TensorX

Access 25 TensorX models through Mastra's model router. Authentication is handled automatically using the TENSORX_API_KEY environment variable.

Learn more in the TensorX documentation.

.env

TENSORX_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: "tensorx/deepseek/deepseek-chat-v3.1"
});

// 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);
}

info

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

Models

25 available models

Model	Context	Tools	Reasoning	Image	Audio	Video	Input $/1M	Output $/1M
tensorx/deepseek/deepseek-chat-v3.1	164K						$0.20	$0.80
tensorx/deepseek/deepseek-r1-0528	164K						$0.66	$3
tensorx/deepseek/deepseek-v3.2	164K						$0.30	$0.50
tensorx/deepseek/deepseek-v4-flash	1.0M						$0.15	$0.30
tensorx/deepseek/deepseek-v4-flash-0731	1.0M						$0.25	$0.30
tensorx/deepseek/deepseek-v4-pro	1.0M						$2	$4
tensorx/minimax/minimax-m2.5	197K						$0.30	$1
tensorx/minimax/minimax-m3	1.0M						$0.40	$2
tensorx/moonshotai/kimi-k2.5	262K						$0.50	$3
tensorx/moonshotai/kimi-k2.6	262K						$1	$4
tensorx/moonshotai/kimi-k2.7-code	262K						$1	$5
tensorx/moonshotai/kimi-k3	1.0M						$3	$15
tensorx/nvidia/nemotron-3-super-120b-a12b	262K						$0.30	$0.90
tensorx/openai/gpt-oss-120b	131K						$0.04	$0.20
tensorx/qwen/qwen3-235b-a22b-2507	131K						$0.07	$0.46
tensorx/qwen/qwen3-coder-30b-a3b-instruct	262K						$0.06	$0.25
tensorx/qwen/qwen3-vl-235b-a22b-instruct	131K						$0.21	$2
tensorx/qwen/qwen3.5-122b-a10b	262K						$0.50	$4
tensorx/qwen/qwen3.5-9b	262K						$0.15	$0.20
tensorx/z-ai/glm-4.7	200K						$0.60	$2
tensorx/z-ai/glm-5	203K						$1	$3
tensorx/z-ai/glm-5-turbo	203K						$1	$4
tensorx/z-ai/glm-5.1	203K						$1	$4
tensorx/z-ai/glm-5.2	1.0M						$2	$5
tensorx/z-ai/glm-5v-turbo	203K						$1	$4

Advanced configuration

Custom headers

src/mastra/agents/my-agent.ts

const agent = new Agent({
  id: "custom-agent",
  name: "custom-agent",
  model: {
    url: "https://api.tensorx.ai/v1",
    id: "tensorx/deepseek/deepseek-chat-v3.1",
    apiKey: process.env.TENSORX_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
      ? "tensorx/z-ai/glm-5v-turbo"
      : "tensorx/deepseek/deepseek-chat-v3.1";
  }
});