Zum Hauptinhalt springen
DeepSeekApr 24, 2026

DeepSeek V4 Pro

deepseek-v4-proPrivateOpen 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/$3.30
per 1M in / out
1M
context window
256K
max output
How it comparesamong 128 text models
Pricecheaper than 43%$2.06
Context windowlarger than 43%1M
Max outputlarger than 95%256K

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

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",
"messages": [{ "role": "user", "content": "Explain TEE attestation in two sentences." }],
"reasoning_effort": "low"
}'
Base URL https://api.venice.ai/api/v1

Parameters

ParameterValuesNotes
modeldeepseek-v4-proRequired
messagestextContent parts the model reads
max_completion_tokensUp to 262,144Counts reasoning tokens
reasoning_effortnone | low | medium | highDefault low
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

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

Pricing

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

Input$1.65per 1M tokens
Cached input$0.3380% off input
Output$3.30per 1M tokens

Estimate a workload

$0.005per request
$49.51for 10,000 requests

Blended price against similar models

DeepSeek V4 Pro$2.06
GLM 5.2$2.15
GLM 5.1$2.37

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

Specs

Model ID
deepseek-v4-pro
Endpoint
POST /api/v1/chat/completions
Context window
1,000,000 tokens
Max output
262,144 tokens
Reasoning
none · low · medium · high · default low
Precision
Not disclosed
Privacy
Private
Added
Apr 24, 2026

Compare

ModelInputOutputContextMax output
DeepSeek V4 Pro$1.65$3.301M256K
GLM 5.2$1.40$4.401M128K
GLM 5 Turbo$1.20$4.00200K32K
Grok 4.3$1.42$2.831M32K
GLM 5.1$1.54$4.84200K80K

Other versions

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