Skip to main content

submodel logosubmodel

Access 9 submodel models through Mastra's model router. Authentication is handled automatically using the SUBMODEL_INSTAGEN_ACCESS_KEY environment variable.

Learn more in the submodel documentation.

SUBMODEL_INSTAGEN_ACCESS_KEY=your-api-key
import { Agent } from "@mastra/core";

const agent = new Agent({
name: "my-agent",
instructions: "You are a helpful assistant",
model: "submodel/Qwen/Qwen3-235B-A22B-Instruct-2507"
});

// 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 submodel documentation for details.

Models

ModelContextToolsReasoningImageAudioVideoInput $/1MOutput $/1M
submodel/deepseek-ai/DeepSeek-R1-052875K$0.50$2
submodel/deepseek-ai/DeepSeek-V3-032475K$0.20$0.80
submodel/deepseek-ai/DeepSeek-V3.175K$0.20$0.80
submodel/openai/gpt-oss-120b131K$0.10$0.50
submodel/Qwen/Qwen3-235B-A22B-Instruct-2507262K$0.20$0.30
submodel/Qwen/Qwen3-235B-A22B-Thinking-2507262K$0.20$0.60
submodel/Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8262K$0.20$0.80
submodel/zai-org/GLM-4.5-Air131K$0.10$0.50
submodel/zai-org/GLM-4.5-FP8131K$0.20$0.80
9 available models

Advanced Configuration

Custom Headers

const agent = new Agent({
name: "custom-agent",
model: {
url: "https://llm.submodel.ai/v1",
id: "submodel/Qwen/Qwen3-235B-A22B-Instruct-2507",
apiKey: process.env.SUBMODEL_INSTAGEN_ACCESS_KEY,
headers: {
"X-Custom-Header": "value"
}
}
});

Dynamic Model Selection

const agent = new Agent({
name: "dynamic-agent",
model: ({ runtimeContext }) => {
const useAdvanced = runtimeContext.task === "complex";
return useAdvanced
? "submodel/zai-org/GLM-4.5-FP8"
: "submodel/Qwen/Qwen3-235B-A22B-Instruct-2507";
}
});

On this page