Who sells Gemma 4 26B A4B IT cheapest?

Kilo Gateway, at $0.04 in and $0.22 out per million tokens, read on 16 Sept 2026. A promotion on Google's models: 50% off on Kilo's gateway, with no end date published.

Is Gemma 4 26B A4B IT open weights?

Yes. Google publishes the weights, so anyone may host Gemma 4 26B A4B IT, which is why 30 providers sell it and why their prices differ so much.

How much context does Gemma 4 26B A4B IT hold?

262,144 tokens in one call, which is about 262k, and it can call your own functions.

How does Gemma 4 26B A4B IT compare with the rest of the market?

At $1.05 per million tokens, Google's price is 70% below the $3.55 median across the 337 text models we track.

Gemma 4 26B A4B IT pricing.

prices as of 16 Sept 2026 · 30 providers · 35 prices

Google's Gemma 4 26B A4B IT holds 262k tokens of context, reads images as well as text and has a reasoning mode. Open weights, so anyone may host it, which is why the prices below differ so much.

Gemma 4 26B A4B IT costs $0.15 in and $0.60 out per million tokens from Google; the cheapest price we can explain is $0.35 at Kilo Gateway, checked 16 Sept 2026.

tool callingreads imagesreasoningstructured outputopen weights262k contextreleased 2 Apr 2026

Compare withvs Command R vs DeepSeek V4.1 Flash vs DeepSeek V4.1 Flash or any model →

Google list price

$1.05/M tokens

$0.15 in · $0.60 out

read 16 Sept 2026 · 70% below the market median

Cheapest price we can explain

$0.35/M tokens

$0.04 in · $0.22 out · 67% under list

Kilo Gateway

View at Kilo Gateway ↗

read 16 Sept 2026

What it costs for your work

how manypages a month

Google list price

$0.126a month

cheapest we can explain · Kilo Gateway

$0.0384a month

difference

$0.0876saved

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.

Every provider selling Gemma 4 26B A4B IT

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 Google's price.

The maker's list price

1 price

What the lab that trained the model charges on its own API.

Google
The price Google charges for the model it trained. Every row below is measured against it.
Google ↗
$0 / $0in / out per M
0.00×of list price

Cheaper, and we know why

30 prices

Below list, with a published reason: hosting the open weights, a regional price list, credits, a stated discount.

Kilo Gateway
A promotion on Google's models: 50% off on Kilo's gateway, with no end date published.
Kilo Gateway ↗
$0.04 / $0.22in / out per M
0.33×of list price
Darkbloom
Hosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.
131k context here
$0.04 / $0.22in / out per M
0.33×of list price
Nous Portal
Resells OpenRouter's catalog at 0.80× the listed price, funded by a subscription whose credits carry a 10% bonus.
Nous Portal ↗
$0.04 / $0.22in / out per M
0.33×of list price
Eden AI
Routes to a host serving the open weights; precision not disclosed.
Eden AI ↗
$0.04 / $0.22in / out per M
0.33×of list price
LLMTR
Routes to a host serving the open weights; precision not disclosed.
131k context hereLLMTR ↗
$0.04 / $0.22in / out per M
0.33×of list price
NanoGPT
Routes to a host serving the open weights; precision not disclosed.
NanoGPT ↗
$0.12 / $0.06in / out per M
0.40×of list price
OrcaRouter
Hosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.
$0.06 / $0.33in / out per M
0.49×of list price
DekaLLM
Hosts the open weights on its own servers, so the price is its own, not a resale. Precision bf16.
bf16 precision
$0.06 / $0.33in / out per M
0.49×of list price
TrustedRouter
Routes to a host serving the open weights; precision not disclosed.
TrustedRouter ↗
$0.07 / $0.32in / out per M
0.51×of list price
LLM Gateway
Routes to a host serving the open weights; precision not disclosed.
LLM Gateway ↗
$0.07 / $0.34in / out per M
0.52×of list price
Requesty
Routes to a host serving the open weights; precision not disclosed.
Requesty ↗
$0.07 / $0.34in / out per M
0.52×of list price
DeepInfra
Hosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.
DeepInfra ↗
$0.07 / $0.34in / out per M
0.52×of list price
DeepInfra
Serves the open weights at fp8, a lower precision than the maker's, so not quite the same product.
fp8 precisionDeepInfra ↗
$0.07 / $0.34in / out per M
0.52×of list price
OpenRouter
Routes to a host serving the open weights; precision not disclosed.
OpenRouter ↗
$0.09 / $0.30in / out per M
0.54×of list price
NextBit
Hosts the open weights on its own servers, so the price is its own, not a resale. Precision bf16.
bf16 precision
$0.09 / $0.30in / out per M
0.54×of list price
Cloudflare Workers AI
Hosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.
256k context hereCloudflare Workers AI ↗
$0.10 / $0.30in / out per M
0.57×of list price
Charm Hyper
Hosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.
256k context here
$0.10 / $0.33in / out per M
0.60×of list price
io.net Intelligence
Hosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.
262k context hereio.net Intelligence ↗
$0.10 / $0.33in / out per M
0.60×of list price
Makora
Hosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.
$0.10 / $0.34in / out per M
0.61×of list price
SiliconFlow
Hosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.
SiliconFlow ↗
$0.12 / $0.40in / out per M
0.72×of list price
NanoGPT
Routes to a host serving the open weights; precision not disclosed.
NanoGPT ↗
$0.13 / $0.40in / out per M
0.75×of list price
Novita
Hosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.
Novita ↗
$0.13 / $0.40in / out per M
0.75×of list price
Hugging Face Inference Providers
Routes to a host serving the open weights; precision not disclosed.
Hugging Face Inference Providers ↗
$0.13 / $0.40in / out per M
0.75×of list price
Merge Gateway
Hosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.
$0.13 / $0.40in / out per M
0.75×of list price
Venice
Hosts the open weights on its own servers, so the price is its own, not a resale. Precision bf16.
256k context herebf16 precisionVenice ↗
$0.13 / $0.40in / out per M
0.75×of list price

showing the 25 cheapest of 30 · every row in the open dataset

Same price as the maker

2 prices

The same price the maker charges, sold by someone else.

Vercel AI Gateway
The same price Google charges.
Vercel AI Gateway ↗
$0.15 / $0.60in / out per M
1.00×of list price
Scaleway
67% above Google's price.
256k context hereScaleway ↗
$0.25 / $0.50in / out per M
1.19×of list price

Cheaper, and nobody says why

1 price · never ranked

Below list on a closed model with nothing to account for it. Shown, never ranked, never a pick.

Featherless
We could not read this provider's prices reliably, so the row is listed but never ranked.
33k context hereFeatherless ↗
$0.07 / $0.34in / out per M
0.52×of list price

Given away with limits

1 free tiers · never ranked

These providers give Gemma 4 26B A4B IT 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.

FastRouter

Frequently asked

Who sells Gemma 4 26B A4B IT cheapest?: Kilo Gateway, at $0.04 in and $0.22 out per million tokens, read on 16 Sept 2026. A promotion on Google's models: 50% off on Kilo's gateway, with no end date published.
Is Gemma 4 26B A4B IT open weights?: Yes. Google publishes the weights, so anyone may host Gemma 4 26B A4B IT, which is why 30 providers sell it and why their prices differ so much.
How much context does Gemma 4 26B A4B IT hold?: 262,144 tokens in one call, which is about 262k, and it can call your own functions.
How does Gemma 4 26B A4B IT compare with the rest of the market?: At $1.05 per million tokens, Google's price is 70% below the $3.55 median across the 337 text models we track.