Models/Gemma 3 27B
GoogleGoogle / Gemma 3 27B
Released: 3/12/2025
texttext
Input: $0.20 / Output: $0.40

Gemma 3 27B Instruct is a 27 billion parameter multimodal LLM that excels in a wide variety of tasks, including question answering, reasoning, code generation, and image understanding. It features a large 128K token context window and supports over 140 languages, enabling complex analysis and multilingual capabilities.

Some other noteworthy features of Gemma 3 27B Instruct include function calling for task automation, structured output generation, and the ability to process both text and images.

MetricValue
Parameter Count27 billion
Mixture of ExpertsNo
Context Length128,000 tokens
MultilingualYes
Quantized*No

*Quantization is specific to the inference provider and the model may be offered with different quantization levels by other providers.

Google models available on Oxen.ai
ModalityPrice (1M tokens)
ModelInference providerInputOutputInputOutput
Google
texttext$0.08$0.30
Google
texttext$0.04$0.15
Google
texttext$1.25$5.00
Google
text, imagetext$0.10$0.40
Google
text, imagetext$0.08$0.30
Google
texttext$1.25$5.00
Google
text, imagetext$2.50$5.00
Groq
texttext$0.20$0.20
Google
texttext$0.20$0.40
Google
textembeddings$0.02$0.02
See all models available on Oxen.ai