| Channel | Billing | Input | Output | Cache hit | Cache write |
|---|---|---|---|---|---|
| hvoy | Token | ¥0.15 | ¥0.45 | ¥0.005 | - |
DeepSeek
DeepSeek V4.1 Flash
First CED-architecture sparse MoE, successor to retired V4 Flash
DeepSeek V4.1 Flash is DeepSeek's first sparse-MoE model on the Causal Encoder-Decoder (CED) architecture, served as deepseek-flash, with 1M context, up to 384K output, thinking/non-thinking modes, and vision input. The retired deepseek-v4-flash name still works, and those requests are now served by V4.1 Flash at Flash pricing.
1M Token context1M
Released2026-09
Relays57 sites
Economical API serviceCED architectureMultimodalThinking mode1M context384K output
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 ¥1.3 / 1M tokens
| Channel | Billing | Input | Output | Cache hit | Cache write |
|---|---|---|---|---|---|
| deepseek-stable | Token | ¥1.3 | ¥5.21 | ¥0.0261 | - |
Price range ¥0.5 / 1M tokens
| Channel | Billing | Input | Output | Cache hit | Cache write |
|---|---|---|---|---|---|
| znb-deepseek-v4.1-flash | Token | ¥0.5 | ¥2 | ¥0.01 | - |
Price range ¥0.6 / 1M tokens
Deepseek
BillingToken
Input¥0.6
Output¥2.4
Cache hit¥0.012
Cache write-
default
BillingToken
Input¥0.6
Output¥2.4
Cache hit¥0.012
Cache write-
| Channel | Billing | Input | Output | Cache hit | Cache write |
|---|---|---|---|---|---|
| Deepseek | Token | ¥0.6 | ¥2.4 | ¥0.012 | - |
| default | Token | ¥0.6 | ¥2.4 | ¥0.012 | - |
国模全家桶-openai接口
BillingToken
Input¥0.3
Output¥1.2
Cache hit¥0.015
Cache write-
国模高缓存-openai接口
BillingToken
Input¥0.6
Output¥2.4
Cache hit¥0.03
Cache write-
国模高缓存-openai接口
BillingToken
Input¥1.2
Output¥4.8
Cache hit¥0.024
Cache write-
| Channel | Billing | Input | Output | Cache hit | Cache write |
|---|---|---|---|---|---|
| 国模全家桶-openai接口 | Token | ¥0.3 | ¥1.2 | ¥0.015 | - |
| 国模高缓存-openai接口 | Token | ¥0.6 | ¥2.4 | ¥0.03 | - |
| 国模高缓存-openai接口 | Token | ¥1.2 | ¥4.8 | ¥0.024 | - |
Price range ¥0.5 - ¥0.7 / 1M tokens
Deepseek开源
BillingToken
Input¥0.5
Output¥2
Cache hit¥0.01
Cache write-
Deepseek官转
BillingToken
Input¥0.7
Output¥2.8
Cache hit¥0.014
Cache write-
| Channel | Billing | Input | Output | Cache hit | Cache write |
|---|---|---|---|---|---|
| Deepseek开源 | Token | ¥0.5 | ¥2 | ¥0.01 | - |
| Deepseek官转 | Token | ¥0.7 | ¥2.8 | ¥0.014 | - |
Price range ¥0.4 / 1M tokens
| Channel | Billing | Input | Output | Cache hit | Cache write |
|---|---|---|---|---|---|
| deepseek-promotion | Token | ¥0.4 | ¥1.6 | ¥0.008 | - |
Price range ¥0.25 / 1M tokens
| Channel | Billing | Input | Output | Cache hit | Cache write |
|---|---|---|---|---|---|
| DeepSeek(高缓) | Token | ¥0.25 | ¥1 | ¥0.005 | ¥0 |
Price range ¥0.3 - ¥1 / 1M tokens
国模
BillingToken
Input¥0.3
Output¥1.2
Cache hit¥0.006
Cache write-
国模-原厂
BillingToken
Input¥1
Output¥4
Cache hit¥0.02
Cache write-
| Channel | Billing | Input | Output | Cache hit | Cache write |
|---|---|---|---|---|---|
| 国模 | Token | ¥0.3 | ¥1.2 | ¥0.006 | - |
| 国模-原厂 | Token | ¥1 | ¥4 | ¥0.02 | - |
Price range ¥1 / 1M tokens
| Channel | Billing | Input | Output | Cache hit | Cache write |
|---|---|---|---|---|---|
| 国产模型聚合专区 | Token | ¥1 | ¥4 | ¥0.02 | ¥1 |
How should DeepSeek V4.1 Flash relay pricing be compared?
This DeepSeek V4.1 Flash pricing page compares official pricing with public prices from 57 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.