Subconscious

How to use OpenClaw with Subconscious

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

Set up OpenClaw 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 OpenClaw
The installer sets up the CLI and the local Gateway daemon.
```bash
curl -fsSL https://openclaw.ai/install.sh | bash
```

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 provider
The config is JSON5 and hot-reloaded. Model references split on the first slash, so the primary model needs the provider name in front of the full Subconscious model ID.
```json5
{
  agents: {
    defaults: { model: { primary: "subconscious/subconscious/glm-5.3-marathon" } },
  },
  models: {
    mode: "merge",
    providers: {
      subconscious: {
        baseUrl: "https://api.subconscious.dev/v1",
        apiKey: "${SUBCONSCIOUS_API_KEY}",
        api: "openai-completions",
        models: [{ id: "subconscious/glm-5.3-marathon", name: "GLM-5.3 Marathon" }],
      },
    },
  },
}
```

4. Check the setup
openclaw doctor validates the config. You can also edit it from the Control UI at http://127.0.0.1:18789.
```bash
openclaw doctor
```

Full guide: https://www.subconscious.dev/agents/agent-harnesses/openclaw.md

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

To use OpenClaw with Subconscious, add a subconscious provider under models.providers in ~/.openclaw/openclaw.json with base URL https://api.subconscious.dev/v1 and api: "openai-completions", then set the primary model to subconscious/subconscious/glm-5.3-marathon. OpenClaw reloads the config and runs on Subconscious.

Get an API keyRead the API docs

Last verified against the OpenClaw docs on

Before you start

  • macOS, Linux or Windows (WSL)
  • A Subconscious account and API key

OpenClaw docs · Source on GitHub

Set up OpenClaw

  1. Step 1: Install OpenClaw

    The installer sets up the CLI and the local Gateway daemon.

    Terminal
    curl -fsSL https://openclaw.ai/install.sh | bash

  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 provider

    The config is JSON5 and hot-reloaded. Model references split on the first slash, so the primary model needs the provider name in front of the full Subconscious model ID.

    ~/.openclaw/openclaw.json
    {
  agents: {
    defaults: { model: { primary: "subconscious/subconscious/glm-5.3-marathon" } },
  },
  models: {
    mode: "merge",
    providers: {
      subconscious: {
        baseUrl: "https://api.subconscious.dev/v1",
        apiKey: "${SUBCONSCIOUS_API_KEY}",
        api: "openai-completions",
        models: [{ id: "subconscious/glm-5.3-marathon", name: "GLM-5.3 Marathon" }],
      },
    },
  },
}

  4. Step 4: Check the setup

    openclaw doctor validates the config. You can also edit it from the Control UI at http://127.0.0.1:18789.

    Terminal
    openclaw doctor

Why run OpenClaw on Subconscious

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.
Long sessions stay fast
2x faster task completion on long tasks than standard open-model inference, especially past 200k tokens of context.
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 does the OpenClaw model reference repeat "subconscious"?
OpenClaw reads everything before the first slash as the provider name. The first subconscious is your provider entry; the rest, subconscious/glm-5.3-marathon, is the model ID sent to the API.
Which Subconscious model should I use with OpenClaw?
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 OpenClaw on Subconscious OpenAI- or Anthropic-compatible?
This guide connects OpenClaw 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 OpenClaw 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 agent harnesses

See all