Skip to content

DeepSeek V4 Pro 0423

ModelOpen sourceActive
by DeepSeek · family “deepseek-v4-pro”

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,... (description from the OpenRouter listing)

in: textout: textReasoningTool useStructured output
Epoch Capabilities Index
149.1 #54 of 268
90% CI 147.5 – 150.8
Listing ↗
Released
24 Apr 2026
Context window
1.05M tokens
Max output
384K tokens
Input $ / 1M tokens
$0.96
Output $ / 1M tokens
$1.91
Cached input $ / 1M
$0.080
Each benchmark shown separately with its own source

Benchmark results (0)

All benchmarks
No benchmark results recorded for this model.

Source: Epoch AI Benchmarking Hub (CC BY 4.0). “External” rows are leaderboard results Epoch collects from third parties. Best reported setting per benchmark is shown.

API list price over time

Price history

$ per 1M tokens

12 recorded prices on 4 May 2026 (OpenRouter listing + Internet Archive snapshots); re-read on every data refresh, most recently 8h ago. Steps show when the price changed.

Events