Quick Start

Get started with FreeInference in 5 minutes.

Step 1: Get Your API Key

Visit https://freeinference.org
Register for a free account
Log in and create your API key from the dashboard

Step 2: Configure Your Agent

Choose your coding agent below and follow the steps. If you want the fastest agent-first setup, start with Kilo Code. For detailed setup and troubleshooting, see the Integration Guides.

Kilo Code (Recommended)

Install the Kilo Code extension or plugin in your IDE
Open the Kilo Code side panel
Open Kilo Code settings
Set API Provider to OpenAI Compatible
Enter the exact connection values:
- Base URL: https://freeinference.org/v1
- API Key: your-api-key-here
Select a model:
- glm-5.1 for general coding tasks
- glm-5-turbo for faster edits and shorter loops
- minimax-m2.5 for long-context or image-aware work
Save the settings
Start a new Kilo Code session and send a short prompt to verify the connection

Tip: If the model list does not refresh immediately, reopen the Kilo panel or paste the model ID manually.

Cursor

Open Settings (Cmd + , or Ctrl + ,)
Go to Models → Enter your API key
Click Override OpenAI Base URL → Enter: https://freeinference.org/v1
Enable the toggle and start coding

Claude Code

curl -fsSL -o setup_claude_code.sh https://raw.githubusercontent.com/HarvardMadSys/hybridInference/main/ops/setup/setup_claude_code.sh
# Inspect the script before running (recommended):
less setup_claude_code.sh
bash setup_claude_code.sh

Security note: Always review remote shell scripts before executing them. You can also clone the repo and run ops/setup/setup_claude_code.sh from your local checkout.

Roo Code / Cline

Install extension in your IDE
Settings → OpenAI Compatible
Base URL: https://freeinference.org/v1
API Key: your-api-key-here

Continue

Add a new model entry to the models array in ~/.continue/config.json (merge with your existing config — don’t overwrite it):

{
  "title": "FreeInference",
  "provider": "openai",
  "model": "glm-5.1",
  "apiBase": "https://freeinference.org/v1",
  "apiKey": "your-api-key-here"
}

Note: If ~/.continue/config.json doesn’t exist yet, wrap the entry above as {"models": [ <entry> ]}. Otherwise, append it to your existing models array so prior models and settings are preserved.

Aider

export OPENAI_API_BASE=https://freeinference.org/v1
export OPENAI_API_KEY=your-api-key-here
aider --model openai/glm-5.1

Other Agents (Windsurf, Twinny, CodeGPT, etc.)

See the full Integration Guides for all supported agents.

Step 3: Choose a Model

See available models and select one that fits your needs.

Next Steps

Integration Guides - Detailed setup for all supported agents and troubleshooting
Available Models - Model specifications and features
API Headers Reference - Authentication and custom headers

Need Help?

Having issues? Check the integration guide for troubleshooting.