and cost
DeepSeek Official Pricing
CNYUpdated: 2026-04-01T00:00:00.000+08:00Source
Input
¥1/ 1M tokens
Output
¥2/ 1M tokens
Cache read
¥0.02/ 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 ¥0.7 - ¥1 / 1M tokens
deepseek-sale
BillingToken
Input¥0.7
Output¥1.4
Cache hit¥0.014
Cache write-
default
BillingToken
Input¥1
Output¥2
Cache hit¥0.02
Cache write-
| Channel | Billing | Input | Output | Cache hit | Cache write |
|---|---|---|---|---|---|
| deepseek-sale | Token | ¥0.7 | ¥1.4 | ¥0.014 | - |
| default | Token | ¥1 | ¥2 | ¥0.02 | - |
Price range ¥0.9014 / 1M tokens
| Channel | Billing | Input | Output | Cache hit | Cache write |
|---|---|---|---|---|---|
| DeepSeek 原生官方 | Token | ¥0.9014 | ¥3.61 | ¥0.018 | - |
Price range ¥1.73 / 1M tokens
| Channel | Billing | Input | Output | Cache hit | Cache write |
|---|---|---|---|---|---|
| deepseek-stable | Token | ¥1.73 | ¥5.19 | ¥0.0577 | - |
Price range ¥0.4019 / 1M tokens
国模2折福利
BillingToken
Input¥0.4019
Output¥1.61
Cache hit¥0.008
Cache write¥0
国模福利-chat端点
BillingToken
Input¥0.4019
Output¥1.61
Cache hit¥0.008
Cache write¥0
国模福利-messages端点
BillingToken
Input¥0.4019
Output¥1.61
Cache hit¥0.008
Cache write¥0
| Channel | Billing | Input | Output | Cache hit | Cache write |
|---|---|---|---|---|---|
| 国模2折福利 | Token | ¥0.4019 | ¥1.61 | ¥0.008 | ¥0 |
| 国模福利-chat端点 | Token | ¥0.4019 | ¥1.61 | ¥0.008 | ¥0 |
| 国模福利-messages端点 | Token | ¥0.4019 | ¥1.61 | ¥0.008 | ¥0 |
Price range ¥0.15 - ¥0.9 / 1M tokens
free
BillingToken
Input¥0.15
Output¥0.45
Cache hit¥0.005
Cache write-
国产官方模型
BillingToken
Input¥0.9
Output¥2.7
Cache hit¥0.03
Cache write-
| Channel | Billing | Input | Output | Cache hit | Cache write |
|---|---|---|---|---|---|
| free | Token | ¥0.15 | ¥0.45 | ¥0.005 | - |
| 国产官方模型 | Token | ¥0.9 | ¥2.7 | ¥0.03 | - |
Price range ¥1.5 - ¥1.8 / 1M tokens
国产模型-oai
BillingToken
Input¥1.5
Output¥4.5
Cache hit¥0.05
Cache write-
DeepSeek
BillingToken
Input¥1.8
Output¥5.4
Cache hit¥0.06
Cache write-
| Channel | Billing | Input | Output | Cache hit | Cache write |
|---|---|---|---|---|---|
| 国产模型-oai | Token | ¥1.5 | ¥4.5 | ¥0.05 | - |
| DeepSeek | Token | ¥1.8 | ¥5.4 | ¥0.06 | - |
Price range ¥0.75 - ¥1.05 / 1M tokens
Deepseek开源
BillingToken
Input¥0.75
Output¥2.25
Cache hit¥0.025
Cache write-
Deepseek官转
BillingToken
Input¥1.05
Output¥3.15
Cache hit¥0.035
Cache write-
| Channel | Billing | Input | Output | Cache hit | Cache write |
|---|---|---|---|---|---|
| Deepseek开源 | Token | ¥0.75 | ¥2.25 | ¥0.025 | - |
| Deepseek官转 | Token | ¥1.05 | ¥3.15 | ¥0.035 | - |
Price range ¥0.6 - ¥0.8 / 1M tokens
Deepseek-满血版-余额
BillingToken
Input¥0.6
Output¥2.4
Cache hit¥0.012
Cache write¥0
Deepseek-量化版-余额
BillingToken
Input¥0.8
Output¥3.2
Cache hit¥0.016
Cache write¥0
| Channel | Billing | Input | Output | Cache hit | Cache write |
|---|---|---|---|---|---|
| Deepseek-满血版-余额 | Token | ¥0.6 | ¥2.4 | ¥0.012 | ¥0 |
| Deepseek-量化版-余额 | Token | ¥0.8 | ¥3.2 | ¥0.016 | ¥0 |
Price range ¥0.7 / 1M tokens
| Channel | Billing | Input | Output | Cache hit | Cache write |
|---|---|---|---|---|---|
| deepseek-promotion | Token | ¥0.7 | ¥2.8 | ¥0.014 | - |
How should DeepSeek V4 Flash relay pricing be compared?
This DeepSeek V4 Flash pricing page compares official pricing with public prices from 68 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: 09/20/2026, 23:14.
- 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.