Gemma 3 12B pricing.
Prices checked
Gemma 3 12B costs $0.05 in and $0.15 out per million tokens from OpenRouter; the cheapest price is $0.06 at Kilo Gateway, checked .
OpenRouter's own price
OpenRouter
$0.05 in · $0.15 out
91% below the typical price of the 392 text models we track.
Cheapest price
Kilo Gateway
$0.04 in · $0.12 out
20% less than OpenRouter, and the provider says why.
Every provider selling Gemma 3 12B
- 1
$0.04 in · $0.12 out
$0.06/M tokens - 2
$0.04 in · $0.12 out
$0.06/M tokens - 3
$0.05 in · $0.10 out
$0.06/M tokens - 4
$0.05 in · $0.10 out
$0.06/M tokens - 5
$0.05 in · $0.10 out
$0.06/M tokens - 6
$0.05 in · $0.11 out
$0.07/M tokens - 7
$0.05 in · $0.15 out
$0.08/M tokens - 8
$0.05 in · $0.15 out
$0.08/M tokens - 9
$0.05 in · $0.15 out
$0.08/M tokens - 10
$0.05 in · $0.15 out
$0.08/M tokens - 11
$0.05 in · $0.15 out
$0.08/M tokens - 12
$0.05 in · $0.15 out
$0.08/M tokens - 13Costs more
$0.05 in · $0.16 out
$0.08/M tokens - 14
NextBit
Costs more$0.07 in · $0.15 out
$0.09/M tokens - 15
$0.10 in · $0.10 out
$0.10/M tokens - 16
$0.09 in · $0.29 out · 128k context here
$0.14/M tokens - 17
$0.27 in · $0.27 out
$0.27/M tokens
Not ranked
Below the maker's own price with nothing published to account for it, from a catalog we could not read reliably, or a free tier, which is a limit rather than a price. Why
given away with limits
free$0.05 in · $0.15 out · 33k context here
$0.08/M tokens
What it costs for your work
A month at OpenRouter's own price
A month at Kilo Gateway, the cheapest
What you save
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
On a server by the month
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 Leaseweb VPS 2 at $9.04 a month, streaming about 1.9–3.9 tok/s. Every plan that fits
On a GPU by the hour
The RTX A5000 holds Gemma 3 12B in 24 GB of memory against the 11.8 GB the weights, the context and the runtime need. The cheapest one we track is RunPod's RTX A5000 · Community Cloud at $0.16/GPU-hr, which is $116.80 for the 730 hours in a month, checked 31 Oct. Every GPU price
How we count
Prices are per million tokens. The big number on each row is blended 3 in : 1 out, the way most work uses a model. A price below OpenRouter's own is listed as cheapest only when the provider says why. Google trained Gemma 3 12B and sells it on no catalog we read, so the price every row is measured against is OpenRouter's.
- Promotion
- A discount the provider publishes, which may end.
- Runs it themselves
- The provider runs the open weights on hardware of its own, so the price is its own rather than a resale.
- Same as maker
- Sold by someone else at the price the maker charges.
- Costs more
- Sold by someone else for more than the maker charges.
- Free tier
- Given away inside a quota. A limit is not a price, so it is never called cheapest.
- Not ranked
- Below the maker's price on a closed model with nothing to account for it, or from a catalog we could not read reliably. Listed, and never a pick.
Similar models
Models from other labs that do what Gemma 3 12B does, cheapest first. Each percentage is against Gemma 3 12B's cheapest price, $0.06 per M tokens.
Frequently asked
- Who sells Gemma 3 12B cheapest?
- Kilo Gateway, at $0.04 in and $0.12 out per million tokens, checked 31 Oct 2026. A discount the provider publishes, which may end.
- Is Gemma 3 12B open weights?
- Yes. Google publishes the weights, so anyone may host Gemma 3 12B, which is why 16 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 $0.08 per million tokens, OpenRouter's own price is 91% below the typical $0.88 across the 392 text models we track.