DeepSeek V4 Flash 0731
Weights availableDeepSeek V4 Flash 0731 weights published by DeepSeek in its Hugging Face organization (deepseek-ai/DeepSeek-V4-Flash-0731). 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-Flash-0731Updated Oct 1, 2026
Capabilities & limits
- Context window
- 1M
- Maximum output
- 384K
- Image input
- Unsupported
- Tool calling
- Supported
- Structured output
- Not published
Hosted price
USD / 1M tokens- Input
- $0.0108
- Output
- $1.28
What OpenRouter charges for deepseek/deepseek-v4-flash-0731. Other hosts set their own prices.
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
- 284B
- Active parameters
- 13B
- Architecture
- Mixture-of-Experts with hybrid Compressed Sparse Attention and Heavily Compressed Attention, manifold-constrained hyper-connections and the Muon optimizer; speculative decoding module attached
- Input modalities
- Text
- Output modalities
- Text
License
MIT
From DeepSeek
Official announcement ↗How they describe it
the official release of DeepSeek-V4-Flash, superseding the preview version, with substantially enhanced agentic capabilities
What they say is new
Significantly enhanced agent capabilities, with benchmark results far exceeding V4-Pro-Preview
Release & lifecycle
- Published
- Jul 31, 2026
- available
- As of Oct 1, 2026