OpenClaw Skills | The Largest Library of OpenClaw Extensions

Venice is our recommended Venice configuration: privacy-first inference, with optional anonymous proxy access to proprietary models.

Venice AI provides privacy-oriented inference services, supporting "uncensored" models and accessing major proprietary models through its anonymous proxy. By default, inference is private: no data training, no logging.

Tutorial.step

Why use Venice in OpenClaw

- Private inference: Run open-source models (no logging by default).

- Uncensored models: Use models with fewer content restrictions when needed.

- Anonymous access: Access proprietary models (Opus/GPT/Gemini) through anonymous proxy, use when quality matters most.

- Provides OpenAI-compatible '<code className="bg-white/10 px-1.5 py-0.5 rounded text-emerald-300 text-sm">'/v1'</code>' endpoints.

Tutorial.step

Privacy modes

Venice offers two privacy levels—understanding this is key to choosing models:

| Mode | Description | Model Examples |

| ''General chat'' | '<code className="bg-white/10 px-1.5 py-0.5 rounded text-emerald-300 text-sm">'llama-3.3-70b'</code>' | All-purpose, fully private |

| ''Best overall quality'' | '<code className="bg-white/10 px-1.5 py-0.5 rounded text-emerald-300 text-sm">'claude-opus-45'</code>' | Opus still strongest on hardest tasks |

| ''Privacy + Claude quality'' | '<code className="bg-white/10 px-1.5 py-0.5 rounded text-emerald-300 text-sm">'claude-opus-45'</code>' | Strong reasoning via anonymous proxy |

| ''Coding'' | '<code className="bg-white/10 px-1.5 py-0.5 rounded text-emerald-300 text-sm">'qwen3-coder-480b-a35b-instruct'</code>' | Code-focused, 262k context |

| ''Vision tasks'' | '<code className="bg-white/10 px-1.5 py-0.5 rounded text-emerald-300 text-sm">'qwen3-vl-235b-a22b'</code>' | Strong vision model in private mode |

| ''Uncensored'' | '<code className="bg-white/10 px-1.5 py-0.5 rounded text-emerald-300 text-sm">'venice-uncensored'</code>' | Fewer content restrictions |

| ''Fast and economical'' | '<code className="bg-white/10 px-1.5 py-0.5 rounded text-emerald-300 text-sm">'qwen3-4b'</code>' | Lightweight but still capable |

| ''Complex reasoning'' | '<code className="bg-white/10 px-1.5 py-0.5 rounded text-emerald-300 text-sm">'deepseek-v3.2'</code>' | Strong reasoning, private |

Tutorial.step

Available models (25 total)

Tutorial.step

Private Models (15) — Fully private, no logging

| | | -- |

| '<code className="bg-white/10 px-1.5 py-0.5 rounded text-emerald-300 text-sm">'zai-org-glm-4.7'</code>' | GLM 4.7 | 202k | Reasoning, multilingual |

Tutorial.step

Anonymized Models (10) — Through Venice proxy

| | - | - |

| Streaming | ✅ All models |

| ''Function calling'' | ✅ Most models (per API's '<code className="bg-white/10 px-1.5 py-0.5 rounded text-emerald-300 text-sm">'supportsFunctionCalling'</code>') |

| Vision/Images | ✅ Models marked with Vision feature |

| ''JSON mode'' | ✅ Available via '<code className="bg-white/10 px-1.5 py-0.5 rounded text-emerald-300 text-sm">'response_format'</code>' |

Tutorial.step

Pricing

Venice uses credit-based billing. For latest pricing, see '<a href="https://venice.ai/pricing" className="text-emerald-400 hover:text-emerald-300 transition-colors">'venice.ai/pricing'</a>':

- Private models: Usually cheaper

- Anonymized models: Roughly equal to direct API pricing + small Venice fee

Tutorial.step

Comparison: Venice vs Direct API

| Dimension | Venice (Anonymized) | Direct API |

| --- |

| Privacy | Strips metadata, anonymized | Tied to your account |

| Latency | +10~50ms (proxy overhead) | Direct |

| Features | Most features supported | Full features |

| Billing | Venice credits | Provider bill |

Tutorial.step

Usage examples

Bash

openclaw chat --model venice/llama-3.3-70b


openclaw chat --model venice/claude-opus-45


openclaw chat --model venice/venice-uncensored


openclaw chat --model venice/qwen3-vl-235b-a22b


openclaw chat --model venice/qwen3-coder-480b-a35b-instruct

Tutorial.step

Troubleshooting

Tutorial.step

API Key not recognized

Bash

echo $VENICE_API_KEY
openclaw models list | grep venice

Ensure key starts with '<code className="bg-white/10 px-1.5 py-0.5 rounded text-emerald-300 text-sm">'vapi_'</code>'.

Tutorial.step

Model unavailable

Venice's model catalog is dynamically updated. Run '<code className="bg-white/10 px-1.5 py-0.5 rounded text-emerald-300 text-sm">'openclaw models list'</code>' to see currently available models. Some models may be temporarily offline.

Tutorial.step

Connection issues

Venice API address is '<code className="bg-white/10 px-1.5 py-0.5 rounded text-emerald-300 text-sm">'https://api.venice.ai/api/v1'</code>'. Ensure network allows HTTPS access.

Tutorial.step

Config file example

Json5

{
  env: { VENICE_API_KEY: "vapi_..." },
  agents: { defaults: { model: { primary: "venice/llama-3.3-70b" } } },
  models: {
    mode: "merge",
    providers: {
      venice: {
        baseUrl: "https://api.venice.ai/api/v1",
        apiKey: "${VENICE_API_KEY}",
        api: "openai-completions",
        models: [
          {
            id: "llama-3.3-70b",
            name: "Llama 3.3 70B",
            reasoning: false,
            input: ["text"],
            cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 },
            contextWindow: 131072,
            maxTokens: 8192,
          },
        ],
      },
    },
  },
}

Tutorial.step

Links

- '<a href="https://venice.ai" className="text-emerald-400 hover:text-emerald-300 transition-colors">'Venice AI'</a>'

- '<a href="https://docs.venice.ai" className="text-emerald-400 hover:text-emerald-300 transition-colors">'API docs'</a>'

- '<a href="https://venice.ai/pricing" className="text-emerald-400 hover:text-emerald-300 transition-colors">'Pricing'</a>'

- '<a href="https://status.venice.ai" className="text-emerald-400 hover:text-emerald-300 transition-colors">'Status page'</a>'