DeepSeek V4 Pro 0813

The official release of DeepSeek's flagship V4 Pro, coming soon

Try now

read docs

About model

DeepSeek V4 Pro 0813 is the upcoming official release of DeepSeek's flagship model, superseding the V4 Pro preview. The V4 Pro line is a Mixture-of-Experts design with 1.6T total parameters and 49B active per token, built on the V4 generation's hybrid attention architecture for efficient long-context inference, with reasoning effort adjustable across three modes. Full release details, updated capabilities, and benchmarks arrive with the launch. Coming soon to Together AI.

‍

Total Parameters (49B activated)

1.6T

DeepSeek's flagship MoE architecture

Context Window

512K

Hybrid attention built for efficient long-context inference

Reasoning Modes

Deliberation depth adjustable per request

Model key capabilities

Flagship-Scale Reasoning: DeepSeek's largest model line, with reasoning effort adjustable across three modes
Efficient Long Context: Hybrid attention architecture from the V4 generation, built to keep long-context inference fast and affordable
Official Release: Supersedes the V4 Pro preview; full release details and updated benchmarks arrive at launch
Production-Ready Infrastructure: 99.9% SLA, available on Together AI serverless infrastructure

Performance benchmarks

Model	FrontierMath Tier 4	GPQA Diamond	HLE	SciCode	GDPval-AA	Terminal-Bench 2.1	Agent Arena	FrontierCode	DeepSWE
DeepSeek V4 Pro 0813	2.4%	88.8%	36%	50%	40%	64%	-2.9pp	17.6%
Related open-source models
Competitor closed-source models
Claude Fable 5	87.8%	92.6%	53%	60%	62%	85%		53.5%	70%
Claude Opus 5	73.2%	93.2%	53%	56%	68%	89%	+16.4pp	53.4%	74%
GPT-5.6 Sol	82.9%	94.1%	47%	56%	61%	88%		47.5%	73%
Grok 4.5	24.4%	93.1%	40%	54%	51%	82%	+4.2pp	42.4%	54%
GPT-5.6 Luna	61.0%	91.1%	37%	53%	54%	81%		39.8%	67%

API usage

cURL
Python
Typescript

Endpoint:

deepseek-ai/DeepSeek-V4-Pro-0813

curl -X POST "https://api.together.xyz/v1/chat/completions" \
  -H "Authorization: Bearer $TOGETHER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-ai/DeepSeek-V4-Pro-0813",
    "messages": [
      {
        "role": "user",
        "content": "What are some fun things to do in New York?"
      }
    ]
}'

from together import Together

client = Together()

response = client.chat.completions.create(
  model="deepseek-ai/DeepSeek-V4-Pro-0813",
  messages=[
    {
      "role": "user",
      "content": "What are some fun things to do in New York?"
    }
  ]
)
print(response.choices[0].message.content)

import Together from 'together-ai';
const together = new Together();

const completion = await together.chat.completions.create({
  model: 'deepseek-ai/DeepSeek-V4-Pro-0813',
  messages: [
    {
      role: 'user',
      content: 'What are some fun things to do in New York?'
     }
  ],
});

console.log(completion.choices[0].message.content);

Model card
Architecture Overview:
• Mixture-of-Experts model with 1.6T total parameters and 49B activated per token
• Hybrid attention architecture from DeepSeek's V4 generation for efficient processing of long sequences
• Reasoning effort adjustable across three modes

Training Methodology:
• Official dated release of the V4 Pro line, superseding the preview checkpoint
• Full training and release details will be published by DeepSeek at launch

Performance Characteristics:
• Updated benchmarks for the official release arrive at launch
‍
Prompting
Together AI API Access:
• At launch, access DeepSeek V4 Pro 0813 via Together AI APIs using the endpoint deepseek-ai/DeepSeek-V4-Pro-0813
• Authenticate using your Together AI API key in request headers
• Available soon on Together AI serverless infrastructure
‍
Applications & use cases
Frontier Reasoning Workloads:
• Apply DeepSeek's flagship line to complex reasoning, coding, and analysis tasks
• Adjust reasoning depth per request to match task difficulty
• Details on release-specific strengths arrive at launch
‍

Related models

Model specifications

Model data

Model provider
DeepSeek
Type
Reasoning
Chat
Code
LLM
Main use cases
Reasoning
Features
Function Calling
JSON Mode
Intelligence
High
Deployment
Serverless
Dedicated
Endpoint
deepseek-ai/DeepSeek-V4-Pro-0813
Parameters
1.6T
Activated parameters
49B
Context length
512K
Input price
$1.74 / 1M tokens
$0.20 (cached)/1M
Output price
$3.48 / 1M tokens
Input modalities
Text
Output modalities
Text

Released
August 12, 2026
Category
Chat

Run in Playground

Quickstart docs

Deploy model

DeepSeek V4 Pro 0813

About model

API usage

Model card

Prompting

Applications & use cases