What the DeepSeek API costs. And the same models with no peak hours.
DeepSeek charges double on weekdays from 01:00 to 04:00 and 06:00 to 10:00 UTC. On APIsRouter, DeepSeek V4.1 Flash and DeepSeek V4 Pro cost 13 to 24% less than DeepSeek's off-peak price, at every hour.
DeepSeek V4 Pro output, per million tokens, each hour of a weekday
- DeepSeek peak: $3.96
- DeepSeek off-peak: $1.98
- APIsRouter, every hour: $1.50
DeepSeek API prices, per million tokens
Our price sits under DeepSeek's off-peak price on every token type, and 56 to 62% under its peak price. DeepSeek prices from api-docs.deepseek.com/quick_start/pricing, September 2026.
| Model | Input, cache hit: DeepSeek off-peak / DeepSeek peak / APIsRouter | Input, cache miss: DeepSeek off-peak / DeepSeek peak / APIsRouter | Output: DeepSeek off-peak / DeepSeek peak / APIsRouter |
|---|---|---|---|
| DeepSeek V4.1 Flash | $0.003 / $0.006 / $0.0025 | $0.15 / $0.30 / $0.13 | $0.60 / $1.20 / $0.50 |
| DeepSeek V4 Pro | $0.022 / $0.044 / $0.019 | $0.66 / $1.32 / $0.55 | $1.98 / $3.96 / $1.50 |
When DeepSeek's peak hours are
- Monday to Friday, 01:00 to 04:00 and 06:00 to 10:00 UTC. That is 09:00 to 12:00 and 14:00 to 18:00 in Beijing, the working day in China.
- Weekends and Chinese public holidays are off-peak all day, and off-peak costs half of peak.
- APIsRouter has no peak hours: the prices above hold around the clock, every day.
Switch with one line
- Get a key: Top up from $10 below. The key and a login link arrive by email.
- Point the OpenAI SDK at APIsRouter: Set base_url to https://api.apisrouter.com/v1 and the model to deepseek-v4.1-flash or deepseek-v4-pro.
- Send requests: Every request shows up in your console with its tokens and cost.
from openai import OpenAI
client = OpenAI(
base_url="https://api.apisrouter.com/v1",
api_key="sk-your-apisrouter-key",
)
reply = client.chat.completions.create(
model="deepseek-v4-pro",
messages=[{"role": "user", "content": "Hello"}],
)
print(reply.choices[0].message.content)Two ways to pay
Both fill one balance, spent at the prices above. Pay as you go from $10 with no account, with +30% on the first top-up.
FAQ
How much does the DeepSeek API cost?
DeepSeek V4.1 Flash costs $0.15 / $0.60 per million input and output tokens off-peak and $0.30 / $1.20 at peak. DeepSeek V4 Pro costs $0.66 / $1.98 off-peak and $1.32 / $3.96 at peak. On APIsRouter they cost $0.13 / $0.50 and $0.55 / $1.50 at every hour.
Can I try it for free?
Yes. Sign in with your email or Google and claim a $2 trial credit from your dashboard, no card needed. When it runs out, top up from $10.
When are DeepSeek's peak hours?
Monday to Friday, 01:00 to 04:00 and 06:00 to 10:00 UTC, which is 09:00 to 12:00 and 14:00 to 18:00 in Beijing. Weekends and Chinese public holidays are off-peak all day.
How is cached input billed?
Input that repeats a recent prompt prefix bills at the cache hit price: $0.022 off-peak and $0.044 at peak per million on DeepSeek V4 Pro, $0.019 on APIsRouter.
DeepSeek V4.1 Flash or DeepSeek V4 Pro?
Start with DeepSeek V4.1 Flash for chat, extraction and high-volume work, at $0.13 / $0.50 per million tokens here. Move to DeepSeek V4 Pro, at $0.55 / $1.50, when answers need deeper reasoning.
Which model IDs do I use?
deepseek-v4.1-flash and deepseek-v4-pro. DeepSeek's own API names them deepseek-flash and deepseek-v4-pro.
Can I keep using the OpenAI SDK?
Yes. Set base_url (baseURL in Node) to https://api.apisrouter.com/v1 and use your APIsRouter key. Streaming and tool calls work as before.