GPT OSS 120B vs GLM-5.3: API price and specs

GPT OSS 120B is 86% cheaper than GLM-5.3 on input price.

GPT OSS 120B is 85% cheaper than GLM-5.3 on output price.

GPT OSS 120B is 85% cheaper than GLM-5.3 on a 1M-in / 200k-out workload.

GLM-5.3 has a 700% larger context than GPT OSS 120B.

Field	GPT OSS 120B	GLM-5.3
Lowest input, per 1M	$0.027	$0.19 +603.3%
Median input, per 1M	$0.15	$1.40 +833.3%
Lowest output, per 1M	$0.098	$0.64 +553.1%
Median output, per 1M	$0.60	$4.40 +633.3%
Lowest unit price	—	$0.033 / request
Cost of 1M in + 200k out	$0.0466	$0.32 +582.2%
Context	131K +87.5%	1M
Max output	131K +87.5%	1M
Providers	43 +34.8%	66
Regions	EU, GLOBAL, US	APAC, EU, FI, GLOBAL, US
Accepts	file, text	file, image, text
Returns	text	text
Type	Text models	Text models
Free option	yes	yes
Cheapest provider	kilo	trustedrouter

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

abacus, aiand, aihubmix, aiml, aki-io, baseten, cloudflare-workers-ai, cometapi, cortecs, deepinfra, digitalocean, edenai, fastrouter, fireworks-ai, huggingface, hyper, impossibl, io-net, jiekou, kenari, kilo, melious, nebius, novita, ollama, ollama-cloud, openrouter, orcarouter, poe, requesty, siliconflow, synthetic, tinfoil, togetherai, trustedrouter, vercel

Frequently asked questions

Which is cheaper, GPT OSS 120B or GLM-5.3?

GPT OSS 120B is 86% cheaper than GLM-5.3 on input price. GPT OSS 120B is 85% cheaper than GLM-5.3 on output price. GPT OSS 120B is 85% cheaper than GLM-5.3 on a 1M-in / 200k-out workload.

Which has the larger context, GPT OSS 120B or GLM-5.3?

GPT OSS 120B: 131K tokens; GLM-5.3: 1M tokens.

Where can I use both GPT OSS 120B and GLM-5.3?