DeepSeek: DeepSeek V4 Pro

Text input Text output
Author's Description

DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding,...

Key Specifications
Context
1M
Parameters
1.6T (Rumoured)
Released
Apr 23, 2026
Supported Parameters

This model supports the following parameters:

Tools Response Format Top Logprobs Stop Frequency Penalty Logprobs Tool Choice Include Reasoning Temperature Max Tokens Reasoning Presence Penalty Top P
Features

This model supports the following features:

Tools Reasoning Response Format
Model Pricing

Current Pricing

Feature Price (per 1M tokens)
Prompt $1.74
Completion $3.48
Input Cache Read $0.145

Price History

Available Endpoints
Provider Endpoint Name Context Length Pricing (Input) Pricing (Output)
DeepSeek
DeepSeek | deepseek/deepseek-v4-pro-20260423 1M $1.74 / 1M tokens $3.48 / 1M tokens
Benchmark Results
Benchmark Category Reasoning Strategy Free Executions Accuracy Cost Duration
Other Models by deepseek