Deepseek V4 Flash
DeepSeek develops the DeepSeek V 4 Flash, a chat model that excels at handling long contexts with its support for up to 1,048,576 tokens, making it well-suited for tasks requiring extensive contextual understanding. Notably, it features a hybrid attention architecture combining Compressed Sparse Attention and Heavily Compressed Attention, which enhances efficiency in long-context settings.
Input
Output
Context
1049K
Max Output
384K
Parameters
158.1B
Technical Specifications
Model TypeChat
Context Window1,048,576 tokens
Max Output Tokens384,000 tokens
Parameters158.1B
Release DateApr 22, 2026
Training CutoffNot available
Licensemit
Open SourceYes
Input Modalities
Text
Output Modalities
Text
Capabilities
Benchmarks
Artificial Analysis
32.1%
HLE
89.4%
GPQA
44.9%
SciCode
38.7
Coding
40.3
Intelligence
114
Speed (tok/s)
50.4
TTFA (s)
0.997
TTFT (s)
Resources & Links
Estimated GPU Requirements for Deepseek V4 Flash
Estimates based on INT8 quantization. Actual requirements vary by framework and configuration.
Related Tools
Data sourced from official provider APIs and documentation
Last updated: Jun 23, 2026
Start building with the right model.
Automatically route workloads to the right model for every task, every time.