Muse Spark Open vs GPT OSS 120B: API price and specs

GPT OSS 120B is 98% cheaper than Muse Spark Open on input price.

GPT OSS 120B is 98% cheaper than Muse Spark Open on output price.

GPT OSS 120B is 98% cheaper than Muse Spark Open on a 1M-in / 200k-out workload.

Muse Spark Open has a 700% larger context than GPT OSS 120B.

Field	Muse Spark Open	GPT OSS 120B
Lowest input, per 1M	$1.10 +3984.2%	$0.027
Median input, per 1M	$1.25 +733.3%	$0.15
Lowest output, per 1M	$4.25 +4236.7%	$0.098
Median output, per 1M	$4.25 +608.3%	$0.60
Lowest unit price	—	—
Cost of 1M in + 200k out	$1.95 +4090.4%	$0.0466
Context	1M	131K +87.5%
Max output	1M	131K +87.5%
Providers	17 +60.5%	43
Regions	GLOBAL, US	EU, GLOBAL, US
Accepts	audio, file, image, pdf, text, video	file, text
Returns	text	text
Type	Text models	Text models
Free option	no	yes
Cheapest provider	kenari	kilo

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

aiml, baseten, edenai, fireworks-ai, hyper, impossibl, kenari, kilo, nebius, ollama, ollama-cloud, openrouter, poe, requesty, togetherai, trustedrouter, vercel

Frequently asked questions

Which is cheaper, Muse Spark Open or GPT OSS 120B?

GPT OSS 120B is 98% cheaper than Muse Spark Open on input price. GPT OSS 120B is 98% cheaper than Muse Spark Open on output price. GPT OSS 120B is 98% cheaper than Muse Spark Open on a 1M-in / 200k-out workload.

Which has the larger context, Muse Spark Open or GPT OSS 120B?

Muse Spark Open: 1M tokens; GPT OSS 120B: 131K tokens.

Where can I use both Muse Spark Open and GPT OSS 120B?

aiml, baseten, edenai, fireworks-ai, hyper, impossibl, kenari, kilo, nebius, ollama, ollama-cloud, openrouter, poe, requesty, togetherai, trustedrouter, vercel