DeepSeek v4 Pro API pricing and code examples

DeepSeek v4 Pro is a DeepSeek model you can call through LivRouter's OpenAI-compatible endpoint. There is no separate DeepSeek account and no separate invoice: one LivRouter API key reaches DeepSeek v4 Pro alongside every other model on the platform, billed per token from prepaid credits.

DeepSeek v4 Pro API at a glance

Compare DeepSeek v4 Pro API pricing, model ID, and OpenAI-compatible examples through LivRouter.

Model ID
deepseek-v4-pro
Provider
DeepSeek
API format
OpenAI-compatible
Billing
Per token from LivRouter credits
Common integration focus
DeepSeek API integrations

DeepSeek v4 Pro pricing

Rates are in USD per 1M tokens. The reference row is the provider base rate recorded in LivRouter's catalog; the plan rows show the published rates for each eligible plan.

PlanInput / 1MOutput / 1MCached input / 1M
Reference (DeepSeek)$0.66$1.98$0.022
Start$0.66$1.98$0.022
Max Deepseek−79%$0.139$0.416$0.00462
Pro Deepseek−71%$0.191$0.574$0.00638

Lowest listed LivRouter rate for DeepSeek v4 Pro: $0.139 per 1M input tokens on the Max Deepseek plan — about 79% below the DeepSeek reference rate. See every plan and rate.

Source: LivRouter model catalog. Catalog checked .

What does a DeepSeek v4 Pro request cost?

One million uncached input tokens plus 100,000 output tokens at the listed Max Deepseek rates cost $0.18. This example excludes subscription fees and assumes the selected plan is active. Actual charges depend on input, output, and cached-token usage.

Compare plan fees and credit allowances

Call DeepSeek v4 Pro with the OpenAI SDK

DeepSeek v4 Pro follows the OpenAI chat completions format, so existing OpenAI client code keeps working — change the base URL and the model name.

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.livrouter.com/v1",
  apiKey: process.env.LIVROUTER_API_KEY,
});

const completion = await client.chat.completions.create({
  model: "deepseek-v4-pro",
  messages: [{ role: "user", content: "Hello" }],
});

console.log(completion.choices[0].message.content);

Prefer plain HTTP? The same request over curl:

curl https://api.livrouter.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $LIVROUTER_API_KEY" \
  -d '{
    "model": "deepseek-v4-pro",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

Frequently asked questions about DeepSeek v4 Pro

How much does deepseek-v4-pro cost through LivRouter?

deepseek-v4-pro is metered per token. The DeepSeek reference rate is $0.66 per 1M input tokens and $1.98 per 1M output tokens. On the Max Deepseek plan LivRouter charges $0.139 per 1M input tokens, about 79% below the DeepSeek reference rate. Cached input is $0.00462 per 1M tokens.

Can I call deepseek-v4-pro with the OpenAI SDK?

Yes. deepseek-v4-pro is reachable through the OpenAI-compatible endpoint at https://api.livrouter.com/v1. Keep your existing OpenAI client code and change the base URL and the model name to "deepseek-v4-pro".

Do I need a separate DeepSeek account?

No. LivRouter routes the request for you. You only need a LivRouter API key and credits — no separate DeepSeek subscription.

Is deepseek-v4-pro available on the Start tier?

Yes. deepseek-v4-pro is reachable from the Start tier group, billed pay-as-you-go at the rates shown above.

Other DeepSeek models on LivRouter

View all model pricingDeepSeek API overviewQuickstart guide