How much does DeepSeek V4 Pro cost on Ofox?

DeepSeek V4 Pro on Ofox.ai costs $0.45/M per million input tokens and $0.88/M per million output tokens. Pay-as-you-go, no monthly fees.

What is DeepSeek V4 Pro's context window?

DeepSeek V4 Pro supports a context window of 1,000,000 tokens, allowing you to process large documents and maintain long conversations.

How to use DeepSeek V4 Pro API via Ofox?

Simply set your base URL to https://api.ofox.ai/v1 and use your Ofox API key. The API is OpenAI-compatible — just change the base URL and API key in your existing code.

What capabilities does DeepSeek V4 Pro support?

DeepSeek V4 Pro supports the following capabilities: function calling, prompt caching. Access all features through the Ofox.ai unified API.

DeepSeek V4 Pro

Name: DeepSeek V4 Pro
Brand: deepseek
Price: 0.44999999999999996 USD
Availability: InStock
Rating: 5 (1 reviews)

Chat

deepseek/deepseek-v4-pro

Сравнить Открыть в Playground Начать

DeepSeek 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, and long-horizon agent workflows, with strong performance across knowledge, math, and software engineering benchmarks.

Контекстное окно

Макс. выходных токенов

384K

Дата релиза

2026-04-24

Возможности

Function CallingКэширование промптов

Доступные провайдеры

AliyunAzureDeepSeek

Поддерживаемые протоколы

openaianthropic

Providers

Aliyun

Входные токены

$1.74/M

Выходные токены

$3.48/M

Чтение кэша

$0.15/M

Веб-поиск

$0.01/R

Protocols

anthropic

Azure

Входные токены

$0.45/M

Выходные токены

$0.88/M

Чтение кэша

$0.0037/M

Protocols

openai/v1/chat/completions/v1/responses

anthropic

DeepSeek

Входные токены

$0.45/M

Выходные токены

$0.88/M

Чтение кэша

$0.0037/M

Protocols

openai/v1/chat/completions

anthropic

Примеры кода

from openai import OpenAI

client = OpenAI(
    base_url="https://api.ofox.ai/v1",
    api_key="YOUR_OFOX_API_KEY",
)

response = client.chat.completions.create(
    model="deepseek/deepseek-v4-pro",
    messages=[
        {"role": "user", "content": "Hello!"}
    ],
)

print(response.choices[0].message.content)