DeepSeek V4.1 Flash
Weights availableDeepSeek V4.1 Flash weights published by DeepSeek in its Hugging Face organization (deepseek-ai/DeepSeek-V4.1-Flash). Self-hosting costs and serving limits depend on your deployment.
Access details: DeepSeek open weights (Hugging Face)
The Hugging Face repository. Download the weights and run them yourself or with a host.
deepseek-ai/DeepSeek-V4.1-FlashAlso on the DeepSeek API as deepseek-flash
Updated Oct 1, 2026
Capabilities & limits
- Context window
- 1M
- Maximum output
- Not published
- Image input
- Supported
- Tool calling
- Supported
- Structured output
- Not published
Hosted price
USD / 1M tokens- Input
- $0.30
- Output
- $1.20
What DeepSeek charges for deepseek-flash, its API version of this model.
Free to download. Running the weights costs whatever your hardware or host charges.
Price history
Oct 1, 2026
Input Not applicable per million tokens
Oct 1, 2026
Output Not applicable per million tokens
Technical details
- Parameters
- 552B
- Active parameters
- 8B per token in prefill, 16B in decode
- Architecture
- Mixture-of-Experts with a Causal Encoder-Decoder (CED) architecture
- Input modalities
- Text, image
- Output modalities
- Text
License
MIT
From DeepSeek
Official announcement ↗How they describe it
a multimodal Mixture-of-Experts (MoE) model with 552B backbone parameters and support for contexts of up to one million tokens
What they say is new
More intelligence, less cost.
Release & lifecycle
- Published
- Sep 10, 2026
- available
- As of Oct 1, 2026