Subconscious

How to use Rig with Subconscious

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

Make Subconscious the model provider in my Rig project.

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. If I already have agent code, change its model setup to match the example instead of adding a new file.

1. Install Rig
Install the framework and its OpenAI-compatible client.
```bash
cargo add rig@0.42 anyhow
cargo add tokio --features macros,rt-multi-thread
```

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. Point it at Subconscious
Written for Rig 0.42. openai::Client targets OpenAI's Responses API, so use CompletionsClient for Chat Completions. The base URL keeps /v1.
```rust
use rig::prelude::*;
use rig::providers::openai;

#[tokio::main]
async fn main() -> Result<(), anyhow::Error> {
    let client = openai::CompletionsClient::builder()
        .api_key(std::env::var("SUBCONSCIOUS_API_KEY")?)
        .base_url("https://api.subconscious.dev/v1")
        .build()?;

    let agent = client
        .agent("subconscious/glm-5.3-marathon")
        .preamble("You are a helpful assistant.")
        .build();

    let response = agent.prompt("Hello!").await?;
    println!("{response}");
    Ok(())
}
```

4. Run it
Build and run.
```bash
cargo run
```

Full guide: https://www.subconscious.dev/agents/frameworks/rig.md

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

To use Rig with Subconscious, build an openai::CompletionsClient with .base_url("https://api.subconscious.dev/v1") and your API key, then create an agent with client.agent("subconscious/glm-5.3-marathon"). Rig then calls Subconscious through Chat Completions, billed per token.

Get an API keyRead the API docs

Last verified against the Rig docs on

Before you start

  • Rust and Cargo
  • A Subconscious account and API key

Rig docs · Source on GitHub

Set up Rig

  1. Step 1: Install Rig

    Install the framework and its OpenAI-compatible client.

    Terminal
    cargo add rig@0.42 anyhow
cargo add tokio --features macros,rt-multi-thread

  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: Point it at Subconscious

    Written for Rig 0.42. openai::Client targets OpenAI's Responses API, so use CompletionsClient for Chat Completions. The base URL keeps /v1.

    src/main.rs
    use rig::prelude::*;
use rig::providers::openai;

#[tokio::main]
async fn main() -> Result<(), anyhow::Error> {
    let client = openai::CompletionsClient::builder()
        .api_key(std::env::var("SUBCONSCIOUS_API_KEY")?)
        .base_url("https://api.subconscious.dev/v1")
        .build()?;

    let agent = client
        .agent("subconscious/glm-5.3-marathon")
        .preamble("You are a helpful assistant.")
        .build();

    let response = agent.prompt("Hello!").await?;
    println!("{response}");
    Ok(())
}

  4. Step 4: Run it

    Build and run.

    Terminal
    cargo run

Why run Rig on Subconscious

No new SDK
Subconscious speaks OpenAI Chat Completions and Anthropic Messages, so the client you already use works with a base URL change.
Pay per token
No plan and no commitment: sign up, get an API key and pay for the tokens your agents use.
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.

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 Subconscious model should I use with Rig?
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 Rig on Subconscious OpenAI- or Anthropic-compatible?
This guide connects Rig 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 Rig 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 frameworks

See all