DeepSeek V4 Pro vs Step 3.5 Flash: API price and specs

Step 3.5 Flash is 43% cheaper than DeepSeek V4 Pro on input price.

Step 3.5 Flash is 53% cheaper than DeepSeek V4 Pro on output price.

Step 3.5 Flash is 47% cheaper than DeepSeek V4 Pro on a 1M-in / 200k-out workload.

DeepSeek V4 Pro has a 300% larger context than Step 3.5 Flash.

Field	DeepSeek V4 Pro	Step 3.5 Flash
Lowest input, per 1M	$0.16 +75.8%	$0.09
Median input, per 1M	$1.50 +1401.6%	$0.10
Lowest output, per 1M	$0.63 +111%	$0.30
Median output, per 1M	$3.25 +983.3%	$0.30
Lowest unit price	—	—
Cost of 1M in + 200k out	$0.28 +89.9%	$0.15
Context	1M	262K +75%
Max output	1M	262K +75%
Providers	44	13 +70.5%
Regions	APAC, EU, GLOBAL, US	US
Accepts	file, text	text
Returns	text	text
Type	Text models	Text models
Free option	no	no
Cheapest provider	trustedrouter	deepinfra

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

aihubmix, deepinfra, edenai, empiriolabs, huggingface, kilo, openrouter, siliconflow, siliconflow-cn, trustedrouter, zenmux

Frequently asked questions

Which is cheaper, DeepSeek V4 Pro or Step 3.5 Flash?

Step 3.5 Flash is 43% cheaper than DeepSeek V4 Pro on input price. Step 3.5 Flash is 53% cheaper than DeepSeek V4 Pro on output price. Step 3.5 Flash is 47% cheaper than DeepSeek V4 Pro on a 1M-in / 200k-out workload.

Which has the larger context, DeepSeek V4 Pro or Step 3.5 Flash?

DeepSeek V4 Pro: 1M tokens; Step 3.5 Flash: 262K tokens.

Where can I use both DeepSeek V4 Pro and Step 3.5 Flash?

aihubmix, deepinfra, edenai, empiriolabs, huggingface, kilo, openrouter, siliconflow, siliconflow-cn, trustedrouter, zenmux