Long-running agents deserve better inference.
Subconscious

How to use Coder with Subconscious

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

Set up Coder 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. 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.

2. Add Subconscious as a provider
In the Coder dashboard, open Admin settings, then AI, then Providers, and choose Add provider. Keep the /v1 in the base URL: Coder appends /chat/completions. Save; no restart is needed.
   - Type: OpenAI Compatible
   - Name: subconscious
   - Base URL: https://api.subconscious.dev/v1
   - API key: Your Subconscious API key

3. Add the model
Open Admin settings, then AI, then Models, and choose Add model. Give it a display name and context limit, and save. Optionally make it the Coder Agents default model.
   - Provider: subconscious
   - Model Identifier: subconscious/glm-5.3-marathon

Full guide: https://www.subconscious.dev/integrations/agent-harnesses/coder.md

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

To use Coder with Subconscious, go to Admin settings, then AI, then Providers, and add an OpenAI Compatible provider named subconscious with base URL https://api.subconscious.dev/v1 and your API key. Then add the model subconscious/glm-5.3-marathon under Models so Coder Agents and AI Gateway clients can use it.

Get an API keyRead the API docs

Last verified against the Coder docs on

Before you start

  • A Coder deployment and admin access
  • A Subconscious account and API key

Coder docs · Source on GitHub

Set up Coder

  1. Step 1: 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.

  2. Step 2: Add Subconscious as a provider

    In the Coder dashboard, open Admin settings, then AI, then Providers, and choose Add provider. Keep the /v1 in the base URL: Coder appends /chat/completions. Save; no restart is needed.

    Type
    OpenAI Compatible
    Name
    subconscious
    Base URL
    https://api.subconscious.dev/v1
    API key
    Your Subconscious API key

  3. Step 3: Add the model

    Open Admin settings, then AI, then Models, and choose Add model. Give it a display name and context limit, and save. Optionally make it the Coder Agents default model.

    Provider
    subconscious
    Model Identifier
    subconscious/glm-5.3-marathon

Why run Coder 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

Can I configure Coder providers with environment variables?
Not since Coder v2.34. Provider flags and env vars such as CODER_AI_GATEWAY_OPENAI_BASE_URL are ignored, and removed flags stop startup. Configure providers in the dashboard or the API.
Can Claude Code in a Coder workspace use Subconscious?
Yes. Add a second provider of type Anthropic with endpoint https://api.subconscious.dev, then point workspaces at it with ANTHROPIC_BASE_URL set to your Coder URL plus /api/v2/ai-gateway/<provider-name> and ANTHROPIC_AUTH_TOKEN set to a Coder API token. AI Gateway needs a Coder Premium license.
Which Subconscious model should I use with Coder?
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 Coder on Subconscious OpenAI- or Anthropic-compatible?
This guide connects Coder 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 Coder 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 agent harnesses

See all