deepseek/deepseek-v4-flash-0731DeepSeek V4 Flash 0731 is DeepSeek’s AI model, released Jul 31, 2026. It costs $0.14/M input and $0.28/M output tokens, and handles a 1M-token context window. Its strongest use case is reasoning & knowledge, where it ranks in the 81st percentile of the models Model Beat tracks.
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.
Scores on standardized evaluations. Higher is better — and rank shows where DeepSeek V4 Flash 0731 lands among all models tracked on Model Beat.
Graduate-level scientific reasoning
Frontier of human expert knowledge
Scientific research coding
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.
DeepSeek V4 Flash 0731 is an AI model developed by DeepSeek, part of the DeepSeek family, released Jul 31, 2026.
DeepSeek V4 Flash 0731's list price from DeepSeek is $0.14 per million input tokens and $0.28 per million output tokens.
DeepSeek V4 Flash 0731 supports a context window of up to 1M tokens.
On standardized evaluations tracked by Epoch AI, DeepSeek V4 Flash 0731 scores 90.8% on GPQA Diamond, 36.8% on Humanity's Last Exam, 49.9% on SciCode.
Benchmark data from Epoch AI (CC BY) and Artificial Analysis; pricing, specs & descriptions from OpenRouter. Data updated Aug 2, 2026.