STACKIT

Access 8 STACKIT models through Mastra's model router. Authentication is handled automatically using the STACKIT_API_KEY environment variable.

Learn more in the STACKIT documentation.

STACKIT_API_KEY=your-api-key

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

const agent = new Agent({
  id: "my-agent",
  name: "My Agent",
  instructions: "You are a helpful assistant",
  model: "stackit/Qwen/Qwen3-VL-235B-A22B-Instruct-FP8"
});

// 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 STACKIT documentation for details.

:::

Models

<ProviderModelsTable models={[ { "model": "stackit/cortecs/Llama-3.3-70B-Instruct-FP8-Dynamic", "imageInput": false, "audioInput": false, "videoInput": false, "toolUsage": true, "reasoning": false, "contextWindow": 128000, "maxOutput": 8192, "inputCost": 0.49, "outputCost": 0.71 }, { "model": "stackit/google/gemma-3-27b-it", "imageInput": true, "audioInput": false, "videoInput": false, "toolUsage": false, "reasoning": false, "contextWindow": 37000, "maxOutput": 8192, "inputCost": 0.49, "outputCost": 0.71 }, { "model": "stackit/intfloat/e5-mistral-7b-instruct", "imageInput": false, "audioInput": false, "videoInput": false, "toolUsage": false, "reasoning": false, "contextWindow": 4096, "maxOutput": 4096, "inputCost": 0.02, "outputCost": 0.02 }, { "model": "stackit/neuralmagic/Meta-Llama-3.1-8B-Instruct-FP8", "imageInput": false, "audioInput": false, "videoInput": false, "toolUsage": true, "reasoning": false, "contextWindow": 128000, "maxOutput": 8192, "inputCost": 0.16, "outputCost": 0.27 }, { "model": "stackit/neuralmagic/Mistral-Nemo-Instruct-2407-FP8", "imageInput": false, "audioInput": false, "videoInput": false, "toolUsage": true, "reasoning": false, "contextWindow": 128000, "maxOutput": 8192, "inputCost": 0.49, "outputCost": 0.71 }, { "model": "stackit/openai/gpt-oss-120b", "imageInput": false, "audioInput": false, "videoInput": false, "toolUsage": true, "reasoning": true, "contextWindow": 131000, "maxOutput": 8192, "inputCost": 0.49, "outputCost": 0.71 }, { "model": "stackit/Qwen/Qwen3-VL-235B-A22B-Instruct-FP8", "imageInput": true, "audioInput": false, "videoInput": false, "toolUsage": true, "reasoning": false, "contextWindow": 218000, "maxOutput": 8192, "inputCost": 1.64, "outputCost": 1.91 }, { "model": "stackit/Qwen/Qwen3-VL-Embedding-8B", "imageInput": true, "audioInput": false, "videoInput": false, "toolUsage": false, "reasoning": false, "contextWindow": 32000, "maxOutput": 4096, "inputCost": 0.09, "outputCost": 0.09 } ]} />

Advanced configuration

Custom headers

const agent = new Agent({
  id: "custom-agent",
  name: "custom-agent",
  model: {
    url: "https://api.openai-compat.model-serving.eu01.onstackit.cloud/v1",
    id: "stackit/Qwen/Qwen3-VL-235B-A22B-Instruct-FP8",
    apiKey: process.env.STACKIT_API_KEY,
    headers: {
      "X-Custom-Header": "value"
    }
  }
});

Dynamic model selection

const agent = new Agent({
  id: "dynamic-agent",
  name: "Dynamic Agent",
  model: ({ requestContext }) => {
    const useAdvanced = requestContext.task === "complex";
    return useAdvanced
      ? "stackit/openai/gpt-oss-120b"
      : "stackit/Qwen/Qwen3-VL-235B-A22B-Instruct-FP8";
  }
});