Plain-text specification

DeepSeek V4 Pro API

DeepSeek V4 Pro is a large language model by DeepSeek, available on the Venice API as deepseek-v4-pro. It runs privately, with zero data retention.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.

DeepSeek V4 Pro API pricing

Model ID	Variant	Privacy	Price
`deepseek-v4-pro`	Standard	Private	$1.65 input /$ 3.30 output per 1M tokens

DeepSeek V4 Pro specifications

Spec	Value
Provider	DeepSeek
Released	Apr 24, 2026
Privacy	Private
Open weights	Yes
Context window	1M tokens
Max output	32K tokens
Reasoning effort	none, low, medium, high

How to use the DeepSeek V4 Pro API

Send requests to POST https://api.venice.ai/api/v1/chat/completions with "model": "deepseek-v4-pro" and your 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"
  }'

DeepSeek V4 Pro API FAQ

How much does the DeepSeek V4 Pro API cost?

1.65 per 1M input tokens and

3.30 per 1M output tokens, with cached input at $0.33 per 1M. Prices are in USD and can be paid in DIEM at parity.

What is the DeepSeek V4 Pro model ID?

Use deepseek-v4-pro as the model parameter.

Is the DeepSeek V4 Pro API private?

DeepSeek V4 Pro is private: requests run on infrastructure Venice controls with zero data retention, and prompts and outputs are never stored or used for training.

What is the context window of DeepSeek V4 Pro?

1M tokens of context, with up to 32K output tokens per response.

What does DeepSeek V4 Pro support?

DeepSeek V4 Pro supports function calling, structured outputs, reasoning, web search and prompt caching. Reasoning effort is adjustable with reasoning_effort: none, low, medium and high (default low).

Which endpoint does the DeepSeek V4 Pro API use?

Call POST /chat/completions. /responses (Alpha) is also supported.

Related models

DeepSeek V4 Pro 0813 API: $1.65 input /$ 4.95 output per 1M tokens
GPT-5.4 Mini API: $0.94 input /$ 5.63 output per 1M tokens
GLM 5.2 API: $1.40 input /$ 4.40 output per 1M tokens
GLM 5 Turbo API: $1.20 input /$ 4.00 output per 1M tokens
Grok 4.3 API: $1.42 input /$ 2.83 output per 1M tokens