Introducing ASpec

How to use OpenHands with Subconscious

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

Set up OpenHands 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 Agent Canvas
Agent Canvas is the current OpenHands app; the older OpenHands CLI is no longer maintained. It runs on macOS, Linux, Windows and WSL2.
```bash
npm install -g @openhands/agent-canvas
```

2. Create a Subconscious API key
Sign in at https://platform.subconscious.dev and create an API key. You will paste it into the settings screen below.

3. Open the LLM settings
Start Agent Canvas and open http://localhost:8000. Go to Settings, then LLM, and choose the Advanced tab.
```bash
agent-canvas
```

4. Point OpenHands at Subconscious
Fill in these fields, or save the base URL and key as a Provider Connection and select it. Save the profile, then start a new conversation to check it responds.
   - Model: openai/subconscious/glm-5.3-marathon
   - Base URL: https://api.subconscious.dev/v1
   - API key: Your Subconscious API key

Full guide: https://www.subconscious.dev/integrations/terminal-and-ide/openhands.md

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

To use OpenHands with Subconscious, run Agent Canvas, open Settings, then LLM, then the Advanced tab, and set the model to openai/subconscious/glm-5.3-marathon, the base URL to https://api.subconscious.dev/v1 and the API key to your Subconscious key. The openai/ prefix tells OpenHands to treat Subconscious as an OpenAI compatible endpoint.

Last verified against the OpenHands docs on

Before you start

  • Node.js 24 or newer, and uv
  • A Subconscious account and API key

OpenHands docs · Source on GitHub

Set up OpenHands

  1. Step 1: Install Agent Canvas

    Agent Canvas is the current OpenHands app; the older OpenHands CLI is no longer maintained. It runs on macOS, Linux, Windows and WSL2.

    Terminal
    npm install -g @openhands/agent-canvas
  2. Step 2: Create a Subconscious API key

    Sign in at https://platform.subconscious.dev and create an API key. You will paste it into the settings screen below.

  3. Step 3: Open the LLM settings

    Start Agent Canvas and open http://localhost:8000. Go to Settings, then LLM, and choose the Advanced tab.

    Terminal
    agent-canvas
  4. Step 4: Point OpenHands at Subconscious

    Fill in these fields, or save the base URL and key as a Provider Connection and select it. Save the profile, then start a new conversation to check it responds.

    Model
    openai/subconscious/glm-5.3-marathon
    Base URL
    https://api.subconscious.dev/v1
    API key
    Your Subconscious API key

Why run OpenHands 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

Which Subconscious model should I use with OpenHands?
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 OpenHands on Subconscious OpenAI or Anthropic compatible?
This guide connects OpenHands 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 OpenHands usage on Subconscious billed?
Per token by default, with no commitment. Heavy users can switch to a Team Token Plan: a large monthly budget with 5x the usage, shared across your team.

More terminal and IDE agents

See all