Unverified50% confidenceBenchmarkExact time
The deployed 0.8B SLM reduced service costs by approximately 16x.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/9/2026
First Seen
Valid until: 1/7/2027
Sources
Related Entities
Related Claims
UnverifiedDuring the price war, the API call price of some models fell to a few cents per million tokens.60% similarUnverifiedOver the past two years, the per-token API call cost of mainstream large model vendors has shown a continuous downward trend.58% similarUnverifiedLLM打破了传统软件边际成本趋近于零的特性，其成本随用户规模线性甚至超线性增长57% similarUnverified$27.5 represents a cost reduction of more than 80% compared to the original solution's $144.55% similarUnverifiedFor businesses with an average of one million requests per day, the unit cost of self-hosting a 70B parameter model can be 5–10 times lower than that of commercial APIs.54% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/990334API
curl https://kongchang.com/api/v1/knowledge/claims/990334MCP
get_claim(id=990334)