Vultr

Access 15 Vultr models through Mastra's model router. Authentication is handled automatically using the VULTR_API_KEY environment variable.

Learn more in the Vultr documentation.

.env

VULTR_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: "vultr/deepseek-v4-flash-0731"
});

// 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 Vultr documentation for details.

Models

15 available models

Model	Context	Tools	Reasoning	Image	Audio	Video	Input $/1M	Output $/1M
vultr/deepseek-v4-flash-0731	1.0M						$0.10	$0.25
vultr/deepseek-v4.1-flash	1.0M						$0.15	$0.60
vultr/glm-5.2	1.0M						$0.75	$3
vultr/glm-5.3	1.0M						$0.75	$3
vultr/glm-5.3-flash	1.0M						$0.10	$0.35
vultr/glm-5.x-menthol	203K						$0.40	$2
vultr/laguna-s-2.1	1.0M						$0.09	$0.18
vultr/mimo-v2.6-flash-rl	1.0M						$0.10	$0.25
vultr/mimo-v2.6-pro-rl	1.0M						$0.40	$0.80
vultr/minimax-m3	524K						$0.20	$0.90
vultr/muse-glimmer-30b	131K						$0.25	$1
vultr/nemotron-3-nano-omni-30b-a3b-reasoning	262K						$0.10	$0.25
vultr/nemotron-3.5-content-safety	131K						$0.05	$0.15
vultr/qwen3.8-27b	262K						$0.15	$1
vultr/qwen3.8-flash-next	262K						$0.10	$0.20

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.vultrinference.com/v1",
    id: "vultr/deepseek-v4-flash-0731",
    apiKey: process.env.VULTR_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
      ? "vultr/qwen3.8-flash-next"
      : "vultr/deepseek-v4-flash-0731";
  }
});