High-performance deepseek-v4-pro model from DeepSeek
Context Window
128K tokens
Max Output Tokens
16,384 tokens
Release Date
2025 - 2026
Step-by-step Reasoning
Standard
• Frontier Class• Top Tier
$
Token Pricing (Per 1M tokens)
Pay-As-You-Go pricing based on actual usage. No recurring maintenance fees, no minimum commitment, automatic real-time wallet deduction.
Input (Prompt Tokens)
1.403 ₫/M$0.0541/M
13.750 ₫/M$0.55/M90% OFF
Output (Completion Tokens)
1.403 ₫/M$0.0541/M
54.750 ₫/M$2.19/M98% OFF
Official provider list price: $0.55 / $2.19 per 1M tokens. Save up to 90% via Gateway.
24h Gateway Performance
Real-world latency and throughput metrics automatically monitored 24/7.
Average TPS
108.3 t/s
Average Latency
13.94 s
Time to First Token
6.28 s
Success Rate
100.00%
Quickstart API Integration
Compatible with standard OpenAI SDKs. Replace the Base URL and pass Model ID deepseek-v4-pro:
curl https://giahuynexus.com/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{
"model": "deepseek-v4-pro",
"messages": [
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "Hello, how can you help me today?"}
],
"temperature": 0.7
}'
from openai import OpenAI
client = OpenAI(
api_key="YOUR_API_KEY",
base_url="https://giahuynexus.com/v1"
)
response = client.chat.completions.create(
model="deepseek-v4-pro",
messages=[
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "Hello, how can you help me today?"}
],
temperature=0.7
)
print(response.choices[0].message.content)
import OpenAI from "openai";
const openai = new OpenAI({
apiKey: "YOUR_API_KEY",
baseURL: "https://giahuynexus.com/v1",
});
const response = await openai.chat.completions.create({
model: "deepseek-v4-pro",
messages: [
{ role: "system", content: "You are a helpful assistant." },
{ role: "user", content: "Hello, how can you help me today?" }
],
temperature: 0.7,
});
console.log(response.choices[0].message.content);
deepseek-v4-pro
deepseek-v4-pro
Copy the cURL command below and run it in your terminal to test model responses: