Subconscious

How to use MiniMax Code with Subconscious

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

Set up MiniMax 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 the MiniMax Code CLI
The official install script puts the mcode command on your PATH.
```bash
curl -fsSL https://filecdn.minimax.chat/public/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
--use makes it the active provider. Without --api-key-env, mcode reads the key from MCODE_PROVIDER_API_KEY.
```bash
mcode provider add --name "Subconscious" \
  --base-url "https://api.subconscious.dev/v1" \
  --api-format openai-completions \
  --model "subconscious/glm-5.3-marathon" \
  --api-key-env SUBCONSCIOUS_API_KEY --use
```

4. Start mcode
Run mcode, then /status to confirm the Subconscious provider is active.
```bash
mcode
```

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

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

To use MiniMax Code with Subconscious, install the mcode CLI, then run mcode provider add with base URL https://api.subconscious.dev/v1, API format openai-completions, model subconscious/glm-5.3-marathon, and --api-key-env SUBCONSCIOUS_API_KEY. Start mcode and it runs on Subconscious, billed per token.

Get an API keyToken plans for coding agents

Last verified against the MiniMax Code docs on

Before you start

  • macOS, Linux or Windows with a terminal
  • A Subconscious account and API key

MiniMax Code docs

Set up MiniMax Code

  1. Step 1: Install the MiniMax Code CLI

    The official install script puts the mcode command on your PATH.

    Terminal
    curl -fsSL https://filecdn.minimax.chat/public/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

    --use makes it the active provider. Without --api-key-env, mcode reads the key from MCODE_PROVIDER_API_KEY.

    Terminal
    mcode provider add --name "Subconscious" \
  --base-url "https://api.subconscious.dev/v1" \
  --api-format openai-completions \
  --model "subconscious/glm-5.3-marathon" \
  --api-key-env SUBCONSCIOUS_API_KEY --use

  4. Step 4: Start mcode

    Run mcode, then /status to confirm the Subconscious provider is active.

    Terminal
    mcode

Why run MiniMax 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

How do I use Subconscious in the MiniMax Code desktop app?
Open Settings, then Usage & model, and choose Add model under Custom model. Pick Others, enter a provider name, the base URL https://api.subconscious.dev/v1, your API key and the model ID, then save, run the connectivity test and select the model.
Which Subconscious model should I use with MiniMax 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 MiniMax Code on Subconscious OpenAI- or Anthropic-compatible?
This guide connects MiniMax 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 MiniMax 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