Price cut: deepseek/deepseek-v4-flash on wafer
| Field | Before | After | Change |
|---|---|---|---|
| Input | 0.70 | 0.60 | -14.3% |
| Cache read | 0.0130 | 0.20 | +1438.5% |
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 | $6.65 | $5.70 |
| RAG chat | $5.95 | $5.10 |
| Summarisation (batch) | $6.30 | $5.40 |
| Classification | $6.86 | $5.88 |
| Chat assistant | $4.20 | $3.60 |
| Content generation | $1.40 | $1.20 |
Back to model page | Compare vs Llama 3.3 70B Instruct | All changes