Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.clawdia.cc/llms.txt

Use this file to discover all available pages before exploring further.

​
Venice AI (Venius highlight)

Venius is our highlight Venice setup for privacy-first inference with optional anonymized access to proprietary models. 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.

​
Why Venice in Clawdia

  • Private inference for open-source models (no logging).
  • Uncensored models when you need them.
  • Anonymized access to proprietary models (Opus/GPT/Gemini) when quality matters.
  • OpenAI-compatible /v1 endpoints.

​
Privacy Modes

Venice offers two privacy levels — understanding this is key to choosing your model:
ModeDescriptionModels
PrivateFully private. Prompts/responses are never stored or logged. Ephemeral.Llama, Qwen, DeepSeek, Venice Uncensored, etc.
AnonymizedProxied through Venice with metadata stripped. The underlying provider (OpenAI, Anthropic) sees anonymized requests.Claude, GPT, Gemini, Grok, Kimi, MiniMax

​
Features

  • Privacy-focused: Choose between “private” (fully private) and “anonymized” (proxied) modes
  • Uncensored models: Access to models without content restrictions
  • Major model access: Use Claude, GPT-5.2, Gemini, Grok via Venice’s anonymized proxy
  • OpenAI-compatible API: Standard /v1 endpoints for easy integration
  • Streaming: ✅ Supported on all models
  • Function calling: ✅ Supported on select models (check model capabilities)
  • Vision: ✅ Supported on models with vision capability
  • No hard rate limits: Fair-use throttling may apply for extreme usage

​
Setup

​
1. Get API Key

  1. Sign up at venice.ai
  2. Go to Settings → API Keys → Create new key
  3. Copy your API key (format: vapi_xxxxxxxxxxxx)

​
2. Configure Clawdia

Option A: Environment Variable 
export VENICE_API_KEY="vapi_xxxxxxxxxxxx"
Option B: Interactive Setup (Recommended) 
clawdia 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
Option C: Non-interactive 
clawdia onboard --non-interactive \
  --auth-choice venice-api-key \
  --venice-api-key "vapi_xxxxxxxxxxxx"

​
3. Verify Setup

clawdia chat --model venice/llama-3.3-70b "Hello, are you working?"

​
Model Selection

After setup, Clawdia shows all available Venice models. Pick based on your needs:
  • Default (our pick): venice/llama-3.3-70b for private, balanced performance.
  • Best overall quality: venice/claude-opus-45 for hard jobs (Opus remains the strongest).
  • Privacy: Choose “private” models for fully private inference.
  • Capability: Choose “anonymized” models to access Claude, GPT, Gemini via Venice’s proxy.
Change your default model anytime: 
clawdia models set venice/claude-opus-45
clawdia models set venice/llama-3.3-70b
List all available models: 
clawdia models list | grep venice

​
Configure via clawdia configure

  1. Run clawdia configure
  2. Select Model/auth
  3. Choose Venice AI

​
Which Model Should I Use?

Use CaseRecommended ModelWhy
General chatllama-3.3-70bGood all-around, fully private
Best overall qualityclaude-opus-45Opus remains the strongest for hard tasks
Privacy + Claude qualityclaude-opus-45Best reasoning via anonymized proxy
Codingqwen3-coder-480b-a35b-instructCode-optimized, 262k context
Vision tasksqwen3-vl-235b-a22bBest private vision model
Uncensoredvenice-uncensoredNo content restrictions
Fast + cheapqwen3-4bLightweight, still capable
Complex reasoningdeepseek-v3.2Strong reasoning, private

​
Available Models (25 Total)

​
Private Models (15) — Fully Private, No Logging

Model IDNameContext (tokens)Features
llama-3.3-70bLlama 3.3 70B131kGeneral
llama-3.2-3bLlama 3.2 3B131kFast, lightweight
hermes-3-llama-3.1-405bHermes 3 Llama 3.1 405B131kComplex tasks
qwen3-235b-a22b-thinking-2507Qwen3 235B Thinking131kReasoning
qwen3-235b-a22b-instruct-2507Qwen3 235B Instruct131kGeneral
qwen3-coder-480b-a35b-instructQwen3 Coder 480B262kCode
qwen3-next-80bQwen3 Next 80B262kGeneral
qwen3-vl-235b-a22bQwen3 VL 235B262kVision
qwen3-4bVenice Small (Qwen3 4B)32kFast, reasoning
deepseek-v3.2DeepSeek V3.2163kReasoning
venice-uncensoredVenice Uncensored32kUncensored
mistral-31-24bVenice Medium (Mistral)131kVision
google-gemma-3-27b-itGemma 3 27B Instruct202kVision
openai-gpt-oss-120bOpenAI GPT OSS 120B131kGeneral
zai-org-glm-4.7GLM 4.7202kReasoning, multilingual

​
Anonymized Models (10) — Via Venice Proxy

Model IDOriginalContext (tokens)Features
claude-opus-45Claude Opus 4.5202kReasoning, vision
claude-sonnet-45Claude Sonnet 4.5202kReasoning, vision
openai-gpt-52GPT-5.2262kReasoning
openai-gpt-52-codexGPT-5.2 Codex262kReasoning, vision
gemini-3-pro-previewGemini 3 Pro202kReasoning, vision
gemini-3-flash-previewGemini 3 Flash262kReasoning, vision
grok-41-fastGrok 4.1 Fast262kReasoning, vision
grok-code-fast-1Grok Code Fast 1262kReasoning, code
kimi-k2-thinkingKimi K2 Thinking262kReasoning
minimax-m21MiniMax M2.1202kReasoning

​
Model Discovery

Clawdia automatically discovers models from the Venice API when VENICE_API_KEY is set. If the API is unreachable, it falls back to a static catalog. The /models endpoint is public (no auth needed for listing), but inference requires a valid API key.

​
Streaming & Tool Support

FeatureSupport
Streaming✅ All models
Function calling✅ Most models (check supportsFunctionCalling in API)
Vision/Images✅ Models marked with “Vision” feature
JSON mode✅ Supported via response_format

​
Pricing

Venice uses a credit-based system. Check venice.ai/pricing for current rates:
  • Private models: Generally lower cost
  • Anonymized models: Similar to direct API pricing + small Venice fee

​
Comparison: Venice vs Direct API

AspectVenice (Anonymized)Direct API
PrivacyMetadata stripped, anonymizedYour account linked
Latency+10-50ms (proxy)Direct
FeaturesMost features supportedFull features
BillingVenice creditsProvider billing

​
Usage Examples

# Use default private model
clawdia chat --model venice/llama-3.3-70b

# Use Claude via Venice (anonymized)
clawdia chat --model venice/claude-opus-45

# Use uncensored model
clawdia chat --model venice/venice-uncensored

# Use vision model with image
clawdia chat --model venice/qwen3-vl-235b-a22b

# Use coding model
clawdia chat --model venice/qwen3-coder-480b-a35b-instruct

​
Troubleshooting

​
API key not recognized

echo $VENICE_API_KEY
clawdia models list | grep venice
Ensure the key starts with vapi_.

​
Model not available

The Venice model catalog updates dynamically. Run clawdia models list to see currently available models. Some models may be temporarily offline.

​
Connection issues

Venice API is at https://api.venice.ai/api/v1. Ensure your network allows HTTPS connections.

​
Config file example

{
  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
          }
        ]
      }
    }
  }
}