Gemma 3 is the latest generation of open models from Google, designed for both text and image input with text output. Built on the same research foundation as Gemini, Gemma 3 supports over 140 languages, a 131K token context window, and comes in more size options than earlier versions. Available as both pre-trained and instruction-tuned variants with open weights, these models are optimized for tasks like question answering, summarization, reasoning, and image understanding. Their small footprint allows easy deployment on laptops, desktops, and private infrastructure, making advanced AI more accessible.
Provider
Context Size
Max Output
Cost
Speed
nebius_fast
128K
128K
€NaN/M
155.00 tps
nebius_fdt
128K
128K
€NaN/M
155.00 tps
nebius_slow
128K
128K
€NaN/M
155.00 tps
nebiusf
128K
128K
€NaN/M
155.00 tps
API Usage
Seamlessly integrate our API into your project by following these simple steps: