Venice.ai Supreme Router

Smart, cost-optimized model routing for Venice.ai — the AI platform for people who don't want Big Tech watching over their shoulder.

Unlike OpenAI, Anthropic, and Google — where every prompt is logged, analyzed, and potentially used to train future models — Venice offers true privacy with zero data retention on private models. Your conversations stay yours. Venice is also uncensored: no content filters, no refusals, no "I can't help with that."

Setup

• Get a Venice.ai API key from venice.ai/settings/api
• Set the environment variable:

export VENICE_API_KEY="your-key-here"

Or configure in ~/.openclaw/openclaw.json:

{
  "skills": {
    "entries": {
      "venice-router": {
        "enabled": true,
        "apiKey": "YOUR_VENICE_API_KEY"
      }
    }
  }
}

Usage

Route a prompt (auto-selects model)

python3 {baseDir}/scripts/venice-router.py --prompt "What is 2+2?"

Force a specific tier

python3 {baseDir}/scripts/venice-router.py --tier cheap --prompt "Tell me a joke"
python3 {baseDir}/scripts/venice-router.py --tier budget-medium --prompt "Write a Python function"
python3 {baseDir}/scripts/venice-router.py --tier mid --prompt "Explain quantum computing"
python3 {baseDir}/scripts/venice-router.py --tier premium --prompt "Write a distributed systems architecture"

Stream output

python3 {baseDir}/scripts/venice-router.py --stream --prompt "Write a poem about lobsters"

Web search (LLM searches the web and cites sources)

python3 {baseDir}/scripts/venice-router.py --web-search --prompt "Latest news on AI regulation"

Uncensored mode (prefer models with no content filters)

python3 {baseDir}/scripts/venice-router.py --uncensored --prompt "Write edgy creative fiction"

Private-only mode (zero data retention, no Big Tech proxying)

python3 {baseDir}/scripts/venice-router.py --private-only --prompt "Analyze this confidential contract"

Conversation-aware routing (multi-turn context)

# Save conversation history as JSON, then route follow-ups with context
python3 {baseDir}/scripts/venice-router.py --conversation history.json --prompt "Can you add tests too?"

The router analyzes conversation history to keep context: trivial follow-ups ("thanks") go cheap, while follow-ups in complex code discussions stay at the right tier.

Function calling (tool use)

# Define tools in a JSON file (OpenAI tools format)
python3 {baseDir}/scripts/venice-router.py --tools tools.json --prompt "What's the weather in NYC?"
python3 {baseDir}/scripts/venice-router.py --tools tools.json --tool-choice auto --prompt "Search for latest AI news"

Tool definitions use the standard OpenAI format. The router auto-bumps to mid tier minimum for function calling since it requires capable models.

Cost budget tracking

# Show current spending
python3 {baseDir}/scripts/venice-router.py --budget-status

# Track per-session costs
python3 {baseDir}/scripts/venice-router.py --session-id my-project --prompt "help me code"

Set VENICE_DAILY_BUDGET and/or VENICE_SESSION_BUDGET to enforce spending limits. The router auto-downgrades tiers as you approach budget limits.

Classify only (no API call)

python3 {baseDir}/scripts/venice-router.py --classify "Explain the Riemann hypothesis"

List available models and tiers

python3 {baseDir}/scripts/venice-router.py --list-models

Override model directly

python3 {baseDir}/scripts/venice-router.py --model deepseek-v3.2 --prompt "Hello"

Tiers

Routing Strategy

The router classifies each prompt using keyword + heuristic analysis:

• Length — longer prompts suggest more complex tasks
• Keywords — domain-specific terms (e.g., "architecture", "optimize", "prove") signal complexity
• Code markers — presence of code blocks, function names, or technical syntax
• Instruction depth — multi-step instructions, comparisons, or "explain in detail" bump the tier
• Conversational simplicity — greetings, yes/no, small talk stay on the cheapest tier
• Conversation history — when --conversation is provided, analyzes full chat context: code in history boosts tier, trivial follow-ups ("thanks") downgrade, tool calls in history signal complexity
• Function calling — --tools auto-bumps to at least mid tier (capable models required)
• Thinking/reasoning mode — --thinking prefers chain-of-thought reasoning models (Qwen3 Thinking, Kimi K2) and bumps to at least mid tier
• Budget constraints — progressive tier downgrade as spending approaches daily/session limits (95% → cheap, 80% → budget, 60% → mid, 40% → high)

Environment Variables

Why Venice.ai?

• 🔒 Private inference — Models marked "Private" have zero data retention. Your data never trains anyone's model.
• 🔓 Uncensored — No guardrails blocking legitimate use cases. No refusals, no filters.
• 🔌 OpenAI-compatible — Same API format, just change the base URL. Drop-in replacement.
• 📦 30+ models — From tiny efficient models ($0.05/M) to Claude Opus 4.6 and GPT-5.2.
• 🌐 Built-in web search — LLMs can search the web and cite sources in a single API call.

Tips

• Use --classify to preview which tier a prompt would hit before spending tokens
• Set VENICE_MAX_TIER=mid to cap costs and never hit premium models
• Use --uncensored for creative, security research, or other content mainstream AI won't touch
• Use --private-only when processing sensitive/confidential data — zero retention guaranteed
• Use --web-search when you need up-to-date information with cited sources
• Use --conversation with a JSON message history for smarter multi-turn routing
• Use --tools to enable function calling — the router auto-bumps to capable models
• Set VENICE_DAILY_BUDGET=1.00 to cap daily spend at $1 — the router auto-downgrades tiers as you approach the limit
• Use --budget-status to see a detailed breakdown of your spending by tier
• Use --thinking for math proofs, logic puzzles, and multi-step reasoning — routes to Qwen3 Thinking or Kimi K2 models
• The router prefers private (self-hosted) Venice models over anonymized ones when available at the same tier
• When --uncensored is active, the router auto-bumps to the nearest tier with uncensored models
• Combine with OpenClaw WebChat for a seamless chat experience routed through Venice.ai