> ## Documentation Index
> Fetch the complete documentation index at: https://docs.radium.cloud/llms.txt
> Use this file to discover all available pages before exploring further.

# Tools and frameworks

> Radium inside the frameworks your application already runs on

# Tools and frameworks

Radium exposes an OpenAI-compatible Chat Completions API. Any framework, SDK, or library that can point at a custom base URL and model name works with Radium. This section covers the most common integrations.

## Frameworks

<CardGroup cols={2}>
  <Card title="LangChain" icon="link" href="/tools/langchain">Python chains and agents via ChatOpenAI</Card>
  <Card title="LangGraph" icon="sitemap" href="/tools/langgraph">State-machine agents with graph nodes</Card>
  <Card title="LlamaIndex" icon="layer-group" href="/tools/llamaindex">RAG and query engines via OpenAILike</Card>
  <Card title="Vercel AI SDK" icon="cloud" href="/tools/vercel-ai-sdk">Next.js and Node.js streaming</Card>
  <Card title="OpenAI Python SDK" icon="terminal" href="/tools/openai-python">Direct SDK with custom base URL</Card>
  <Card title="PydanticAI" icon="check-circle" href="/tools/pydanticai">Type-safe agents withOpenAIChatModel</Card>
  <Card title="CrewAI" icon="users" href="/tools/crewai">Multi-agent crews with LiteLLM routing</Card>
  <Card title="DSPy" icon="code" href="/tools/dspy">Program optimization with signatures</Card>
  <Card title="AG2" icon="robot" href="/tools/ag2">AutoGen successor with OpenAIConfig</Card>
  <Card title="Agno" icon="brain" href="/tools/agno">Lightweight agents with OpenAILike</Card>
</CardGroup>

## What changes in every integration

Three values change when you point any framework at Radium:

1. **Base URL** — `https://api.radium.cloud/v1` (OpenAI format)
2. **API key** — your Radium API key from [deploy.radium.cloud](https://deploy.radium.cloud)
3. **Model string** — `hal-1.0`, `clarke-1.0`, or `tycho-1.0`

Everything else — prompts, tools, chains, agents, streaming logic — stays the same.

## Compatibility matrix

| Framework | Transport | Streaming | Tool calling | Verified |
| - | - | - | - | - |
| LangChain | HTTP | Yes | Yes | Aug 2026 |
| LangGraph | HTTP | Yes | Yes | Aug 2026 |
| LlamaIndex | HTTP | Yes | Yes | Aug 2026 |
| Vercel AI SDK | HTTP | Yes | Yes | Aug 2026 |
| OpenAI Python SDK | HTTP | Yes | Yes | Aug 2026 |
| PydanticAI | HTTP | Yes | Yes | Aug 2026 |
| CrewAI | HTTP | Yes | Yes | Aug 2026 |
| DSPy | HTTP | Yes | Yes | Aug 2026 |
| AG2 | HTTP | Yes | Yes | Aug 2026 |
| Agno | HTTP | Yes | Yes | Aug 2026 |

<Note>
  All integrations were verified with Python 3.12.7 or Node.js 22+ against `hal-1.0`, `clarke-1.0`, and `tycho-1.0`.
</Note>

## Common patterns

### Environment variables

Every guide uses the same two environment variables:

```bash theme={null}
export RADIUM_API_KEY="your-radium-api-key"
export RADIUM_MODEL="hal-1.0"
```

### Virtual environment

Python guides create a virtual environment before installing packages:

```bash theme={null}
mkdir radium-project && cd radium-project
python3 -m venv .venv
source .venv/bin/activate  # macOS/Linux
# .venv\Scripts\Activate.ps1  # Windows
```

### Model selection

Switch models by changing the environment variable:

```bash theme={null}
export RADIUM_MODEL="clarke-1.0"  # or tycho-1.0
```

## Troubleshooting all integrations

| Symptom | Cause | Fix |
| - | - | - |
| `401` or `403` | Missing or wrong API key | Export `RADIUM_API_KEY` in the active terminal |
| `404` | Wrong base URL or model ID | Use `https://api.radium.cloud/v1` and exact model names |
| Empty output | `max_tokens` too low | Use `512` or higher |
| Import errors | Wrong virtual environment | Activate `.venv` and reinstall packages |
| Calls going to OpenAI | Missing custom provider | Pass the Radium `base_url` explicitly |


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.