
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, and long-horizon agent workflows, with strong performance across knowledge, math, and software engineering benchmarks.
Built on the same architecture as DeepSeek V4 Flash, it introduces a hybrid attention system for efficient long-context processing. Reasoning efforts high and xhigh are supported; xhigh maps to max reasoning. It is well suited for complex workloads such as full-codebase analysis, multi-step automation, and large-scale information synthesis, where both capability and efficiency are critical
Modalities
In / Out Price
$0.6943 / $1.389per 1M
Context
1M
Released
Apr 24, 2026
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, and long-horizon agent workflows, with strong performance across knowledge, math, and software engineering benchmarks.
DeepSeek V4 Pro 0423 costs $0.6943/M input tokens and $1.389/M output tokens, with separate rates for Cache Read at $0.05786/M tokens.
DeepSeek V4 Pro 0423 has a 1,048,576 token context window. It supports up to 384,000 completion tokens.
Yes. DeepSeek V4 Pro 0423 accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.
DeepSeek V4 Pro 0423 is served by 18 providers on OpenRouter: StreamLake, GMICloud, DigitalOcean, Ionstream, CoreWeave, DeepInfra, DeepSeek, Alibaba Cloud Int. and 10 more. Requests are routed to the best available provider, with automatic failover to the others, and you can pin or exclude providers with provider routing.
DeepSeek V4 Pro 0423 was released on April 24, 2026.