AI Rate Card

DeepSeek V4.1 Flash 1017 Basic vs DeepSeek V4 Flash 0731: API price and specs

DeepSeek V4 Flash 0731 is 53% cheaper than DeepSeek V4.1 Flash 1017 Basic on input price.

DeepSeek V4 Flash 0731 is 74% cheaper than DeepSeek V4.1 Flash 1017 Basic on output price.

DeepSeek V4 Flash 0731 is 62% cheaper than DeepSeek V4.1 Flash 1017 Basic on a 1M-in / 200k-out workload.

DeepSeek V4 Flash 0731 has a 4.9% larger context than DeepSeek V4.1 Flash 1017 Basic.

FieldDeepSeek V4.1 Flash 1017 BasicDeepSeek V4 Flash 0731
Lowest input, per 1M$0.09 +113.3%$0.0422
Median input, per 1M$0.15 +3.6%$0.14
Lowest output, per 1M$0.36 +279.1%$0.09495
Median output, per 1M$0.48 +60%$0.30
Lowest unit price——
Cost of 1M in + 200k out$0.16 +164.7%$0.06119
Context1M +4.6%1M
Max output384K +63.4%1M
Providers2 +95.5%44
Regions—CN, EU, GLOBAL, US
Accepts—text
Returns—text
TypeText modelsText models
Free optionnono
Cheapest providerinferxtrustedrouter

Your own workload: how many tokens the model gets (input) and gives back (output) - for example, in a month. The "Cost" row of the table above is recalculated for these numbers, for each model.

Computed from current offers each time the page opens; the best value of a row is bold, the percent is how far behind the best.

Providers selling both

hyper, inferx

Frequently asked questions

Which is cheaper, DeepSeek V4.1 Flash 1017 Basic or DeepSeek V4 Flash 0731?

DeepSeek V4 Flash 0731 is 53% cheaper than DeepSeek V4.1 Flash 1017 Basic on input price. DeepSeek V4 Flash 0731 is 74% cheaper than DeepSeek V4.1 Flash 1017 Basic on output price. DeepSeek V4 Flash 0731 is 62% cheaper than DeepSeek V4.1 Flash 1017 Basic on a 1M-in / 200k-out workload.

Which has the larger context, DeepSeek V4.1 Flash 1017 Basic or DeepSeek V4 Flash 0731?

DeepSeek V4.1 Flash 1017 Basic: 1M tokens; DeepSeek V4 Flash 0731: 1M tokens.

Where can I use both DeepSeek V4.1 Flash 1017 Basic and DeepSeek V4 Flash 0731?

hyper, inferx