DeepSeek V4.1 Flash 0910 is the original September 10, 2026 release of DeepSeek V4.1 Flash (the October 17 snapshot is DeepSeek V4.1 Flash 1017). It is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on output from a 552B-parameter backbone, an asymmetric split that keeps per-token compute low relative to the model's total size. Image understanding is native to the architecture, with visual and text embeddings trained jointly from the start of pre-training rather than added afterward as in the earlier experimental V4 Flash Vision Exp.
$0.003market price $0.006
$0.0005market price $0.001
$0.101market price $0.203
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 V4.1 Flash 0910 is the original September 10, 2026 release of DeepSeek V4.1 Flash (the October 17 snapshot is DeepSeek V4.1 Flash 1017). It is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture.
On NagaAI, DeepSeek V4.1 Flash 0910 costs $0.003 per 1M input tokens and $0.101 per 1M output tokens. You pay only for what you use, with no subscription.
DeepSeek V4.1 Flash 0910 reads up to 1.0M tokens in one request, counting the prompt and the answer together.
Yes. DeepSeek V4.1 Flash 0910 can call your functions as tools and can answer in a JSON schema you give it.
It takes text and images 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.