Unverified50% confidenceFactExact time
A single DeepInfer cluster processes up to 155 trillion tokens per day, earns 38 USD per GPU hour, with an estimated gross margin of about 80% (counting only GPU costs), and an input cache hit rate of 96%.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/23/2026
First Seen
Valid until: 1/21/2027
Sources
DeepSeek's New Model + Inference Engine Tested: Open-Source AI Nears the Frontier
bilibili黑纹白斑马10/23/2026
Related Entities
Related Claims
UnverifiedAccording to the video information, DeepInfer is compatible with both the NVIDIA and Huawei Ascend platforms, a single cluster can reach a daily throughput of 155 trillion tokens, and each GPU can earn $38 per hour.77% similarUnverifiedDeepInfer generates $22 million in revenue per day at roughly an 80% gross margin.77% similarUnverifiedAccording to DeepSeek's data, each decode GPU produces about 14,000 tokens per second for all of its users, bringing in about $38 of revenue per GPU per hour on average.75% similarUnverifiedHosted calls processing 200,000 tokens per day cost about $1,500 per month, while renting a dedicated GPU costs about $1,000, but only if the GPU runs at full utilization continuously.72% similarUnverifiedUsing one GPU running a 32B model at approximately 50% average utilization, compared against API pricing of $0.50/million tokens with approximately 500 tokens per request as the baseline, the break-even point is approximately 10 million requests/month, equivalent to approximately 5 billion tokens.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1090417API
curl https://kongchang.com/api/v1/knowledge/claims/1090417MCP
get_claim(id=1090417)