Save 15% on top-ups, plus 15% back on usage — use OFOXAI2608Learn more
DeepSeek

DeepSeek V4 Pro 0813

Chat
deepseek/deepseek-v4-pro-0813
CompareTry in PlaygroundGet Started

DeepSeek V4 Pro (0813) is the official release of DeepSeek's flagship Mixture-of-Experts model with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. This version greatly enhances agent capabilities — tool use, code execution, and long-horizon multi-step workflows — alongside strong reasoning, coding, and software engineering performance.

Context Window
1M
Max Output Tokens
384K
Released
2026-08-13
Capabilities
Function CallingPrompt Caching
Available Providers
DeepSeekDeepSeek
Supported Protocols
OpenAIopenaiAnthropicanthropic

Providers

DeepSeekDeepSeek
Input Tokens
$0.45/M
Output Tokens
$0.88/M
Cache Read
$0.0037/M
Protocols
OpenAIopenai/v1/chat/completions
Anthropicanthropic

Code Examples

from openai import OpenAI


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


response = client.chat.completions.create(
    model="deepseek/deepseek-v4-pro-0813",
    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 V4 Pro
$0.45/M/$0.88/M
DeepSeek
DeepSeek V3.2
$0.29/M/$0.43/M

Similar Models

Qwen
Qwen: Qwen3.8 Max
$2/M/$6/M
Claude
Anthropic: Claude Opus 5
$5/M/$25/M
Gemini
Google: Gemini 3.5 Flash Lite
$0.3/M/$2.5/M

Frequently Asked Questions

DeepSeek V4 Pro 0813 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.