ME News report, September 8 (UTC+8), Beating AI Quick News: Initial tests of DeepSeek V4.1 Flash show the model achieves an output speed of 420 tokens/s, generating over 71,000 tokens in under three minutes. For reference, Artificial Analysis currently measures the output speed of V4 Flash 0731 on the DeepSeek API at approximately 128 tokens/s. (Source: BlockBeats)
DeepSeek V4.1 Flash achieves 420 tokens/s output speed in initial tests.
KuCoinFlashShare
Summary
According to on-chain data from MetaEra, DeepSeek V4.1 Flash achieved an output speed of 420 tokens/s in initial tests, generating over 71,000 tokens in under three minutes. On-chain analysis by Artificial Analysis showed that the earlier V4 Flash 0731 model operated at approximately 128 tokens/s via the DeepSeek API.
Source:Show original
Disclaimer: The information on this page may have been obtained from third parties and does not necessarily reflect the views or opinions of KuCoin. This content is provided for general informational purposes only, without any representation or warranty of any kind, nor shall it be construed as financial or investment advice. KuCoin shall not be liable for any errors or omissions, or for any outcomes resulting from the use of this information.
Investments in digital assets can be risky. Please carefully evaluate the risks of a product and your risk tolerance based on your own financial circumstances. For more information, please refer to our Terms of Use and Risk Disclosure.