Price increase: meta/nvidia/llama-3.1-nemotron-70b-instruct on deepinfra
| Field | Before | After | Change |
|---|---|---|---|
| Input | 0.12 | 0.60 | +400.0% |
| Output | 0.30 | 0.60 | +100.0% |
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.
| Workload | Before / month | After / month |
|---|---|---|
| Coding agent | $1.29 | $6.00 |
| RAG chat | $1.47 | $6.00 |
| Summarisation (batch) | $1.38 | $6.00 |
| Classification | $1.24 | $6.00 |
| Chat assistant | $1.92 | $6.00 |
| Content generation | $2.64 | $6.00 |