/ Models

Language models

Google: Gemma 3 27B

Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...

Maker
Google
Context window
262K
Max output
131K
Input / 1M
$0.08
Output / 1M
$0.45
1M in + 1M out
$0.53

Everything else

Max output131K
Input / 1M$0.08
Output / 1M$0.45
Cache read / 1M$0.04
Cache write / 1M
1M in + 1M out$0.53
Takestext, image
Returnstext
Toolsyes
Reasoningno
Open weightsyes
Released2025-03-12
Knowledge cutoff2024-08-31
Retires
Catalog idgoogle/gemma-3-27b-it

Benchmarks

sourceepoch
eci131.06
confidenceConfident
accessibilityOpen weights (restricted use)
gpqa0.489
gpqaStderr0.0303
mathLevel50.74
mathLevel5Stderr0.0112
aime0.197
aimeStderr0.0543

Benchmark scores by Epoch AI, CC BY 4.0.

Using it

In 00, this model is picked per agent — and per tier, so the model that answers your customers need not be the one that writes your code. Get 00.

← all models