Unverified50% confidenceBenchmarkExact time
Official DeepInfer data shows that a single cluster can reach a daily throughput of 155 trillion Tokens, an input cache hit rate as high as 96%, and chat caches retained for up to seven days.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/21/2026
First Seen
Valid until: 11/4/2026
Sources
DeepSeek Open-Sources DeepInfer Inference Engine — Why Did It Trigger a US Ban?
bilibili智灵Shaw10/21/2026
Related Entities
Related Claims
UnverifiedOpenRouter data for the past 30 days shows that the old version of DeepSeek Flash processed about 122 trillion prompt tokens and about 2.2 trillion completion tokens, a ratio of about 55:1, and most prompts were cache hits.72% similarUnverifiedThe script made approximately 2,700 requests within 8 hours, consuming approximately 375 million uncached input tokens and approximately 1 million output tokens.67% similarUnverifiedThe developer's Claude Code logs over three days show a total of about 65,000 requests, 12.6 billion tokens processed, and only 14 million tokens of actual output.67% similarUnverifiedAt peak usage, that user consumed over 700 million tokens in a single day.67% similarUnverifiedWeChat has 1.4 billion monthly active users, with an average daily usage duration exceeding 90 minutes.65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1081781API
curl https://kongchang.com/api/v1/knowledge/claims/1081781MCP
get_claim(id=1081781)