Unverified50% confidenceBenchmarkExact time
Measured against GPT-4o as the baseline, token costs for image-heavy content dropped by 85.9% after compression.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/13/2026
First Seen
Valid until: 1/11/2027
Sources
Related Entities
Related Claims
UnverifiedFrom GPT-3.5 to GPT-4o mini, the token cost for handling the same tasks has dropped by more than 90%.73% similarUnverifiedOpenAI compressed inference costs for capabilities comparable to GPT-3.5 through GPT-4o by approximately 95% in about 18 months.71% similarUnverifiedThe release of GPT-3.5-turbo in March 2023 reduced API call costs by approximately 90%.71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1019549API
curl https://kongchang.com/api/v1/knowledge/claims/1019549MCP
get_claim(id=1019549)