DeepSeek V4 Pro (Routed)
Description
DeepSeek V4 Pro is a large-scale Mixture-of-Experts model with a 1M-token context window, designed for advanced reasoning, coding, long-horizon agent workflows, knowledge, math, and software engineering tasks. Note: This version is routed through DeepSeek infrastructure, making it more cost-efficient, but prompts and responses may be used by DeepSeek to improve their models. If you require stronger privacy guarantees, consider using DeepSeek V4 Pro (deepseek-v4-pro), which is not routed to DeepSeek.
At a Glance
Key pricing and model details available for this model.
Input price
$0.44
per 1M tokens
Output price
$0.87
per 1M tokens
Context window
1.0M
tokens
Hallucination rate
0%
Token Pricing
Token pricing normalized to per-million-token rates.
Input / 1M tokens
$0.44
Output / 1M tokens
$0.87
Cache Read / 1M tokens
$0.04
Token Pricing Details
Rates are shown per 1M tokens for easier comparison.
| Input / 1M tokens | $0.44 |
| Input unit | 1M tokens |
| Output / 1M tokens | $0.87 |
| Output unit | 1M tokens |
| Cache Read / 1M tokens | $0.04 |
| Cache Read unit | 1M tokens |
Feature Availability
Capabilities explicitly listed in the current payload.
LLM
Available
Vision
Not listed
Function calling
Available
Reasoning
Available
Supported Parameters
Code Samples
Quick start with the Routeway API
import OpenAI from 'openai';
const openai = new OpenAI({
baseURL: "https://api.routeway.ai/v1",
apiKey: "<YOUR_API_KEY>",
});
async function main() {
const completion = await openai.chat.completions.create({
model: "deepseek-v4-pro-routed",
messages: [
{
role: "user",
content: "Explain quantum computing in simple terms"
}
]
});
console.log(completion.choices[0].message);
}
main();