DeepSeek
DeepSeek V4 Pro 0423
deepseek/deepseek-v4-proDeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding,...
Context
1M tokens
Input, 1M tokens
$1.63
Output, 1M tokens
$3.26
Benchmark
—
Uptime and speed
Loading…
Pricing
Charged from your prepaid balance for the tokens actually used.
Input tokens$1.63 per 1M tokens
Output tokens$3.26 per 1M tokens
Cache read$0.14 per 1M tokens
Apps and activity
Loading…
Technical details
Model IDdeepseek/deepseek-v4-pro
Context window1M tokens
AcceptsText
ProducesText
TokenizerDeepSeek
Max output tokens384,000
How to connect
The API is OpenAI-compatible: the official SDKs, LangChain and any client with a "base URL" field work.
import OpenAI from 'openai'
const client = new OpenAI({
baseURL: 'https://getmegabrain.com/api/gateway/v1',
apiKey: process.env.MEGABRAIN_API_KEY,
})
const response = await client.chat.completions.create({
model: 'deepseek/deepseek-v4-pro',
messages: [{ role: 'user', content: 'Hello!' }],
})Start using DeepSeek V4 Pro 0423
Create a free account, get a key in your dashboard and send your first request. Top up your balance when you need it.