DeepSeek V4.1 Flash vs GPT OSS 20B: API price and specs

GPT OSS 20B is 80% cheaper than DeepSeek V4.1 Flash on input price.

GPT OSS 20B is 73% cheaper than DeepSeek V4.1 Flash on output price.

GPT OSS 20B is 77% cheaper than DeepSeek V4.1 Flash on a 1M-in / 200k-out workload.

DeepSeek V4.1 Flash has a 700% larger context than GPT OSS 20B.

Field	DeepSeek V4.1 Flash	GPT OSS 20B
Lowest input, per 1M	$0.045 +400%	$0.009
Median input, per 1M	$0.30 +500%	$0.05
Lowest output, per 1M	$0.15 +275%	$0.04
Median output, per 1M	$1.20 +500%	$0.20
Lowest unit price	—	—
Cost of 1M in + 200k out	$0.075 +341.2%	$0.017
Context	1M	131K +87.5%
Max output	1M	131K +87.5%
Providers	60	28 +53.3%
Regions	APAC, EU, GLOBAL, US	EU, GLOBAL, US
Accepts	application/pdf, file, image, image/gif, image/jpeg, image/png, image/webp, pdf, text	file, image, text
Returns	text	text
Type	Text models	Text models
Free option	yes	yes
Cheapest provider	openrouter	edenai

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, cometapi, cortecs, deepinfra, digitalocean, edenai, fastrouter, google-vertex, huggingface, impossibl, io-net, jiekou, kenari, kilo, nvidia, ollama, ollama-cloud, openrouter, poe, requesty, siliconflow, trustedrouter, vercel

Frequently asked questions

Which is cheaper, DeepSeek V4.1 Flash or GPT OSS 20B?

GPT OSS 20B is 80% cheaper than DeepSeek V4.1 Flash on input price. GPT OSS 20B is 73% cheaper than DeepSeek V4.1 Flash on output price. GPT OSS 20B is 77% cheaper than DeepSeek V4.1 Flash on a 1M-in / 200k-out workload.

Which has the larger context, DeepSeek V4.1 Flash or GPT OSS 20B?

DeepSeek V4.1 Flash: 1M tokens; GPT OSS 20B: 131K tokens.

Where can I use both DeepSeek V4.1 Flash and GPT OSS 20B?