Subconscious

How to use Mastra with Subconscious

Let your AI do the setup. Paste this into Claude Code, Cursor, ChatGPT or any assistant.

Make Subconscious the model provider in my Mastra project.

Subconscious is an inference API for agents. It serves open models through OpenAI- and Anthropic-compatible endpoints, billed per token.
- OpenAI-compatible base URL: https://api.subconscious.dev/v1
- Anthropic-compatible base URL: https://api.subconscious.dev
- Model: subconscious/glm-5.3-marathon
- API key: read it from the SUBCONSCIOUS_API_KEY environment variable. Never commit the key or paste it into project files. If it is not set, ask me to create one at https://platform.subconscious.dev.

Follow these steps. Run commands and edit files yourself. If I already have agent code, change its model setup to match the example instead of adding a new file.

1. Install Mastra
Install the framework and its OpenAI-compatible client.
```bash
pnpm add @mastra/core
```

2. Create a Subconscious API key
Sign in at https://platform.subconscious.dev, create an API key, and export it so the tool can read it.
```bash
export SUBCONSCIOUS_API_KEY="your_key"
```

3. Point it at Subconscious
The providerId/modelId form sends the model ID unchanged. With a single id string, Mastra splits on the first slash, so the model would need a doubled prefix.
```ts
import { Agent } from "@mastra/core/agent";

const agent = new Agent({
  id: "subconscious-agent",
  name: "Subconscious Agent",
  instructions: "You are a helpful assistant.",
  model: {
    providerId: "subconscious",
    modelId: "subconscious/glm-5.3-marathon",
    url: "https://api.subconscious.dev/v1",
    apiKey: process.env.SUBCONSCIOUS_API_KEY,
  },
});

const response = await agent.generate("Hello!");
console.log(response.text);
```

4. Run it
Run it with any TypeScript runner.
```bash
npx tsx agent.ts
```

Full guide: https://www.subconscious.dev/agents/frameworks/mastra.md

When you are done, confirm the tool is using subconscious/glm-5.3-marathon, then summarize what you changed.

To use Mastra with Subconscious, give your Agent a model object with providerId: "subconscious", modelId: "subconscious/glm-5.3-marathon", url: "https://api.subconscious.dev/v1" and your API key. Mastra calls Subconscious through its OpenAI-compatible Chat Completions API, billed per token.

Get an API keyRead the API docs

Last verified against the Mastra docs on

Before you start

  • Node.js 20+
  • A Subconscious account and API key

Mastra docs · Source on GitHub

Set up Mastra

  1. Step 1: Install Mastra

    Install the framework and its OpenAI-compatible client.

    Terminal
    pnpm add @mastra/core

  2. Step 2: Create a Subconscious API key

    Sign in at https://platform.subconscious.dev, create an API key, and export it so the tool can read it.

    Terminal
    export SUBCONSCIOUS_API_KEY="your_key"

  3. Step 3: Point it at Subconscious

    The providerId/modelId form sends the model ID unchanged. With a single id string, Mastra splits on the first slash, so the model would need a doubled prefix.

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

const agent = new Agent({
  id: "subconscious-agent",
  name: "Subconscious Agent",
  instructions: "You are a helpful assistant.",
  model: {
    providerId: "subconscious",
    modelId: "subconscious/glm-5.3-marathon",
    url: "https://api.subconscious.dev/v1",
    apiKey: process.env.SUBCONSCIOUS_API_KEY,
  },
});

const response = await agent.generate("Hello!");
console.log(response.text);

  4. Step 4: Run it

    Run it with any TypeScript runner.

    Terminal
    npx tsx agent.ts

Why run Mastra on Subconscious

No new SDK
Subconscious speaks OpenAI Chat Completions and Anthropic Messages, so the client you already use works with a base URL change.
Pay per token
No plan and no commitment: sign up, get an API key and pay for the tokens your agents use.
Long sessions stay fast
2x faster task completion on long tasks than standard open-model inference, especially past 200k tokens of context.
Context that keeps going
The OrangeLine runtime compresses the parts of context that stopped mattering, on the GPU, while the run continues. That gives a 5M+ token context window with no stop-and-compact pause.

Connection details

For any client that takes a custom OpenAI- or Anthropic-compatible endpoint.

OpenAI-compatible base URL
https://api.subconscious.dev/v1
Anthropic-compatible base URL
https://api.subconscious.dev
API key
From subc login or the Subconscious dashboard
Model
subconscious/glm-5.3-marathon
Multimodal, high-throughput model
subconscious/deepseek-v4.1-flash-marathon

Full reference in the Subconscious API docs.

Questions

Which Subconscious model should I use with Mastra?
Start with subconscious/glm-5.3-marathon, an open frontier coding model built for long agent runs. subconscious/deepseek-v4.1-flash-marathon is a cheaper, high-throughput alternative that also takes image input. Use the full model ID, including the subconscious/ prefix.
Is Mastra on Subconscious OpenAI- or Anthropic-compatible?
This guide connects Mastra through the OpenAI-compatible Subconscious API. Subconscious serves both formats: OpenAI Chat Completions at https://api.subconscious.dev/v1 and Anthropic Messages at https://api.subconscious.dev.
How is Mastra usage on Subconscious billed?
Per token by default, with no commitment. Heavy users can switch to a monthly token plan: a fixed price for a large daily token allowance shared across your team.

More frameworks

See all