DeepSeek V4 Flash is an efficiency-focused Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B active parameters, supporting a 1M-token context window. It is built for fast inference and high-throughput workloads while preserving strong reasoning and coding capabilities. The model features hybrid attention for efficient long-context processing and offers configurable reasoning modes. It is a strong fit for use cases such as coding assistants, chat applications, and agent workflows where responsiveness and cost efficiency matter.
$0.025market price $0.05
$0.0084market price $0.0168
$0.084market price $0.168
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 Flash is an efficiency-focused Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B active parameters, supporting a 1M-token context window. It is built for fast inference and high-throughput workloads while preserving strong reasoning and coding capabilities.
On NagaAI, DeepSeek V4 Flash 0423 costs $0.025 per 1M input tokens and $0.084 per 1M output tokens. You pay only for what you use, with no subscription.
DeepSeek V4 Flash 0423 reads up to 1.0M tokens in one request, counting the prompt and the answer together.
Yes. DeepSeek V4 Flash 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.