Gemma 3 27B
Overview
Gemma 3 27B is a 27-billion-parameter vision-language model from Google, handling text and image input and generating text output. It features a 128K context window, multilingual support, and open weights. Suitable for complex question answering, summarization, reasoning, and image understanding tasks.
Gemma 3 27B was released on March 12, 2025. API access is available through DeepInfra, Novita.
Performance
Timeline
Specifications
Benchmarks
Gemma 3 27B Performance Across Datasets
Scores sourced from the model's scorecard, paper, or official blog posts
llm-stats.com - Thu Jan 15 2026Pricing
Pricing, performance, and capabilities for Gemma 3 27B across different providers:
| Provider | Input ($/M) | Output ($/M) | Max Input | Max Output | Latency (s) | Throughput | Quantization | Input | Output |
|---|---|---|---|---|---|---|---|---|---|
 DeepInfra | $0.10 | $0.20 | 131.1K | 131.1K | 0.2 | 33.0 c/s | — | Text Image Audio Video | Text Image Audio Video |
 Novita | $0.11 | $0.20 | 131.1K | 131.1K | 0.2 | 33.0 c/s | — | Text Image Audio Video | Text Image Audio Video |
Price Comparison for Gemma 3 27B
Price per 1M input tokens (USD), lower is better
llm-stats.com - Thu Jan 15 2026Throughput Comparison for Gemma 3 27B
Tokens per second, higher is better
llm-stats.com - Thu Jan 15 2026Latency Comparison for Gemma 3 27B
Time to first token (s), lower is better
llm-stats.com - Thu Jan 15 2026API Access
API Access Coming Soon
API access for Gemma 3 27B will be available soon through our gateway.
Recent Posts
Recent Reviews
FAQ
Common questions about Gemma 3 27B