How much does the DeepSeek V4 Pro API cost?

$0.792 per million input tokens and $1.92 per million output tokens, with cached input at $0.0338. DeepSeek's list price is $1.32 and $3.96, so this is 40% under DeepSeek's list price on input and 51% on output.

Is DeepSeek V4 Pro free?

It is pay as you go: prepaid credit from $10, with no subscription or monthly fee, billed per token. A 1,000-token prompt with a 500-token reply costs about $0.0018.

What is the DeepSeek V4 Pro context window?

DeepSeek V4 Pro has a 1,048,576-token context window, with up to 393,216 output tokens per request. It takes text input.

What is the DeepSeek V4 Pro model id?

deepseek-v4-pro. Send it as the model through the OpenAI SDK with base URL https://api.uplinkswitch.com/v1.

Is it the real DeepSeek V4 Pro?

Every day each model gets the same test prompt, and a model always counts that prompt the same way; a swapped one would not. DeepSeek V4 Pro's latest result: Same fingerprint since Oct 13.

UplinkSwitch

Models / DeepSeek

DeepSeek V4 Pro API pricing

0423

$0.792 in, $1.92 out per million tokens, 40% under DeepSeek's list price on input and 51% on output.

deepseek-v4-promanaged routeOpenAI SDK

Price · per million tokens, USD

Tokens	DeepSeek list price	UplinkSwitch	Saving
Input	$1.32	$0.792	-40%
Cached input	$0.044	$0.0338	-23%
Output	$3.96	$1.92	-51%

List price: DeepSeek's published rate, read October 2026. Same price on every host.

Real-model check: Same fingerprint since Oct 13

DeepSeek V4 Pro specs

Context window: 1,048,576 tokens
Max output: 393,216 tokens
Input: text
Released: April 24, 2026

DeepSeek V4 Pro API · base URL and key

Python · OpenAI SDK

from openai import OpenAI

client = OpenAI(
    base_url="https://api.uplinkswitch.com/v1",
    api_key="sk-uplink-live-...",
)

completion = client.chat.completions.create(
    model="deepseek-v4-pro",
    messages=[{"role": "user", "content": "Summarize this in one line."}],
)
print(completion.choices[0].message.content)

TypeScript · OpenAI SDK

import OpenAI from 'openai';

const client = new OpenAI({
  baseURL: 'https://api.uplinkswitch.com/v1',
  apiKey: 'sk-uplink-live-...',
});

const completion = await client.chat.completions.create({
  model: 'deepseek-v4-pro',
  messages: [{ role: 'user', content: 'Summarize this in one line.' }],
});
console.log(completion.choices[0].message.content);

curl

curl https://api.uplinkswitch.com/v1/chat/completions \
  -H "authorization: Bearer sk-uplink-live-..." \
  -H "content-type: application/json" \
  -d '{"model":"deepseek-v4-pro","messages":[{"role":"user","content":"Hello"}]}'

Guides: Cursor, Cline, Roo Code, Kilo Code, SDKs.

What would it cost? · paste a prompt, priced before you send it

Prompt

Answer length, tokens

Input is counted at about 4 characters per token.

Cheapest first. A real request is billed on the provider's own token count. Same estimate as JSON: POST https://api.uplinkswitch.com/v1/estimate, no key needed.

DeepSeek V4 Pro questions

How much does the DeepSeek V4 Pro API cost?: $0.792 per million input tokens and $1.92 per million output tokens, with cached input at $0.0338. DeepSeek's list price is $1.32 and $3.96, so this is 40% under DeepSeek's list price on input and 51% on output.
Is DeepSeek V4 Pro free?: It is pay as you go: prepaid credit from $10, with no subscription or monthly fee, billed per token. A 1,000-token prompt with a 500-token reply costs about $0.0018.
What is the DeepSeek V4 Pro context window?: DeepSeek V4 Pro has a 1,048,576-token context window, with up to 393,216 output tokens per request. It takes text input.
What is the DeepSeek V4 Pro model id?: deepseek-v4-pro. Send it as the model through the OpenAI SDK with base URL https://api.uplinkswitch.com/v1.
Is it the real DeepSeek V4 Pro?: Every day each model gets the same test prompt, and a model always counts that prompt the same way; a swapped one would not. DeepSeek V4 Pro's latest result: Same fingerprint since Oct 13.

Read: DeepSeek API cost per request, October 2026: a chat turn and a long document.

Get a key · All models