DeepSeekApr 24, 2026
DeepSeek V4 Pro
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
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/v1Parameters
| Parameter | Values |
|---|---|
model | deepseek-v4-pro |
messages | text |
max_completion_tokens | Up to 262,144 |
reasoning_effort | none | low | medium | high |
tools | Function definitions |
response_format | { type: |
stream | true | false |
venice_parameters.enable_web_search | auto | on | off |
Capabilities
What the model takes in, returns and supports through the API.
InText
OutText
Streaming
Function callingstream: truetoolsStructured outputsresponse_formatReasoningreasoning_effort none · low · medium · highWeb search
Prompt cachingReads at $0.33enable_web_searchOptimized for codeTuned for software work
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
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
- Weights
- deepseek-ai/DeepSeek-V4-Pro
- Added
- Apr 24, 2026
Compare
| Model | Input | Output |
|---|---|---|
| DeepSeek V4 Pro | $1.65 | $3.30 |
| GLM 5.2 | $1.40 | $4.40 |
| GLM 5 Turbo | $1.20 | $4.00 |
| Grok 4.3 | $1.42 | $2.83 |
| GLM 5.1 | $1.54 | $4.84 |
Other versions
- DeepSeek V4 ProApr 2026
- DeepSeek V4 Pro 0813Aug 2026