Unverified50% confidenceFactExact time
Hydrogen enables implicit caching by default (above 4096 tokens), and the input price for cache hits drops to $0.075 per million.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
11/14/2026
First Seen
Valid until: 2/12/2027
Sources
Related Entities
Related Claims
UnverifiedGemini 4 Hydrogen is priced at $1.50/M tokens for input, $0.075/M for cached input, and $7.50/M for output.72% similarUnverifiedIn the FSR benchmark, Hydrogen-1.0's estimated output cost per question is $0.25, versus $0.88 for GPT-6 Astra, a cost reduction of about 72%.69% similarUnverifiedUnder the same H100 configuration, the cost per million output tokens is about $0.22–0.23 under an 8-request concurrent load.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1171288API
curl https://kongchang.com/api/v1/knowledge/claims/1171288MCP
get_claim(id=1171288)