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.

Start free →

Verify your email and get $0.50 of balance

US dollars per 1M tokens
ModelInput, cache hitInput, cache missOutput
DeepSeek V4.1 FlashDeepSeek, 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 ProDeepSeek, 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.

Python (OpenAI SDK)
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)
Node.js (OpenAI SDK)
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
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"}]}'
Streaming
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="")
Python (Anthropic SDK)
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 FlashDeepSeek V4 Pro
Model namedeepseek-flashdeepseek-v4-pro
Served byDeepSeek-V4.1-Flash-1017DeepSeek-V4-Pro-0813
Context1M1M
Max output384K384K
Image inputYesNo

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