Price cut: deepseek/deepseek-v4-flash on openinference
| Field | Before | After | Change |
|---|---|---|---|
| Input | 0.0330 | 0.0174 | -47.2% |
| Output | 1.41 | 1.12 | -20.5% |
| Cache read | 0.0330 | 0.0174 | -47.2% |
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 | $1.02 | $0.73 |
| RAG chat | $2.39 | $1.83 |
| Summarisation (batch) | $1.71 | $1.28 |
| Classification | $0.60 | $0.39 |
| Chat assistant | $5.83 | $4.58 |
| Content generation | $11.33 | $8.99 |
Back to model page | Compare vs Llama 3.3 70B Instruct | All changes