Pass IndexThe State of AISign in

Gemma 3 12B

Gemma 3 introduces multimodality, supporting vision-language input and text outputs.

text + image → text · made by Google

$0.05→$0.15per Mtok in / out
DeepInfra · 10 sellers

Sold by 17 ways

SellerLaneRate
AWS Bedrock cloudbatch$0.05per Mtok in$0.15per Mtok outraw.githubusercontent.com · read 2026-10-31
AWS Bedrock cloudflex$0.05per Mtok in$0.15per Mtok outraw.githubusercontent.com · read 2026-10-31
AWS Bedrock cloudstandard$0.09per Mtok in$0.29per Mtok outmodels.dev · read 2026-10-31
Crusoe cloudstandard$0.1per Mtok in$0.1per Mtok outraw.githubusercontent.com · read 2026-10-31
Databricks cloudstandard$0.15per Mtok in$0.5per Mtok out$0.15per Mtok cached$0.15per Mtok cache writeraw.githubusercontent.com · read 2026-10-31
AWS Bedrock cloudpriority$0.16per Mtok in$0.51per Mtok outraw.githubusercontent.com · read 2026-10-31
OpenRouter 4 ways$0.05per Mtok in$0.15per Mtok out
OpenRouter aggregatordeepinfra/bf16/flex$0.04per Mtok in$0.12per Mtok outopenrouter.ai · read 2026-10-17
OpenRouter aggregatorstandard$0.05per Mtok in$0.15per Mtok outopenrouter.ai · read 2026-08-24
OpenRouter aggregatordeepinfra/bf16/priority$0.075per Mtok in$0.23per Mtok outopenrouter.ai · read 2026-10-16
OpenRouter aggregatornextbit/int4$0.075per Mtok in$0.15per Mtok out$0.05per Mtok cachedopenrouter.ai · read 2026-10-24
DeepInfra aggregatorstandard$0.05per Mtok in$0.15per Mtok outapi.deepinfra.com · read 2026-08-25
Featherless AI aggregatorstandard$0.05per Mtok in$0.15per Mtok outapi.featherless.ai · read 2026-09-20
Hugging Face Inference Providers 2 ways$0.05per Mtok in$0.15per Mtok out
Hugging Face Inference Providers aggregatorstandard$0.05per Mtok in$0.15per Mtok outmodels.dev · read 2026-10-31
Hugging Face Inference Providers aggregatordeepinfra$0.05per Mtok in$0.15per Mtok outrouter.huggingface.co · read 2026-08-25
Nous Research aggregatorstandard$0.05per Mtok in$0.15per Mtok outinference-api.nousresearch.com · read 2026-09-12
Novita AI aggregatorstandard$0.05per Mtok in$0.1per Mtok outapi.novita.ai · read 2026-08-25
ElectronHub aggregatorstandard$0.35per Mtok in$0.56per Mtok outapi.electronhub.ai · read 2026-10-31

Measured 10 standings

PlaceBoardMetricScore
8thof 111Vectara Hallucination LeaderboardHallucination Rate4.4
130thof 131Artificial Analysis · Agentic IndexIndex0.1
160thof 163Artificial Analysis · Coding IndexIndex5.8
196thof 197Lmca — Epoch AIScore4.46
223rdof 235Dtbench — Epoch AIAccuracy48.8
229thof 260Critpt — Epoch AIAccuracy0
231stof 414LMArena · TextScore (Elo)1342
232ndof 235Scicode — Epoch AIScore16.435
248thof 306OTIS Mock AIME 2024-2025mean_score16.667
281stof 326GPQA Diamondmean_score39.457

About

Gemma 3 12B — a text model from Google, sold by 10 companies from $0.05 in and $0.15 out per million tokens, placed 8th of 111 on Vectara Hallucination Leaderboard.

It takes text and images and returns text, with a context window of 32,768 tokens. It was published in December 2024, trained on material up to August 2024. Its sellers say it can call a tool. The catalogue files it under reasoning. Ten companies sell it. The cheapest is $0.05 in and $0.15 out per million tokens at DeepInfra. Beside the standard rate there are batch, flex, faster, separately routed and regional lanes. It has been measured on 10 boards, and stands best at 8th of 111 on Vectara Hallucination Leaderboard.

Every current figure

Maker
Google
Register
model
Takes
text + image
Returns
text
Context
32,768 tokens
Published
December 2024
Knowledge to
August 2024
Parameters
12 billion
Licence
not read
Sellers
10
Maker's own price
not read
Price
$0.05 in and $0.15 out per million tokens — DeepInfra
Boards
10
Best place
8th of 111 — Vectara Hallucination Leaderboard

Known as 3 names

google/gemma-3-12b-itRedHatAI/gemma-3-12b-itunsloth/gemma-3-12b-it