DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B active parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding, and long-horizon agent workflows, delivering strong results across knowledge, mathematics, and software engineering benchmarks. Built on the same architecture as DeepSeek V4 Flash, it adds a hybrid attention system for efficient long-context processing and supports multiple reasoning modes to balance speed and depth based on the task. It is well suited for demanding workloads such as full-codebase analysis, multi-step automation, and large-scale information synthesis, where both performance and efficiency are essential.
$0.395market price $0.791
$0.0329market price $0.0659
$0.75market price $1.50
Throughput is how fast the model writes (tokens per second, higher is better). Time to first token is how long before the answer starts (lower is better).
Share of requests served without a server error. Client errors (4xx) do not count.
Works with the OpenAI SDK pointed at our base URL. Every parameter is in the API reference.
Tokens processed per day on NagaAI.
DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B active parameters, supporting a 1M-token context window.
On NagaAI, DeepSeek V4 Pro 0423 costs $0.395 per 1M input tokens and $0.75 per 1M output tokens. You pay only for what you use, with no subscription.
DeepSeek V4 Pro 0423 reads up to 1.0M tokens in one request, counting the prompt and the answer together.
Yes. DeepSeek V4 Pro 0423 can call your functions as tools and can answer in a JSON schema you give it.
It takes text as input and returns text.
Create an API key, copy the model ID from the top of this page and send requests with the OpenAI or Anthropic SDK pointed at NagaAI. The API section on this page has a ready example.