Gemma 3 12B pricing.
prices as of · 14 providers · 17 prices
Google's Gemma 3 12B holds 131k tokens of context and reads images as well as text. Open weights, so anyone may host it, which is why the prices below differ so much.
Gemma 3 12B costs $0.05 in and $0.15 out per million tokens from OpenRouter, and no provider goes below it with a reason we can point at.
OpenRouter list price
$0.30/M tokens
$0.05 in · $0.15 out
read · 92% below the market median
Cheapest price we can explain
no price
Nobody goes below OpenRouter's price for a reason we can point at, so the list price is the one to beat. Every other price is below.
What it costs for your work
OpenRouter list price
$0.039a month
cheapest we can explain
none
difference
no list price
A page is about 600 tokens in and 60 out, a support reply 200 in and 300 out, an email 150 in and 250 out. Nothing else is counted: no cache discount, no batch rate, no free tier.
Run it yourself
every plan that fits Gemma 3 12B →Google publishes the weights, so you can run Gemma 3 12B on a server you rent by the month. It needs about 11.8 GB of RAM on a CPU, and the cheapest plan we track with that much and a disk included is HOSTKEY vm.v2-medium at $16.15/mo, streaming an estimated 2.6–5.2 tok/s.
Every provider selling Gemma 3 12B
Four groups, decided by the price and by what the provider publishes about it. Prices are per million tokens, and the share is that row against OpenRouter's price. Google trained Gemma 3 12B and sells it on no catalog we read, so the price every row is measured against is OpenRouter's.
Same price as the maker
15 pricesThe same price the maker charges, sold by someone else.
$0.05 / $0.10in / out per M
0.83×of list price
HeliconeThe same price OpenRouter charges.
$0.05 / $0.10in / out per M
0.83×of list price
$0.05 / $0.10in / out per M
0.83×of list price
$0.05 / $0.11in / out per M
0.88×of list price
$0.05 / $0.15in / out per M
1.00×of list price
Hugging Face Inference ProvidersThe same price OpenRouter charges.
$0.05 / $0.15in / out per M
1.00×of list price
$0.05 / $0.15in / out per M
1.00×of list price
$0.05 / $0.15in / out per M
1.00×of list price
$0.05 / $0.15in / out per M
1.00×of list price
$0.05 / $0.15in / out per M
1.00×of list price
$0.05 / $0.15in / out per M
1.00×of list price
$0.05 / $0.15in / out per M
1.00×of list price
$0.10 / $0.10in / out per M
1.33×of list price
$0.09 / $0.29in / out per M
1.87×of list price
$0.27 / $0.27in / out per M
3.63×of list price
Cheaper, and nobody says why
1 price · never rankedBelow list on a closed model with nothing to account for it. Shown, never ranked, never a pick.
FeatherlessWe could not read this provider's prices reliably, so the row is listed but never ranked.
33k context hereFeatherless ↗$0.05 / $0.15in / out per M
1.00×of list price
Given away with limits
1 free tiers · never rankedThese providers give Gemma 3 12B away inside a quota of their own. A limit is not a price, so none of them counts as cheapest here or anywhere else on the site.
NVIDIA build
Frequently asked
- Who sells Gemma 3 12B cheapest?
- No provider sells Gemma 3 12B below OpenRouter's price with a reason we can point at. 14 providers sell it at or above list, and those prices are all on this page.
- Is Gemma 3 12B open weights?
- Yes. Google publishes the weights, so anyone may host Gemma 3 12B, which is why 14 providers sell it and why their prices differ so much.
- How much context does Gemma 3 12B hold?
- 131,072 tokens in one call, which is about 131k, and it can call your own functions.
- How does Gemma 3 12B compare with the rest of the market?
- At $0.30 per million tokens, OpenRouter's price is 92% below the $3.55 median across the 337 text models we track.