Subconscious

How to use Codex with Subconscious

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

Set up Codex 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: `subc login` saves it for you. Do not ask me for it.

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 the Subconscious CLI
subc is the open-source Subconscious CLI. It signs you in, stores your API key, and wires coding agents to the Subconscious API.
```bash
npm install -g subconscious-cli
```

2. Log in
This opens your browser to sign in or create an account, then saves your API key and a ready-to-use default profile on your machine.
```bash
subc login
```

3. Launch Codex
subc launches Codex with a temporary Subconscious provider and model catalog, and merges its context compaction hooks into your existing Codex hooks. If Codex is not installed, subc offers to install it first.
```bash
subc codex
```

4. Pass Codex arguments through
Anything after the subcommand goes straight to Codex, so your usual flags keep working.
```bash
subc codex exec "write a test"
```

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

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

To use Codex with Subconscious, install the Subconscious CLI with npm install -g subconscious-cli, run subc login, then run subc codex. subc points Codex at the OpenAI-compatible Subconscious API, so it runs on open models like GLM-5.3 Marathon, billed per token.

Get an API keyToken plans for coding agents

Last verified against the Codex docs on

Before you start

  • Node.js and npm, to install the subc CLI
  • A Subconscious account

Codex docs · Source on GitHub

Set up Codex

  1. Step 1: Install the Subconscious CLI

    subc is the open-source Subconscious CLI. It signs you in, stores your API key, and wires coding agents to the Subconscious API.

    Terminal
    npm install -g subconscious-cli

  2. Step 2: Log in

    This opens your browser to sign in or create an account, then saves your API key and a ready-to-use default profile on your machine.

    Terminal
    subc login

  3. Step 3: Launch Codex

    subc launches Codex with a temporary Subconscious provider and model catalog, and merges its context compaction hooks into your existing Codex hooks. If Codex is not installed, subc offers to install it first.

    Terminal
    subc codex

  4. Step 4: Pass Codex arguments through

    Anything after the subcommand goes straight to Codex, so your usual flags keep working.

    Terminal
    subc codex exec "write a test"

Why run Codex 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 model does Codex use on Subconscious?
The default model on your subc profile, subconscious/glm-5.3-marathon unless you change it. subconscious/deepseek-v4.1-flash-marathon is a cheaper, high-throughput alternative that also takes image input. Run subc with no arguments and choose Set default model to switch.
Does subc change my Codex configuration?
subc launches Codex with a temporary Subconscious provider and model catalog, and merges its context compaction hooks into your existing Codex hooks. Any persistent change is a merge: subc never replaces your existing Codex config files.
Is Codex on Subconscious OpenAI- or Anthropic-compatible?
This guide connects Codex 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 Codex 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