DeepSeek V4 Pro vs Hy4 preview: API price and specs

DeepSeek V4 Pro is 76% cheaper than Hy4 preview on input price.

DeepSeek V4 Pro is 73% cheaper than Hy4 preview on output price.

DeepSeek V4 Pro is 75% cheaper than Hy4 preview on a 1M-in / 200k-out workload.

DeepSeek V4 Pro has a 0% larger context than Hy4 preview.

Field	DeepSeek V4 Pro	Hy4 preview
Lowest input, per 1M	$0.16	$0.66 +318.1%
Median input, per 1M	$1.50 +80.1%	$0.83
Lowest output, per 1M	$0.63	$2.32 +265.8%
Median output, per 1M	$3.25 +29.9%	$2.50
Lowest unit price	—	—
Cost of 1M in + 200k out	$0.28	$1.12 +294.9%
Context	1M	1M
Max output	1M	131K +87.5%
Providers	44	18 +59.1%
Regions	APAC, EU, GLOBAL, US	APAC, US
Accepts	file, text	file, text
Returns	text	text
Type	Text models	Text models
Free option	no	no
Cheapest provider	trustedrouter	kenari

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, aiml, deepinfra, edenai, fastrouter, huggingface, impossibl, io-net, kenari, kilo, novita, opencode-go, openrouter, poe, requesty, trustedrouter, vercel, zenmux

Frequently asked questions

Which is cheaper, DeepSeek V4 Pro or Hy4 preview?

DeepSeek V4 Pro is 76% cheaper than Hy4 preview on input price. DeepSeek V4 Pro is 73% cheaper than Hy4 preview on output price. DeepSeek V4 Pro is 75% cheaper than Hy4 preview on a 1M-in / 200k-out workload.

Which has the larger context, DeepSeek V4 Pro or Hy4 preview?

DeepSeek V4 Pro: 1M tokens; Hy4 preview: 1M tokens.

Where can I use both DeepSeek V4 Pro and Hy4 preview?

aihubmix, aiml, deepinfra, edenai, fastrouter, huggingface, impossibl, io-net, kenari, kilo, novita, opencode-go, openrouter, poe, requesty, trustedrouter, vercel, zenmux