| Channel | Billing | Input | Output | Cache hit | Cache write |
|---|---|---|---|---|---|
| marketplace | Token | ¥0.0244 | ¥0.0488 | ¥0.0002 | - |
DeepSeek
DeepSeek V4 Pro
Performance close to top closed models
DeepSeek-V4-Pro significantly improves agent capability over prior generations and reaches leading open-model performance on agentic coding evaluations. It has rich world knowledge and performs competitively with top closed models on math, STEM, and competitive coding reasoning benchmarks.
Context1M
Released2026-04
Relays51 sites
Top open agentic codingRich world knowledgeMath and STEM reasoningStrong competitive coding
DeepSeek Official Pricing
CNYUpdated: 2026-04-01T00:00:00.000+08:00Source
Input
¥3/ 1M tokens
Output
¥6/ 1M tokens
Cache read
¥0.025/ 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 ¥0.225 / 1M tokens
| Channel | Billing | Input | Output | Cache hit | Cache write |
|---|---|---|---|---|---|
| deepseek-award | Token | ¥0.225 | ¥0.45 | ¥0.0019 | - |
Price range ¥0.261 / 1M tokens
| Channel | Billing | Input | Output | Cache hit | Cache write |
|---|---|---|---|---|---|
| deepseek | Token | ¥0.261 | ¥0.522 | - | - |
Price range ¥0.3 / 1M tokens
| Channel | Billing | Input | Output | Cache hit | Cache write |
|---|---|---|---|---|---|
| free | Token | ¥0.3 | ¥0.6 | ¥0.0025 | - |
Price range ¥0.55 / 1M tokens
| Channel | Billing | Input | Output | Cache hit | Cache write |
|---|---|---|---|---|---|
| Deepseek | Token | ¥0.55 | ¥1.04 | ¥0.0042 | ¥0 |
Price range ¥0.9 / 1M tokens
| Channel | Billing | Input | Output | Cache hit | Cache write |
|---|---|---|---|---|---|
| DeepSeek V4 | Token | ¥0.9 | ¥1.8 | ¥0.0075 | ¥1.13 |
Price range ¥0.9 / 1M tokens
国产大模型（Claude 协议）
BillingToken
Input¥0.9
Output¥1.8
Cache hit¥0.0011
Cache write-
国产大模型（OpenAI 协议）
BillingToken
Input¥0.9
Output¥1.8
Cache hit¥0.0011
Cache write-
| Channel | Billing | Input | Output | Cache hit | Cache write |
|---|---|---|---|---|---|
| 国产大模型（Claude 协议） | Token | ¥0.9 | ¥1.8 | ¥0.0011 | - |
| 国产大模型（OpenAI 协议） | Token | ¥0.9 | ¥1.8 | ¥0.0011 | - |
| Channel | Billing | Input | Output | Cache hit | Cache write |
|---|---|---|---|---|---|
| hvoy | Token | ¥1.2 | ¥2.4 | ¥0.24 | - |
Price range ¥1.2 / 1M tokens
| Channel | Billing | Input | Output | Cache hit | Cache write |
|---|---|---|---|---|---|
| default | Token | ¥1.2 | ¥2.4 | ¥0.012 | - |
国产模型
BillingToken
Input¥1.35
Output¥2.7
Cache hit¥0.0112
Cache write-
福利gpt
BillingToken
Input¥11.25
Output¥11.25
Cache hit-
Cache write-
| Channel | Billing | Input | Output | Cache hit | Cache write |
|---|---|---|---|---|---|
| 国产模型 | Token | ¥1.35 | ¥2.7 | ¥0.0112 | - |
| 福利gpt | Token | ¥11.25 | ¥11.25 | - | - |
How should DeepSeek V4 Pro relay pricing be compared?
This DeepSeek V4 Pro pricing page compares official pricing with public prices from 51 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: 08/02/2026, 08:13.
- 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.