Price cut: nvidia/nemotron-3-5-super-vl on venice

FieldBeforeAfterChange
Input0.250.20-20.0%
Output1.250.50-60.0%
Cache read0.130.0400-68.0%

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$3.00$2.15
RAG chat$4.00$2.45
Summarisation (batch)$3.50$2.30
Classification$2.70$2.06
Chat assistant$6.50$3.20
Content generation$10.50$4.40

Back to model page | All changes