Gemini Gemma 2 27b It
At a glance
- Price per 1M tokens (input)
- $0.35
- Price per 1M tokens (output)
- $1.05
- Context
- 8,192 tokens
- Free access
- yes (see below)
Refreshed daily; data verified October 28, 2026. Published October 28, 2026.
Gemini Gemma 2 27b is a mid-sized language model from Google designed for teams that need multimodal reasoning without the overhead of larger systems. It suits document analysis, visual question answering, and workflows that require interacting with external software through tool calling, which lets the model request actions from connected applications. Google's approach emphasizes open weights and integration with its broader Gemini ecosystem, giving organizations flexibility to deploy the model in their own infrastructure while maintaining compatibility with Google's tools.
Specifications & pricing
| Input (per 1M tokens) | $0.35 |
|---|---|
| Output (per 1M tokens) | $1.05 |
| Context window | 8,192 tokens |
| Max output | 8,192 tokens |
| Capabilities | images, tool calling |
LiteLLM community dataset (MIT), verified October 28, 2026. Official Google (Gemini) pricing.
What Gemini Gemma 2 27b It would cost on your workload — run it through the cost calculator →
Where to try Gemini Gemma 2 27b It for free
- Google (Gemini) offers a free chat — Gemini (free plan). A vendor's free chat may run a different model from the same family — the exact model is not guaranteed.
- 🎁 On our promo-codes page: Gemini for free: access and discounts.
Frequently asked questions
What is this model good for?+
It handles text generation, image understanding, and function calling, making it suitable for customer support agents, visual document processing, and applications that need to trigger actions in external systems.
How do I get started?+
Access the model through Google's model garden or compatible hosting platforms, then integrate it using standard APIs or SDKs for text, image, and tool-calling workflows.
How does it differ from sibling models?+
It sits between smaller and larger variants in the Gemma line, offering stronger image and reasoning capabilities than compact versions while requiring fewer resources than the largest models in the family.
What are its limitations?+
Like other language models, it can produce incorrect or unsupported information, and its performance depends on the quality of prompts and the reliability of connected tools for function calling.
Compare with others
Org chart: how to move your company onto AI
A practical map: which company roles and processes AI agents can take over, where to start, and in what order to roll it out.