Price cut: meta/llama-3.3-70b-instruct on deepinfra
| Field | Before | After | Change |
|---|---|---|---|
| Input | 0.13 | 0.10 | -23.1% |
| Output | 0.39 | 0.32 | -17.9% |
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 | $1.43 | $1.11 |
| RAG chat | $1.69 | $1.33 |
| Summarisation (batch) | $1.56 | $1.22 |
| Classification | $1.35 | $1.04 |
| Chat assistant | $2.34 | $1.88 |
| Content generation | $3.38 | $2.76 |
Back to model page | Compare vs Llama 4 Maverick | All changes