# How to use CrewAI with Subconscious

> To use CrewAI with Subconscious, create an `LLM` with `model="subconscious/glm-5.3-marathon"`, `custom_openai=True`, `base_url="https://api.subconscious.dev/v1"` and your API key, then give it to each `Agent`. Your crew then runs on Subconscious through CrewAI's native OpenAI client.

Canonical page: https://www.subconscious.dev/agents/frameworks/crewai
Category: [Frameworks](https://www.subconscious.dev/agents/frameworks)
Last verified: 2026-09-30
CrewAI: https://docs.crewai.com
Source: https://github.com/crewAIInc/crewAI

## Before you start

- Python 3.10+
- A Subconscious account and API key

## Set up CrewAI

### 1. Install CrewAI

Install the framework and its OpenAI-compatible client.

```bash
pip install -U crewai
```

### 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

custom_openai=True forces the native OpenAI-compatible client and sends the model name as is. Without it, CrewAI treats "subconscious" as an unknown provider and falls back to LiteLLM.

```python
import os
from crewai import Agent, Crew, LLM, Task

llm = LLM(
    model="subconscious/glm-5.3-marathon",
    custom_openai=True,
    base_url="https://api.subconscious.dev/v1",
    api_key=os.environ["SUBCONSCIOUS_API_KEY"],
)

researcher = Agent(
    role="Researcher",
    goal="Answer questions accurately",
    backstory="A meticulous analyst.",
    llm=llm,
)
task = Task(
    description="Summarize what an inference API is in two sentences.",
    expected_output="A two-sentence summary.",
    agent=researcher,
)
print(Crew(agents=[researcher], tasks=[task]).kickoff().raw)
```

### 4. Run it

Run the script.

```bash
python crew.py
```

## Connection details

- 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 API reference: https://docs.subconscious.dev

## Frequently asked questions

### My CrewAI version does not accept custom_openai. What now?

Use model="openai/subconscious/glm-5.3-marathon" with the same base_url. CrewAI strips the openai/ prefix and sends the rest as the model ID.

### Which Subconscious model should I use with CrewAI?

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 CrewAI on Subconscious OpenAI- or Anthropic-compatible?

This guide connects CrewAI 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 CrewAI 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.