Price increase: nvidia/nvidia-nemotron-3.5-lightning on deepinfra

FieldBeforeAfterChange
Input0.05000.0800+60.0%
Cache read–0.0400–

What this means by workload

Illustrative monthly cost of the changed field(s) alone, at a representative 10M tokens/month split per workload preset. Not a substitute for the calculator, which uses your own volume and every price field.

WorkloadBefore / monthAfter / month
Coding agent$0.48$0.76
RAG chat$0.43$0.68
Summarisation (batch)$0.45$0.72
Classification$0.49$0.78
Chat assistant$0.30$0.48
Content generation$0.10$0.16

Back to model page | All changes