Cheap DeepSeek V4 Pro API

What a top-up buys on DeepSeek V4 Pro

Output-token count only; input tokens are cheaper. First top-up is at least 2.5×.

When to pick DeepSeek V4 Pro

DeepSeek V4 Pro costs $0.0020 per 1,500-in/500-out request at list price, $0.0010 effective. It is one of the lowest-priced models available, ideal for high-volume work.

DeepSeek V4 Pro vs similarly priced models

Nearest models to DeepSeek V4 Pro by blended price (3 input : 1 output). All run on one Somnus key.

Getting the most out of DeepSeek V4 Pro for less

• Input is 3.0× cheaper than output on DeepSeek V4 Pro, so long context with short answers is the cheapest pattern.
• A $200 top-up gives $500 credit — about 505M blended DeepSeek V4 Pro tokens.
• Mix models: send easy steps to DeepSeek V4 Flash and keep DeepSeek V4 Pro for the steps that need it.

Other DeepSeek models on Somnus

Every DeepSeek model shares the same key and balance.

Use DeepSeek V4 Pro

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.SOMNUS_API_KEY,
  baseURL: "https://gateway-production-c837.up.railway.app/v1",
});

const resp = await client.chat.completions.create({
  model: "claude-sonnet-5",
  messages: [
    {"role": "user", "content": "Summarise this in one line"}
  ],
});
console.log(resp.choices[0].message.content);

Copy the exact model id from your dashboard.

Questions

Related