/ Models

Language models

Google: Gemma 3 4B

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
131K
Max output
16K
Input / 1M
$0.05
Output / 1M
$0.1
1M in + 1M out
$0.15

Everything else

Max output16K
Input / 1M$0.05
Output / 1M$0.1
Cache read / 1M
Cache write / 1M
1M in + 1M out$0.15
Takestext, image
Returnstext
Toolsno
Reasoningno
Open weightsyes
Released2025-03-13
Knowledge cutoff2024-08-31
Retires
Catalog idgoogle/gemma-3-4b-it

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