Lilac

Access 4 Lilac models through Mastra's model router. Authentication is handled automatically using the LILAC_API_KEY environment variable.

Learn more in the Lilac documentation.

.env

LILAC_API_KEY=your-api-key

src/mastra/agents/my-agent.ts

import { Agent } from "@mastra/core/agent";

const agent = new Agent({
  id: "my-agent",
  name: "My Agent",
  instructions: "You are a helpful assistant",
  model: "lilac/google/gemma-4-31b-it"
});

// 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);
}

备注

Mastra uses the OpenAI-compatible /chat/completions endpoint. Some provider-specific features may not be available. Check the Lilac documentation for details.

Models

4 available models

Model	Context	Tools	Reasoning	Image	Audio	Video	Input $/1M	Output $/1M
lilac/google/gemma-4-31b-it	262K						$0.11	$0.35
lilac/minimaxai/minimax-m3	1.0M						$0.28	$1
lilac/moonshotai/kimi-k2.6	262K						$0.70	$4
lilac/zai-org/glm-5.2	524K						$0.90	$3

Model availability, capabilities, context windows, and pricing are sourced from models.dev and may change.

Advanced configuration

Custom headers

src/mastra/agents/my-agent.ts

const agent = new Agent({
  id: "custom-agent",
  name: "custom-agent",
  model: {
    url: "https://api.getlilac.com/v1",
    id: "lilac/google/gemma-4-31b-it",
    apiKey: process.env.LILAC_API_KEY,
    headers: {
      "X-Custom-Header": "value"
    }
  }
});

Dynamic model selection

src/mastra/agents/my-agent.ts

const agent = new Agent({
  id: "dynamic-agent",
  name: "Dynamic Agent",
  model: ({ requestContext }) => {
    const useAdvanced = requestContext.task === "complex";
    return useAdvanced
      ? "lilac/zai-org/glm-5.2"
      : "lilac/google/gemma-4-31b-it";
  }
});