DeepSeek

DeepSeek V4 Pro

Chat
deepseek/deepseek-v4-pro
CompareGet Started

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.

1M context window
384K max output tokens
Released: 2026-04-24
Supported Protocols:OpenAIopenaiAnthropicanthropic
Available Providers:DeepSeekDeepSeek
Capabilities:Function CallingPrompt Caching

Pricing

TypePrice
Input Tokens$1.74/M
Output Tokens$3.48/M
Cache Read$0.145/M

Code Examples

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)

Related Models

More from DeepSeek

DeepSeek
DeepSeek V4 Flash
$0.14/M/$0.28/M
DeepSeek
DeepSeek V3.2
$0.29/M/$0.43/M

Similar Models

MoonshotAI
MoonshotAI: Kimi K2.6
$0.95/M/$4/M
Claude
Anthropic: Claude Opus 4.7
$5/M/$25/M
Qwen
Qwen3.6 Plus
$0.5/M/$3/M

Frequently Asked Questions

DeepSeek V4 Pro on Ofox.ai costs $1.74/M per million input tokens and $3.48/M per million output tokens. Pay-as-you-go, no monthly fees.