Google
Access 18 Google models through Mastra’s model router. Authentication is handled automatically using the GOOGLE_GENERATIVE_AI_API_KEY
environment variable.
Learn more in the Google documentation .
GOOGLE_GENERATIVE_AI_API_KEY=your-api-key
import { Agent } from "@mastra/core";
const agent = new Agent({
name: "my-agent",
instructions: "You are a helpful assistant",
model: "google/gemini-1.5-flash"
});
// Generate a response
const response = await agent.generate("Hello!");
// Stream a response
const stream = await agent.stream("Tell me a story");
for await (const chunk of stream) {
console.log(chunk);
}
Mastra uses the OpenAI-compatible /chat/completions
endpoint. Some provider-specific features may not be available. Check the Google documentation for details.
Models
Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
---|---|---|---|---|---|---|---|---|
google/gemini-2.5-flash-preview-05-20 | 1.0M | $0.15 | $0.60 | |||||
google/gemini-flash-lite-latest | 1.0M | $0.10 | $0.40 | |||||
google/gemini-2.5-flash | 1.0M | $0.30 | $3 | |||||
google/gemini-flash-latest | 1.0M | $0.15 | $0.60 | |||||
google/gemini-2.5-pro-preview-05-06 | 1.0M | $1 | $10 | |||||
google/gemini-2.0-flash-lite | 1.0M | $0.07 | $0.30 | |||||
google/gemini-live-2.5-flash-preview-native-audio | 131K | $0.50 | $2 | |||||
google/gemini-2.0-flash | 1.0M | $0.10 | $0.40 | |||||
google/gemini-2.5-flash-lite | 1.0M | $0.10 | $0.40 | |||||
google/gemini-2.5-pro-preview-06-05 | 1.0M | $1 | $10 | |||||
google/gemini-2.5-flash-lite-preview-06-17 | 1.0M | $0.10 | $0.40 | |||||
google/gemini-2.5-flash-preview-09-2025 | 1.0M | $0.15 | $0.60 | |||||
google/gemini-2.5-flash-preview-04-17 | 1.0M | $0.15 | $0.60 | |||||
google/gemini-2.5-pro | 1.0M | $1 | $10 | |||||
google/gemini-1.5-flash | 1.0M | $0.07 | $0.30 | |||||
google/gemini-1.5-flash-8b | 1.0M | $0.04 | $0.15 | |||||
google/gemini-2.5-flash-lite-preview-09-2025 | 1.0M | $0.10 | $0.40 | |||||
google/gemini-1.5-pro | 1.0M | $1 | $5 |
Advanced Configuration
Custom Headers
const agent = new Agent({
name: "custom-agent",
model: {
url: "https://generativelanguage.googleapis.com/v1beta/chat/completions",
modelId: "gemini-1.5-flash",
apiKey: process.env.GOOGLE_GENERATIVE_AI_API_KEY,
headers: {
"X-Custom-Header": "value"
}
}
});
Dynamic Model Selection
const agent = new Agent({
name: "dynamic-agent",
model: ({ runtimeContext }) => {
const useAdvanced = runtimeContext.task === "complex";
return useAdvanced
? "google/gemini-1.5-flash"
: "google/gemini-1.5-flash-8b";
}
});
Direct Provider Installation
This provider can also be installed directly as a standalone package, which can be used instead of the Mastra model router string. View the package documentation for more details.
npm install @ai-sdk/google