Subconscious

How to use smolagents 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 smolagents 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 smolagents
Install the framework and its OpenAI-compatible client.
```bash
pip install "smolagents[openai]"
```

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
The parameter is api_base, not base_url. OpenAIServerModel is an alias for the same class.
```python
import os
from smolagents import OpenAIModel, ToolCallingAgent

model = OpenAIModel(
    model_id="subconscious/glm-5.3-marathon",
    api_base="https://api.subconscious.dev/v1",
    api_key=os.environ["SUBCONSCIOUS_API_KEY"],
)

agent = ToolCallingAgent(tools=[], model=model)
print(agent.run("What is the capital of France?"))
```

4. Run it
Run the script.
```bash
python agent.py
```

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

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

To use smolagents with Subconscious, create an OpenAIModel with model_id="subconscious/glm-5.3-marathon", api_base="https://api.subconscious.dev/v1" and your API key, then pass it to a ToolCallingAgent or CodeAgent. Your agent runs on Subconscious through its OpenAI-compatible API.

Get an API keyRead the API docs

Last verified against the smolagents docs on

Before you start

  • Python 3.10+
  • A Subconscious account and API key

smolagents docs · Source on GitHub

Set up smolagents

  1. Step 1: Install smolagents

    Install the framework and its OpenAI-compatible client.

    Terminal
    pip install "smolagents[openai]"

  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

    The parameter is api_base, not base_url. OpenAIServerModel is an alias for the same class.

    agent.py
    import os
from smolagents import OpenAIModel, ToolCallingAgent

model = OpenAIModel(
    model_id="subconscious/glm-5.3-marathon",
    api_base="https://api.subconscious.dev/v1",
    api_key=os.environ["SUBCONSCIOUS_API_KEY"],
)

agent = ToolCallingAgent(tools=[], model=model)
print(agent.run("What is the capital of France?"))

  4. Step 4: Run it

    Run the script.

    Terminal
    python agent.py

Why run smolagents 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 smolagents?
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 smolagents on Subconscious OpenAI- or Anthropic-compatible?
This guide connects smolagents 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 smolagents 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