AI Rate Card

Gemma 3 12B IT vs GLM-5.3: API price and specs

Gemma 3 12B IT is 79% cheaper than GLM-5.3 on input price.

Gemma 3 12B IT is 84% cheaper than GLM-5.3 on output price.

Gemma 3 12B IT is 81% cheaper than GLM-5.3 on a 1M-in / 200k-out workload.

GLM-5.3 has a 700% larger context than Gemma 3 12B IT.

FieldGemma 3 12B ITGLM-5.3
Lowest input, per 1M$0.04$0.19 +374.8%
Median input, per 1M$0.05275$1.40 +2554%
Lowest output, per 1M$0.10$0.64 +540%
Median output, per 1M$0.15$4.40 +2833.3%
Lowest unit price—$0.033 / request
Cost of 1M in + 200k out$0.06$0.32 +429.8%
Context131K +87.5%1M
Max output131K +87.5%1M
Providers15 +77.3%66
RegionsEU, GLOBAL, USAPAC, EU, FI, GLOBAL, US
Acceptsimage, image/gif, image/jpeg, image/png, image/webp, textfile, image, text
Returnstexttext
TypeText modelsText models
Free optionyesyes
Cheapest providerkilotrustedrouter

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, amazon-bedrock, cloudflare-workers-ai, deepinfra, edenai, fastrouter, huggingface, jiekou, kilo, novita, nvidia, openrouter, trustedrouter

Frequently asked questions

Which is cheaper, Gemma 3 12B IT or GLM-5.3?

Gemma 3 12B IT is 79% cheaper than GLM-5.3 on input price. Gemma 3 12B IT is 84% cheaper than GLM-5.3 on output price. Gemma 3 12B IT is 81% cheaper than GLM-5.3 on a 1M-in / 200k-out workload.

Which has the larger context, Gemma 3 12B IT or GLM-5.3?

Gemma 3 12B IT: 131K tokens; GLM-5.3: 1M tokens.

Where can I use both Gemma 3 12B IT and GLM-5.3?

aihubmix, aiml, amazon-bedrock, cloudflare-workers-ai, deepinfra, edenai, fastrouter, huggingface, jiekou, kilo, novita, nvidia, openrouter, trustedrouter