Skip to main content
DeepSeekAug 14, 2026

DeepSeek V4 Pro 0813

deepseek-v4-pro-0813PrivateOpen weights

DeepSeek V4 Pro is a 1.6T-parameter Mixture-of-Experts model with 49B active parameters and a 1M-token context window. Built for advanced reasoning, coding, and long-horizon agentic workflows with a hybrid attention system for efficient long-context processing.

$1.65/$4.95
per 1M in / out
1M
context window
256K
max output
How it comparesamong 143 text models
GPQA Diamondhigher than 42%82.3%
Blended pricecheaper than 41%$2.47
Context windowlarger than 42%1M
Max outputlarger than 96%256K

Further right is better. Hover a dot for its model.

Time to first token— 
Output speed— 
Uptime— 

Last 24 hours of Venice traffic.How it’s measured

Capabilities

What the model takes in, returns and supports through the API.

InText
OutText

Not supportedimage input, video input, audio input, X search and log probabilities

Benchmarks

GPQA Diamond
82.3%81st of 139 · 37 score higher for less, including Gemini 3.8 Flash, Gemini 3.7 Flash and Pareto

Specs

Model ID
deepseek-v4-pro-0813
Endpoint
POST /api/v1/chat/completions
Context window
1,000,000 tokens
Max output
262,144 tokens
Reasoning
none · low · high · max · default high
Precision
Not disclosed
Privacy
Private
Added
Aug 14, 2026

Compare

ModelInputOutputGPQA DiamondContextMax outputFirst tokenSpeed
DeepSeek V4 Pro 0813$1.65$4.9582.3%1M256K——
GLM 5.3$1.75$5.5079.8%1M128K——
Muse Spark Open$1.56$5.3171.7%1M128K——
GLM 5.3 E2EE$1.75$5.5075.3%1M32K——
GLM 5.2 E2EE$1.75$5.7550.5%512K32K——

Other versions

  1. DeepSeek V4 ProApr 2026
  2. DeepSeek V4 Pro 0813Aug 2026

Pricing

Billed per token in USD. Reasoning tokens bill as output.

Input$1.65per 1M tokens
Cached input$0.16590% off input
Output$4.95per 1M tokens

Estimate a workload

$0.0058per request
$57.75for 10,000 requests

Blended price against similar models

DeepSeek V4 Pro 0813$2.47
GLM 5.3$2.69

Per 1M tokens at three input tokens for each output token.

Quickstart

OpenAI-compatible: point any OpenAI SDK at the Venice base URL with a Venice API key.

curl https://api.venice.ai/api/v1/chat/completions \
-H "Authorization: Bearer $VENICE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "deepseek-v4-pro-0813",
"messages": [{ "role": "user", "content": "Explain TEE attestation in two sentences." }],
"reasoning_effort": "high"
}'
Base URL https://api.venice.ai/api/v1

Parameters

ParameterValuesNotes
modeldeepseek-v4-pro-0813Required
messagestextContent parts the model reads
max_completion_tokensUp to 262,144Counts reasoning tokens
reasoning_effortnone | low | high | maxDefault high
toolsFunction definitionsWith tool_choice
response_format{ type: "json_schema" }Output that matches a schema
streamtrue | falseServer-sent events
venice_parameters.enable_web_searchauto | on | offWeb results and citations