Gemma 3
language modelGoogle
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,...
Key facts
| Made by | |
|---|---|
| Type | language model |
| Released | March 12, 2025 |
| Reads at once | 131,072 tokens |
| Price (API, per million tokens) | $0.05 in · $0.1 out |
| Input → output | text, image → text |
| Sizes | 4B, 12B, 27B |
Questions about Gemma 3
Who makes Gemma 3?
Gemma 3 is made by Google.
When was Gemma 3 released?
We first saw Gemma 3 listed on March 12, 2025.
How much does Gemma 3 cost?
Through OpenRouter it costs $0.05 per million input tokens and $0.1 per million output tokens. Prices change, so check the provider before you build on it.
How much text can Gemma 3 read at once?
Up to 131,072 tokens, roughly 98.3K words.
More from Google
diffusiongemmaGoogle · vision and multimodal model
Jun 9, 2026released
Gemma 4Google · language model
Mar 2, 2026released
Adk-Pythongoogle · AI agent
Apr 1, 2025released
Gemma-4-AssistantGoogle · vision and multimodal model
Apr 23, 2026released
Gemma-4-AssistantGoogle · vision and multimodal model
Apr 23, 2026released
Adk-Python 2.14google · AI agent
Nov 6, 2026expected
Other language models
gpt2Openai Community · language model
Mar 2, 2022released
Qwen3.8Alibaba (Qwen) · language model
Aug 5, 2026released
Qwen3 VLAlibaba (Qwen) · language model
Sep 23, 2025released
Qwen2.5 VLAlibaba (Qwen) · language model
Jan 26, 2025released
optMeta · language model
May 11, 2022released
Qwen3.6Alibaba (Qwen) · language model
Apr 15, 2026released
Ollamaollama · language model
Jun 26, 2023released
pythiaEleutherAI · language model
Feb 8, 2023released
Modelcast collects this page automatically from public sources (OpenRouter). Facts are copied from those sources, not written by the maker. Not affiliated with Google.