Unverified50% confidenceFactExact time
When the prompt exceeds the 100,000-token threshold, output tokens are also billed at the higher price tier.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/18/2026
First Seen
Valid until: 11/1/2026
Sources
Related Entities
Related Claims
UnverifiedThis deployment solution can achieve 400+ tokens/s in batch throughput (manual concurrency testing).71% similarUnverifiedThe model input cost for 100,000 requests × 2,000 billed input tokens is about $8.40 (excluding retries, retrieval, moderation, and platform fees).71% similarUnverifiedFor a customer support agent model processing 100,000 tickets per month (each ticket consuming 2,500 input tokens and 400 output tokens), the monthly bill is $900 at launch pricing and $1,800 after the December 1 price increase.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1060039API
curl https://kongchang.com/api/v1/knowledge/claims/1060039MCP
get_claim(id=1060039)