deepseek-v4.1-flash-1017
BytePlus
Chat
deepseek-v4.1-flash-1017
DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the deepseek-flash API model name. V4.1 Flash 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.
Provider pricing
per 1M tokensThe same model is offered by several providers. Prices below are per provider; select a row to switch provider.
| Provider | Billing | Input / 1M | Output / 1M | Cache read / 1M | Context | Max output |
|---|---|---|---|---|---|---|
Current | Token-based pricing | $0.30 | $1.20 | $0.006 | 1M | 393,216 |
Pricing
USD per 1M tokensPrices from the current provider, per 1M tokens.
| Input / 1M | Output / 1M | Cache read / 1M |
|---|---|---|
| $0.30 | $1.20 | $0.006 |
Performance
Metrics unavailableData for this section is coming soon.
Uptime
Metrics unavailableData for this section is coming soon.