deepseek/deepseek-v4-pro-0813 vs deepseek/deepseek-v4.1-flash-1017
For 100,000 calls of 2,000 in and 500 out, deepseek/deepseek-v4.1-flash-1017 is cheaper: $60.00 a month at DeepSeek, against $231.00 for deepseek/deepseek-v4-pro-0813 at DeepSeek — 3.9× the cost.
Cheapest on each
deepseek/deepseek-v4-pro-0813
$231.00/mo
cheapest, at DeepSeek — $0.66 in, $1.98 out per million
deepseek/deepseek-v4.1-flash-1017
$60.00/mo
cheapest, at DeepSeek — $0.15 in, $0.6 out per million
Aligned facts
Same rows on both sides, including the ones we cannot fill.
| Attribute | deepseek/deepseek-v4-pro-0813 | deepseek/deepseek-v4.1-flash-1017 |
|---|---|---|
| Context window | 1M | 1M |
| Accepts | Aa | Aa · IMG |
| Sellers | 5 | 5 |
| Cheapest input rate | $0.66 / M | $0.15 / M |
| Cached input rate | $0.022 / M | $0.003 / M |
No quality or benchmark row appears here. We hold no throughput or accuracy measurement for either model, and a cost-per-quality figure built from a lab’s own claim would look authoritative and mean nothing.
Cost for this workload — both models, every seller
100,000 calls a month · 2,000 input and 500 output tokens each. Sellers of both models lead, cheapest combined cost first.
| Seller | deepseek/deepseek-v4-pro-0813 /mo | deepseek/deepseek-v4.1-flash-1017 /mo |
|---|---|---|
| DeepSeek | $231.002026-10-22 | $60.002026-10-22 |
| OpenRouter | $231.002026-10-27 | $60.002026-10-27 |
| Baseten | $462.002026-10-22 | $120.002026-10-22 |
| Novita AI | $462.002026-10-22 | $120.002026-10-22 |
| Together AI | $462.002026-10-27 | $120.002026-10-27 |
Cheapest tier per seller, this workload only. In and output rates, and a cached prefix, are broken out in the cost calculator.