DeepSeek V4 Flash 0731
DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows....
Leaderboards
Average Score combining domain-specific Autobench scores; Higher is better
Performance vs. Industry Average
Intelligence
DeepSeek V4 Flash 0731 is of higher intelligence compared to average (4.5), with an intelligence score of 4.6.
Price
DeepSeek V4 Flash 0731 is cheaper compared to average ($1.13 per 1M Tokens) with a price of $0.05 per 1M Tokens.
Latency
DeepSeek V4 Flash 0731 has a higher average latency compared to average (47.46s), with an average latency of 53.47s.
P99 Latency
DeepSeek V4 Flash 0731 has a higher P99 latency compared to average (288.94s), taking 371.82s to receive the first token at P99 (TTFT).
Context Window
DeepSeek V4 Flash 0731 has a larger context window than average (453k tokens), with a context window of 1049k tokens.