Baseten
通过 Mastra 的模型路由访问 6 个 Baseten 模型。身份验证会自动使用 BASETEN_API_KEY 环境变量处理。
🌐 Access 6 Baseten models through Mastra's model router. Authentication is handled automatically using the BASETEN_API_KEY environment variable.
在Baseten文档中了解更多。
🌐 Learn more in the Baseten documentation.
.env
BASETEN_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: "baseten/Qwen/Qwen3-Coder-480B-A35B-Instruct"
});
// 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);
}
info
Mastra 使用与 OpenAI 兼容的 /chat/completions 端点。某些特定提供商的功能可能无法使用。详见 Baseten 文档。
🌐 Mastra uses the OpenAI-compatible /chat/completions endpoint. Some provider-specific features may not be available. Check the Baseten documentation for details.
模型Direct link to 模型
🌐 Models
| Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
|---|---|---|---|---|---|---|---|---|
baseten/deepseek-ai/DeepSeek-V3.2 | 164K | $0.30 | $0.45 | |||||
baseten/moonshotai/Kimi-K2-Instruct-0905 | 262K | $0.60 | $3 | |||||
baseten/moonshotai/Kimi-K2-Thinking | 262K | $0.60 | $3 | |||||
baseten/Qwen/Qwen3-Coder-480B-A35B-Instruct | 262K | $0.38 | $2 | |||||
baseten/zai-org/GLM-4.6 | 200K | $0.60 | $2 | |||||
baseten/zai-org/GLM-4.7 | 205K | $0.60 | $2 |
高级配置Direct link to 高级配置
🌐 Advanced Configuration
自定义头Direct link to 自定义头
🌐 Custom Headers
src/mastra/agents/my-agent.ts
const agent = new Agent({
id: "custom-agent",
name: "custom-agent",
model: {
url: "https://inference.baseten.co/v1",
id: "baseten/Qwen/Qwen3-Coder-480B-A35B-Instruct",
apiKey: process.env.BASETEN_API_KEY,
headers: {
"X-Custom-Header": "value"
}
}
});
动态模型选择Direct link to 动态模型选择
🌐 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
? "baseten/zai-org/GLM-4.7"
: "baseten/Qwen/Qwen3-Coder-480B-A35B-Instruct";
}
});