DeepSeek API at 55% off
For your own product, backend, script or mini app. Keep the OpenAI or Anthropic SDK you already use and change two lines: the base URL and the key.
Verify your email and get $0.50 of balance
| Model | Input, cache hit | Input, cache miss | Output | |
|---|---|---|---|---|
| DeepSeek V4.1 Flash | DeepSeek, peak hours | $0.006 | $0.3 | $1.2 |
| DeepSeek, off-peak | $0.003 | $0.15 | $0.6 | |
| HaryAI | $0.003 | $0.135 | $0.54 | |
| DeepSeek V4 Pro | DeepSeek, peak hours | $0.044 | $1.32 | $3.96 |
| DeepSeek, off-peak | $0.022 | $0.66 | $1.98 | |
| HaryAI | $0.022 | $0.594 | $1.782 |
In your code
Put your key in the HARYAI_KEY environment variable. The model names are deepseek-flash and deepseek-v4-pro.
import os
from openai import OpenAI
client = OpenAI(base_url="https://api.haryai.com/v1", api_key=os.environ["HARYAI_KEY"])
reply = client.chat.completions.create(
model="deepseek-flash",
messages=[{"role": "user", "content": "Hello"}],
)
print(reply.choices[0].message.content)import OpenAI from "openai";
const client = new OpenAI({ baseURL: "https://api.haryai.com/v1", apiKey: process.env.HARYAI_KEY });
const reply = await client.chat.completions.create({
model: "deepseek-flash",
messages: [{ role: "user", content: "Hello" }],
});
console.log(reply.choices[0].message.content);curl https://api.haryai.com/v1/chat/completions \
-H "Authorization: Bearer $HARYAI_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "deepseek-flash", "messages": [{"role": "user", "content": "Hello"}]}'stream = client.chat.completions.create(
model="deepseek-flash",
messages=[{"role": "user", "content": "Hello"}],
stream=True,
)
for chunk in stream:
print(chunk.choices[0].delta.content or "", end="")import os
import anthropic
client = anthropic.Anthropic(base_url="https://api.haryai.com", api_key=os.environ["HARYAI_KEY"])
msg = client.messages.create(
model="deepseek-flash",
max_tokens=1024,
messages=[{"role": "user", "content": "Hello"}],
)
print(msg.content[0].text)Running it in production
OpenAI and Anthropic compatible
Chat Completions and Responses at https://api.haryai.com/v1, Anthropic Messages at https://api.haryai.com.
The models
| DeepSeek V4.1 Flash | DeepSeek V4 Pro | |
|---|---|---|
| Model name | deepseek-flash | deepseek-v4-pro |
| Served by | DeepSeek-V4.1-Flash-1017 | DeepSeek-V4-Pro-0813 |
| Context | 1M | 1M |
| Max output | 384K | 384K |
| Image input | Yes | No |
Questions
Which model should I use?
deepseek-flash for most work: it costs less and reads images. deepseek-v4-pro for harder reasoning; it reads text only.
Can I use separate keys for testing and production?
Yes. Name each key on your account page and turn one off without touching the others.
What happens when my balance runs out?
Requests are refused with 403 insufficient_user_quota until you top up. We email you when it runs low, so you can top up first.
Is there a rate limit?
We don't cap requests per minute. If you expect heavy traffic, write to support@haryai.com first.
Does the Coding Plan cover calls from my own app?
Yes. DeepSeek requests sent with your key count toward the plan, whichever tool or code sends them.
Can I get a receipt or an invoice?
Every order is listed on your account page. For a company invoice, write to support@haryai.com.
Sources
DeepSeek's figures are from its own docs, checked on 2026-11-15.
DeepSeek at 55% off the official price
Cheaper than DeepSeek's own off-peak price, around the clock.
Verify your email and get $0.50 of balance