Gemma 3 27B pricing.
Prices checked
Gemma 3 27B costs $0.08 in and $0.35 out per million tokens from OpenRouter; the cheapest price is $0.10 at Hugging Face Inference Providers, checked .
OpenRouter's own price
OpenRouter
$0.08 in · $0.35 out
83% below the typical price of the 392 text models we track.
Cheapest price
Hugging Face Inference Providers
$0.08 in · $0.16 out
32% less than OpenRouter, and the provider says why.
Every provider selling Gemma 3 27B
- 1
$0.08 in · $0.16 out
$0.10/M tokens - 2
$0.08 in · $0.16 out
$0.10/M tokens - 3
$0.08 in · $0.16 out
$0.10/M tokens - 4
$0.08 in · $0.16 out · 110k context here
$0.10/M tokens - 5
$0.08 in · $0.16 out
$0.10/M tokens - 6
$0.08 in · $0.17 out
$0.11/M tokens - 7
$0.09 in · $0.25 out
$0.13/M tokens - 8
$0.12 in · $0.20 out · 98k context here
$0.14/M tokens - 9
$0.12 in · $0.20 out · 98k context here
$0.14/M tokens - 10
$0.12 in · $0.20 out · 33k context here
$0.14/M tokens - 11
$0.08 in · $0.35 out
$0.15/M tokens - 12
NextBit
Same as maker$0.08 in · $0.35 out
$0.15/M tokens - 13
$0.08 in · $0.35 out
$0.15/M tokens - 14
$0.10 in · $0.30 out
$0.15/M tokens - 15
$0.10 in · $0.30 out · 110k context here
$0.15/M tokens - 16
$0.10 in · $0.30 out · 110k context here
$0.15/M tokens - 17
$0.10 in · $0.30 out · 128k context here
$0.15/M tokens - 18Costs more
$0.12 in · $0.30 out
$0.16/M tokens - 19
$0.08 in · $0.45 out
$0.17/M tokens - 20
$0.08 in · $0.45 out
$0.17/M tokens - 21Costs more
$0.16 in · $0.49 out · 128k context here
$0.24/M tokens - 22
$0.30 in · $0.30 out · 128k context here
$0.30/M tokens - 23
GreenPT
Costs more$0.34 in · $0.68 out · 40k context here
$0.43/M tokens - 24
STACKIT
Costs more$0.53 in · $0.76 out · 37k context here
$0.59/M tokens - 25
$0.90 in · $0.90 out
$0.90/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$0.10 in · $0.30 out · 33k context here
$0.15/M tokens
What it costs for your work
A month at OpenRouter's own price
A month at Hugging Face Inference Providers, 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 27B on a server you rent by the month. It needs about 22 GB of RAM on a CPU, and the cheapest plan we track with that much and a disk included is Leaseweb VPS 4 at $26.13 a month, streaming about 1.4–2.9 tok/s. Every plan that fits
On a GPU by the hour
The RTX A5000 holds Gemma 3 27B in 24 GB of memory against the 22 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 27B and sells it on no catalog we read, so the price every row is measured against is OpenRouter's.
- 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 27B does, cheapest first. Each percentage is against Gemma 3 27B's cheapest price, $0.10 per M tokens.
Frequently asked
- Who sells Gemma 3 27B cheapest?
- No provider sells Gemma 3 27B below OpenRouter's own price for a reason it publishes. 23 providers sell it at that price or above, and every one of them is on this page.
- Is Gemma 3 27B open weights?
- Yes. Google publishes the weights, so anyone may host Gemma 3 27B, which is why 23 providers sell it and why their prices differ so much.
- How much context does Gemma 3 27B hold?
- 131,072 tokens in one call, which is about 131k, and it can call your own functions.
- How does Gemma 3 27B compare with the rest of the market?
- At $0.15 per million tokens, OpenRouter's own price is 83% below the typical $0.88 across the 392 text models we track.