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,...
Specifications
| Provider | DeepSeek |
|---|---|
| Context window | 1,048,576 tokens (1.0M) |
| Input price | $1.6 / 1M tokens |
| Output price | $3.2 / 1M tokens |
| Input modalities | text |
| Output modalities | text |
| Model ID | deepseek/deepseek-v4-pro |
Pricing is per 1M tokens, indicative pricing via OpenRouter (updated 2026-08-22); a provider's own list price may differ.
Compare DeepSeek V4 Pro 0423
Frequently asked questions
How much does DeepSeek V4 Pro 0423 cost?
Indicative pricing (via OpenRouter, updated 2026-08-22) is $1.6 per 1M input tokens and $3.2 per 1M output tokens. A provider's own list price may differ. On Vincony, DeepSeek V4 Pro 0423 is available on credit-based pricing alongside 800+ other models.
What is DeepSeek V4 Pro 0423's context window?
DeepSeek V4 Pro 0423 supports a context window of up to 1,048,576 tokens (1.0M), which is how much text it can consider at once.
Who makes DeepSeek V4 Pro 0423?
DeepSeek V4 Pro 0423 is built by DeepSeek. You can access it — and compare it against other providers' models — through Vincony's multi-model platform.
How do I use DeepSeek V4 Pro 0423?
You can use DeepSeek V4 Pro 0423 directly through DeepSeek, or via Vincony, which aggregates 800+ models (including DeepSeek V4 Pro 0423) into one interface with side-by-side comparison and credit-based pricing.