Gemini is a family of generative AI models that lets developers generate content and solve problems. These models are designed and trained to handle both text and images as input. This guide provides information about each model variant to help you decide which is the best fit for your use case.
Here is a quick summary of the available models and their capabilities:
Models | Input | Output |
---|---|---|
Gemini | ||
|
Text and images | Text |
|
Text | Text |
|
Text and images | Text |
Embeddings | ||
|
Text | Text embeddings |
Retrieval | ||
|
Text | Text |
Safety and intended use
Generative artificial intelligence models are powerful tools, but they are not without their limitations. Their versatility and applicability can sometimes lead to unexpected outputs, such as outputs that are inaccurate, biased, or offensive. Post-processing, and rigorous manual evaluation are essential to limit the risk of harm from such outputs. See the safety guidance for additional safe use suggestions.
The models provide by the Gemini API can be used for a wide variety of generative AI and natural language processing (NLP) applications. Use of these functions is only available through the Gemini API or the Google AI Studio web app. Your use of Gemini API is also subject to the Generative AI Prohibited Use Policy and the Gemini API terms of service.
Model sizes
The following table shows the available sizes and what they mean relative to each other.
Model size | Description | Services |
---|---|---|
Gemini 1.0 Pro | A model size that balances capability and efficiency. |
|
Model versions
Gemini models are available in either preview or stable versions. In your code, you can use one of the following model name formats to specify which model and version you want to use.
Latest: Points to the cutting-edge version of the model for a specified generation and variation. The underlying model is updated regularly and might be a preview version. Only exploratory testing apps and prototypes should use this alias.
To specify the latest version, use the following pattern:
<model>-<generation>-<variation>-latest
. For example,gemini-1.0-pro-latest
.Latest stable: Points to the most recent stable version released for the specified model generation and variation.
To specify the latest stable version, use the following pattern:
<model>-<generation>-<variation>
. For example,gemini-1.0-pro
.Stable: Points to a specific stable model. Stable models don't change. Most production apps should use a specific stable model.
To specify a stable version, use the following pattern:
<model>-<generation>-<variation>-<version>
. For example,gemini-1.0-pro-001
.
For models that have a stable version, see the "Model names" row for the model in Model variations.
Model variations
The Gemini API offers different models optimized for specific use cases. The following table describes attributes of each.
Variation | Attribute | Description | Gemini 1.5 Pro (Preview only) | Model last updated | April 2024 |
---|---|---|
Model code | models/gemini-1.5-pro-latest |
|
Model capabilities |
|
|
Supported generation methods | generateContent |
|
Input token limit | 1048576 | |
Output token limit | 8192 | |
Model safety | Automatically applied safety settings which are adjustable by developers. See the safety settings topic for details. | |
Rate limit | 2 queries per minute, 1000 queries per day [1] | |
Gemini Pro | Model last updated | February 2024 |
Model code | models/gemini-pro |
|
Model capabilities |
|
|
Supported generation methods | generateContent |
|
Input token limit | 30720 | |
Output token limit | 2048 | |
Model safety | Automatically applied safety settings which are adjustable by developers. See the safety settings topic for details. | |
Rate limit | 60 requests per minute [1] | |
Model names |
|
|
Gemini 1.0 Pro Vision | Model last updated | December 2023 |
Model code | models/gemini-pro-vision |
|
Model capabilities |
|
|
Supported generation methods | generateContent |
|
Input token limit | 12288 | |
Output token limit | 4096 | |
Model safety | Automatically applied safety settings which are adjustable by developers. See the safety settings topic for details. | |
Rate limit | 60 requests per minute [1] | |
Embedding | Model last updated | December 2023 |
Model code | models/embedding-001 |
|
Model capabilities |
|
|
Supported generation methods | embedContent |
|
Model safety | No adjustable safety settings. | |
Rate limit | 1500 requests per minute [1] | |
Text Embedding | Model last updated | April 2024 |
Model code | models/text-embedding-004 (text-embedding-preview-0409
in Vertex AI)
|
|
Model capabilities |
|
|
Supported generation methods | embedContent |
|
Model safety | No adjustable safety settings. | |
Rate limit | 1500 requests per minute [1] | |
AQA | Model last updated | December 2023 |
Model code | models/aqa |
|
Model capabilities |
|
|
Supported generation methods | generateAnswer |
|
Supported languages | English | |
Input token limit | 7168 | |
Output token limit | 1024 | |
Model safety | Automatically applied safety settings which are adjustable by developers. See the safety settings topic for details. | |
Rate limit | 60 requests per minute [1] |
See the examples to explore the capabilities of these model variations.
Model metadata
Use the ModelService
API to get additional metadata about
the latest models such as input and output token limits. The following table
displays the metadata for the Gemini Pro model variant.
Attribute | Value |
---|---|
Display name | Gemini 1.0 Pro |
Model code | models/gemini-1.0-pro |
Description | Model targeted for text generation |
Supported generation methods | generateContent |
Temperature | 0.9 |
top_p | 1 |
top_k | 1 |
Model attributes
The following table describes the attributes of the Gemini models which are common to all model variations.
Attribute | Description |
---|---|
Training data | Gemini's knowledge cutoff is early 2023. Knowledge about events after that time is limited. |
Supported languages | See available languages |
Configurable model parameters |
|
[1] Due to capacity limitations, specified maximum rate limits are not guaranteed.
See the model parameters section of the Intro to LLMs guide for information about each of these parameters.
Next steps
- For a no-code way to get started, see the Google AI Studio quickstart.
- To get started using the API, see the Python quickstart.