Add Venice AI as a Model
Change your OpenClaw agent's model to Venice AI for privacy-focused and uncensored inference.
Venice AI provides privacy-focused inference — open models run with no logging, plus anonymized proxy access to Claude, GPT, and other frontier models. OpenClaw ships with Venice as a built-in provider, so no plugin install is required.
What You'll Need
- A deployed OpenClaw agent
- A Venice AI account with an API key
Get a Venice API Key
- Sign up at venice.ai and log in.
- Go to Settings → API Keys.
- Click Create new key, then copy the key. It looks like
vapi_xxxxxxxxxxxx.
Keep this key handy — you'll paste it into the config wizard in the next section.
Add Venice as the Model
Open Your Project
Go to app.xo.builders and select your OpenClaw project from the sidebar.
Open Your Workspace
Open your workspace IDE (Launch → Agent Connections → code-server), then open a terminal and run:
openclaw configSelect Gateway Location
When prompted with "Where will the Gateway run?", select Local (this machine).
Pick the Model Section
The wizard asks which sections to configure. Use arrow keys and spacebar to select:
- Model (pick provider + credentials)
Choose Venice AI
In the Model/auth provider list, scroll down and select Venice AI.
Enter Your Venice API Key
Paste the vapi_... key you created earlier. You can also set it as an environment variable (VENICE_API_KEY) instead.
Select Models
The wizard lists the available Venice models. Use arrow keys and spacebar to pick the ones you want in the /model picker (e.g., GLM 4.7, Claude Opus, Qwen3 Coder).
Finish the Wizard
Back at the section menu, scroll to Continue (Done) and press Enter. The config wizard finalizes and your agent now uses Venice AI.
Popular Venice Models
| Use case | Model |
|---|---|
| General chat (default) | venice/zai-org-glm-4.7 |
| Best overall quality | venice/claude-opus-5 |
| Privacy + coding | venice/qwen3-coder-480b-a35b-instruct-turbo |
| Complex private tasks | venice/deepseek-v3.2 |
| Uncensored | venice/venice-uncensored-1-2 |
Not sure which model?
Run openclaw models list --all --provider venice to see the live catalog — Venice adds and retires models over time.
Verify the Config
Run openclaw models list | grep venice in your terminal to confirm the provider is connected. You can also open openclaw.json in your workspace — the agents.defaults section reflects the new model:
{
"env": {
"VENICE_API_KEY": "vapi_..."
},
"agents": {
"defaults": {
"model": {
"primary": "venice/zai-org-glm-4.7"
}
}
}
}