docs/providers/venice.md
Venice AI provides privacy-focused inference: open models run
with no logging, plus anonymized proxy access to Claude, GPT, Gemini, and Grok.
All endpoints are OpenAI-compatible (/v1).
| Mode | Behavior | Models |
|---|---|---|
| Private | Prompts/responses are never stored or logged. Ephemeral. | Llama, Qwen, DeepSeek, Kimi, MiniMax, Venice Uncensored, etc. |
| Anonymized | Proxied through Venice with metadata stripped before forwarding. | Claude, GPT, Gemini, Grok |
Prompts for the API key (or reuses an existing `VENICE_API_KEY`), lists available Venice models, and sets your default model.
</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>
venice/kimi-k2-5 (private, reasoning, vision).venice/claude-opus-4-6.openclaw models set venice/kimi-k2-5
openclaw models list --all --provider venice
You can also run openclaw configure and pick Model/auth provider > Venice AI.
Grok-backed Venice models (grok-41-fast and similar) get the same tool-schema
compat patch as the native xAI provider, since they share the same upstream
tool-call format.
The bundled catalog above is a manifest-backed seed list. At runtime OpenClaw
refreshes it from the Venice /models API and falls back to the seed list if
the API is unreachable. The /models endpoint is public (no auth needed for
listing), but inference requires a valid API key.
If Venice exposes DeepSeek V4 models such as deepseek-v4-pro or
deepseek-v4-flash, OpenClaw fills the required reasoning_content replay
field on assistant messages when Venice omits it, and strips thinking/
reasoning/reasoning_effort from the request payload (Venice rejects
DeepSeek's native thinking control on these models). This replay fix is
separate from the native DeepSeek provider's own thinking controls.
| Feature | Support |
|---|---|
| Streaming | All models |
| Function calling | Most models; disabled per-model where noted above |
| Vision/Images | Models marked "Vision" above |
| JSON mode | Via response_format |
Venice uses a credit-based system. Anonymized models cost roughly the same as direct API pricing plus a small Venice fee. See venice.ai/pricing for current rates.
# Default private model
openclaw agent --model venice/kimi-k2-5 --message "Quick health check"
# Claude Opus via Venice (anonymized)
openclaw agent --model venice/claude-opus-4-6 --message "Summarize this task"
# Uncensored model
openclaw agent --model venice/venice-uncensored --message "Draft options"
# Vision model with image
openclaw agent --model venice/qwen3-vl-235b-a22b --message "Review attached image"
# Coding model
openclaw agent --model venice/qwen3-coder-480b-a35b-instruct --message "Refactor this function"
Confirm the key starts with `vapi_`.