Verified65% confidenceFactExact time
According 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.
3
Sources
65%
Confidence
Short-term (~14 days)
Relevance
10/21/2026
First Seen
Valid until: 11/4/2026
Sources
Related Entities
Related Claims
UnverifiedA 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%.75% similarUnverifiedAccording 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.73% 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.72% similarUnverifiedA single DeepSeek online cluster processes about 155 trillion tokens per day, translating to revenue of about 38 US dollars per card per hour; Decode uses EP64 to EP128, Pre-fill uses only EP2 to EP8, KV Cache is stored on 3FS with 10+2 erasure coding and retained for 3 to 7 days.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1082065API
curl https://kongchang.com/api/v1/knowledge/claims/1082065MCP
get_claim(id=1082065)