Subconscious

How to use Factory Droid with Subconscious

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

Set up Factory Droid to use Subconscious as its model provider.

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. For any step in a settings screen, tell me exactly what to click and what to enter.

1. Install Droid
Homebrew (brew install --cask droid) and npm (npm install -g droid) also work.
```bash
curl -fsSL https://app.factory.ai/cli | sh
```

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. Add Subconscious as a custom model
generic-chat-completion-api is the provider type for OpenAI Chat Completions endpoints. Droid expands the key variable from your environment.
```json
{
  "customModels": [
    {
      "model": "subconscious/glm-5.3-marathon",
      "displayName": "Subconscious GLM-5.3 Marathon",
      "baseUrl": "https://api.subconscious.dev/v1",
      "apiKey": "${SUBCONSCIOUS_API_KEY}",
      "provider": "generic-chat-completion-api",
      "maxOutputTokens": 16384
    }
  ]
}
```

4. Select the model
Start droid, run /model and choose Subconscious GLM-5.3 Marathon from the Custom models section.
```bash
droid
```

Full guide: https://www.subconscious.dev/agents/terminal-and-ide/factory.md

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

To use Factory Droid with Subconscious, add a custom model to ~/.factory/settings.json with provider generic-chat-completion-api, base URL https://api.subconscious.dev/v1 and model subconscious/glm-5.3-marathon. Run droid, open /model and pick it from Custom models. Droid then runs on Subconscious, billed per token.

Get an API keyToken plans for coding agents

Last verified against the Factory Droid docs on

Before you start

  • A Subconscious account and API key

Factory Droid docs

Set up Factory Droid

  1. Step 1: Install Droid

    Homebrew (brew install --cask droid) and npm (npm install -g droid) also work.

    Terminal
    curl -fsSL https://app.factory.ai/cli | sh

  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: Add Subconscious as a custom model

    generic-chat-completion-api is the provider type for OpenAI Chat Completions endpoints. Droid expands the key variable from your environment.

    ~/.factory/settings.json
    {
  "customModels": [
    {
      "model": "subconscious/glm-5.3-marathon",
      "displayName": "Subconscious GLM-5.3 Marathon",
      "baseUrl": "https://api.subconscious.dev/v1",
      "apiKey": "${SUBCONSCIOUS_API_KEY}",
      "provider": "generic-chat-completion-api",
      "maxOutputTokens": 16384
    }
  ]
}

  4. Step 4: Select the model

    Start droid, run /model and choose Subconscious GLM-5.3 Marathon from the Custom models section.

    Terminal
    droid

Why run Factory Droid on Subconscious

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.
Lower cost on long tasks
50% to 80% lower cost on long tasks, because the runtime processes far fewer tokens. Cached input bills at a steep discount, and agentic coding sees cache hit rates above 95%.
Your data stays yours
Prompts, inputs and outputs are not recorded, and nothing you send is used to train a model.

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

Why is my custom model missing in Factory Droid?
Organization admins can turn off custom models in Factory's enterprise controls. Check with your admin if the Custom models section does not appear.
Which Subconscious model should I use with Factory Droid?
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 Factory Droid on Subconscious OpenAI- or Anthropic-compatible?
This guide connects Factory Droid 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 Factory Droid 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 terminal and IDE agents

See all