Quick Start¶
Get started with FreeInference in 5 minutes.
Step 1: Get Your API Key¶
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/v1API Key:
your-api-key-here
Select a model:
glm-5.3-flashfor general coding tasksqwen3.6-35bfor faster edits and shorter loopsdeepseek-v4-flashfor complex agentic workminimax-m3for 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 + ,orCtrl + ,)Go to Models → Enter your API key
Click Override OpenAI Base URL → Enter:
https://freeinference.org/v1Enable the toggle and start coding
Claude Code¶
curl -fsSL -o setup_claude_code.sh https://doc.freeinference.org/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.shfrom your local checkout.
Roo Code / Cline¶
Install extension in your IDE
Settings → OpenAI Compatible
Base URL:
https://freeinference.org/v1API Key:
your-api-key-here
Continue¶
Add a model entry to the models list in ~/.continue/config.yaml (merge with your existing config — don’t overwrite it):
models:
- name: FreeInference
provider: openai
model: glm-5.3-flash
apiBase: https://freeinference.org/v1
apiKey: your-api-key-here
roles:
- chat
- edit
Note:
config.yamlreplacesconfig.json, which Continue has deprecated. If your installation still usesconfig.json, add the same fields (with"title"in place ofname) to itsmodelsarray instead.
Aider¶
export OPENAI_API_BASE=https://freeinference.org/v1
export OPENAI_API_KEY=your-api-key-here
aider --model openai/glm-5.3-flash
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.