Price cut: deepseek/deepseek-v4-flash on relace
| Field | Before | After | Change |
|---|---|---|---|
| Input | 0.0300 | 0.0228 | -24.0% |
| Cache read | 0.0300 | 0.0228 | -24.0% |
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 | $0.28 | $0.22 |
| RAG chat | $0.26 | $0.19 |
| Summarisation (batch) | $0.27 | $0.21 |
| Classification | $0.29 | $0.22 |
| Chat assistant | $0.18 | $0.14 |
| Content generation | $0.0600 | $0.0456 |
Back to model page | Compare vs Llama 3.3 70B Instruct | All changes