Meganova

通过 Mastra 的模型路由器访问 19 个 Meganova 模型。系统会自动使用 MEGANOVA_API_KEY 环境变量完成身份验证。

更多信息请参阅Meganova 文档。

.env

MEGANOVA_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: 'meganova/MiniMaxAI/MiniMax-M2.1',
})

// 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)
}

信息

Mastra 使用兼容 OpenAI 的 /chat/completions endpoint。部分 Provider 特有功能可能不可用，详情请参阅Meganova 文档。

模型

19 available models

Model	Context	Tools	Reasoning	Image	Audio	Video	Input $/1M	Output $/1M
meganova/deepseek-ai/DeepSeek-R1-0528	164K						$0.50	$2
meganova/deepseek-ai/DeepSeek-V3-0324	164K						$0.25	$0.88
meganova/deepseek-ai/DeepSeek-V3.1	164K						$0.27	$1
meganova/deepseek-ai/DeepSeek-V3.2	164K						$0.26	$0.38
meganova/deepseek-ai/DeepSeek-V3.2-Exp	164K						$0.27	$0.40
meganova/meta-llama/Llama-3.3-70B-Instruct	131K						$0.10	$0.30
meganova/MiniMaxAI/MiniMax-M2.1	197K						$0.28	$1
meganova/MiniMaxAI/MiniMax-M2.5	205K						$0.30	$1
meganova/mistralai/Mistral-Nemo-Instruct-2407	131K						$0.02	$0.04
meganova/mistralai/Mistral-Small-3.2-24B-Instruct-2506	33K						—	—
meganova/moonshotai/Kimi-K2-Thinking	262K						$0.60	$3
meganova/moonshotai/Kimi-K2.5	262K						$0.45	$3
meganova/Qwen/Qwen2.5-VL-32B-Instruct	16K						$0.20	$0.60
meganova/Qwen/Qwen3-235B-A22B-Instruct-2507	262K						$0.09	$0.60
meganova/Qwen/Qwen3.5-Plus	1.0M						$0.40	$2
meganova/XiaomiMiMo/MiMo-V2-Flash	262K						$0.10	$0.30
meganova/zai-org/GLM-4.6	203K						$0.45	$2
meganova/zai-org/GLM-4.7	203K						$0.20	$0.80
meganova/zai-org/GLM-5	203K						$0.80	$3

高级配置

自定义请求头

src/mastra/agents/my-agent.ts

const agent = new Agent({
  id: 'custom-agent',
  name: 'custom-agent',
  model: {
    url: 'https://api.meganova.ai/v1',
    id: 'meganova/MiniMaxAI/MiniMax-M2.1',
    apiKey: process.env.MEGANOVA_API_KEY,
    headers: {
      'X-Custom-Header': 'value',
    },
  },
})

动态选择模型

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 ? 'meganova/zai-org/GLM-5' : 'meganova/MiniMaxAI/MiniMax-M2.1'
  },
})