Subconscious

How to use Qwen Code with Subconscious

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

Set up Qwen Code 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 Qwen Code
Install the qwen CLI globally with npm. Homebrew users can run brew install qwen-code instead.
```bash
npm install -g @qwen-code/qwen-code@latest
```

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 model provider
`envKey` is the name of the environment variable that holds your key, not the key itself. Use `.qwen/settings.json` in a project instead to scope it to that project.
```json
{
  "modelProviders": {
    "openai": [
      {
        "id": "subconscious/glm-5.3-marathon",
        "name": "Subconscious GLM-5.3 Marathon",
        "baseUrl": "https://api.subconscious.dev/v1",
        "envKey": "SUBCONSCIOUS_API_KEY"
      }
    ]
  },
  "security": { "auth": { "selectedType": "openai" } },
  "model": { "name": "subconscious/glm-5.3-marathon" }
}
```

4. Start Qwen Code
Run qwen in your project. Use /model inside a session to switch between configured models.
```bash
qwen
```

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

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

To use Qwen Code with Subconscious, add Subconscious as an OpenAI-compatible entry under modelProviders in ~/.qwen/settings.json, with base URL https://api.subconscious.dev/v1, model subconscious/glm-5.3-marathon, and envKey set to SUBCONSCIOUS_API_KEY. Then run qwen. Qwen Code sends every request to Subconscious, billed per token.

Get an API keyToken plans for coding agents

Last verified against the Qwen Code docs on

Before you start

  • Node.js and npm
  • A Subconscious account and API key

Qwen Code docs · Source on GitHub

Set up Qwen Code

  1. Step 1: Install Qwen Code

    Install the qwen CLI globally with npm. Homebrew users can run brew install qwen-code instead.

    Terminal
    npm install -g @qwen-code/qwen-code@latest

  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 model provider

    envKey is the name of the environment variable that holds your key, not the key itself. Use .qwen/settings.json in a project instead to scope it to that project.

    ~/.qwen/settings.json
    {
  "modelProviders": {
    "openai": [
      {
        "id": "subconscious/glm-5.3-marathon",
        "name": "Subconscious GLM-5.3 Marathon",
        "baseUrl": "https://api.subconscious.dev/v1",
        "envKey": "SUBCONSCIOUS_API_KEY"
      }
    ]
  },
  "security": { "auth": { "selectedType": "openai" } },
  "model": { "name": "subconscious/glm-5.3-marathon" }
}

  4. Step 4: Start Qwen Code

    Run qwen in your project. Use /model inside a session to switch between configured models.

    Terminal
    qwen

Why run Qwen Code 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

Can I still use security.auth.apiKey and baseUrl in Qwen Code?
Those settings are deprecated. Configure custom endpoints under modelProviders, which is also where Qwen Code documents OpenAI-, Anthropic- and Gemini-format providers.
Which Subconscious model should I use with Qwen Code?
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 Qwen Code on Subconscious OpenAI- or Anthropic-compatible?
This guide connects Qwen Code 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 Qwen Code 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