docs/providers/venice.md
Venice AI provides privacy-focused AI inference with support for uncensored models and access to major proprietary models through their anonymized proxy. All inference is private by default — no training on your data, no logging.
/v1 endpoints.Venice offers two privacy levels — understanding this is key to choosing your model:
| Mode | Description | Models |
|---|---|---|
| Private | Fully private. Prompts/responses are never stored or logged. Ephemeral. | Llama, Qwen, DeepSeek, Kimi, MiniMax, Venice Uncensored, etc. |
| Anonymized | Proxied through Venice with metadata stripped. The underlying provider (OpenAI, Anthropic, Google, xAI) sees anonymized requests. | Claude, GPT, Gemini, Grok |
/v1 endpoints for easy integration<Tabs>
<Tab title="Interactive (recommended)">
```bash
openclaw onboard --auth-choice venice-api-key
```
This will:
1. Prompt for your API key (or use existing `VENICE_API_KEY`)
2. Show all available Venice models
3. Let you pick your default model
4. Configure the provider automatically
</Tab>
<Tab title="Environment variable">
```bash
export VENICE_API_KEY="vapi_xxxxxxxxxxxx"
```
</Tab>
<Tab title="Non-interactive">
```bash
openclaw onboard --non-interactive \
--auth-choice venice-api-key \
--venice-api-key "vapi_xxxxxxxxxxxx"
```
</Tab>
</Tabs>
After setup, OpenClaw shows all available Venice models. Pick based on your needs:
venice/kimi-k2-5 for strong private reasoning plus vision.venice/claude-opus-4-6 for the strongest anonymized Venice path.Change your default model anytime:
openclaw models set venice/kimi-k2-5
openclaw models set venice/claude-opus-4-6
List all available models:
openclaw models list --all --provider venice
You can also run openclaw configure, select Model/auth, and choose Venice AI.
| Use Case | Recommended Model | Why |
|---|---|---|
| General chat (default) | kimi-k2-5 | Strong private reasoning plus vision |
| Best overall quality | claude-opus-4-6 | Strongest anonymized Venice option |
| Privacy + coding | qwen3-coder-480b-a35b-instruct | Private coding model with large context |
| Private vision | kimi-k2-5 | Vision support without leaving private mode |
| Fast + cheap | qwen3-4b | Lightweight reasoning model |
| Complex private tasks | deepseek-v3.2 | Strong reasoning, but no Venice tool support |
| Uncensored | venice-uncensored | No content restrictions |
If Venice exposes DeepSeek V4 models such as venice/deepseek-v4-pro or
venice/deepseek-v4-flash, OpenClaw fills the required DeepSeek V4
reasoning_content replay placeholder on assistant messages when the proxy
omits it. Venice rejects DeepSeek's native top-level thinking control, so
OpenClaw keeps that provider-specific replay fix separate from the native
DeepSeek provider's thinking controls.
OpenClaw ships a manifest-backed Venice seed catalog for read-only model listing. Runtime refresh can still discover models from the Venice API, and falls back to the manifest catalog if the API is unreachable.
The /models endpoint is public (no auth needed for listing), but inference requires a valid API key.
| Feature | Support |
|---|---|
| Streaming | All models |
| Function calling | Most models (check supportsFunctionCalling in API) |
| Vision/Images | Models marked with "Vision" feature |
| JSON mode | Supported via response_format |
Venice uses a credit-based system. Check venice.ai/pricing for current rates:
| Aspect | Venice (Anonymized) | Direct API |
|---|---|---|
| Privacy | Metadata stripped, anonymized | Your account linked |
| Latency | +10-50ms (proxy) | Direct |
| Features | Most features supported | Full features |
| Billing | Venice credits | Provider billing |
# Use the default private model
openclaw agent --model venice/kimi-k2-5 --message "Quick health check"
# Use Claude Opus via Venice (anonymized)
openclaw agent --model venice/claude-opus-4-6 --message "Summarize this task"
# Use uncensored model
openclaw agent --model venice/venice-uncensored --message "Draft options"
# Use vision model with image
openclaw agent --model venice/qwen3-vl-235b-a22b --message "Review attached image"
# Use coding model
openclaw agent --model venice/qwen3-coder-480b-a35b-instruct --message "Refactor this function"
Ensure the key starts with `vapi_`.