romtuck/openclaw
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
36d0b15461
openclaw/docs/providers/venice.md

289 lines
9.6 KiB
Markdown
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

---
summary: "Use Venice AI privacy-focused models in Moltbot"
read_when:
- You want privacy-focused inference in Moltbot
- You want Venice AI setup guidance
---
# Venice AI (Venice highlight)
**Venice** 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 Moltbot
- **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:
| Mode | Description | Models |
|------|-------------|--------|
| **Private** | Fully private. Prompts/responses are **never stored or logged**. Ephemeral. | Llama, Qwen, DeepSeek, Venice Uncensored, etc. |
| **Anonymized** | Proxied 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](https://venice.ai)
2. Go to **Settings → API Keys → Create new key**
3. Copy your API key (format: `vapi_xxxxxxxxxxxx`)
### 2. Configure Moltbot
**Option A: Environment Variable**
```bash
export VENICE_API_KEY="vapi_xxxxxxxxxxxx"
```
**Option B: Interactive Setup (Recommended)**
```bash
moltbot 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**
```bash
moltbot onboard --non-interactive \
--auth-choice venice-api-key \
--venice-api-key "vapi_xxxxxxxxxxxx"
```
### 3. Verify Setup
```bash
moltbot chat --model venice/llama-3.3-70b "Hello, are you working?"
```
## Model Selection
After setup, Moltbot 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:
```bash
moltbot models set venice/claude-opus-45
moltbot models set venice/llama-3.3-70b
```
List all available models:
```bash
moltbot models list | grep venice
```
## Configure via `moltbot configure`
1. Run `moltbot configure`
2. Select **Model/auth**
3. Choose **Venice AI**
## Which Model Should I Use?
| Use Case | Recommended Model | Why |
|----------|-------------------|-----|
| **General chat** | `llama-3.3-70b` | Good all-around, fully private |
| **Best overall quality** | `claude-opus-45` | Opus remains the strongest for hard tasks |
| **Privacy + Claude quality** | `claude-opus-45` | Best reasoning via anonymized proxy |
| **Coding** | `qwen3-coder-480b-a35b-instruct` | Code-optimized, 262k context |
| **Vision tasks** | `qwen3-vl-235b-a22b` | Best private vision model |
| **Uncensored** | `venice-uncensored` | No content restrictions |
| **Fast + cheap** | `qwen3-4b` | Lightweight, still capable |
| **Complex reasoning** | `deepseek-v3.2` | Strong reasoning, private |
## Available Models (25 Total)
### Private Models (15) — Fully Private, No Logging
| Model ID | Name | Context (tokens) | Features |
|----------|------|------------------|----------|
| `llama-3.3-70b` | Llama 3.3 70B | 131k | General |
| `llama-3.2-3b` | Llama 3.2 3B | 131k | Fast, lightweight |
| `hermes-3-llama-3.1-405b` | Hermes 3 Llama 3.1 405B | 131k | Complex tasks |
| `qwen3-235b-a22b-thinking-2507` | Qwen3 235B Thinking | 131k | Reasoning |
| `qwen3-235b-a22b-instruct-2507` | Qwen3 235B Instruct | 131k | General |
| `qwen3-coder-480b-a35b-instruct` | Qwen3 Coder 480B | 262k | Code |
| `qwen3-next-80b` | Qwen3 Next 80B | 262k | General |
| `qwen3-vl-235b-a22b` | Qwen3 VL 235B | 262k | Vision |
| `qwen3-4b` | Venice Small (Qwen3 4B) | 32k | Fast, reasoning |
| `deepseek-v3.2` | DeepSeek V3.2 | 163k | Reasoning |
| `venice-uncensored` | Venice Uncensored | 32k | Uncensored |
| `mistral-31-24b` | Venice Medium (Mistral) | 131k | Vision |
| `google-gemma-3-27b-it` | Gemma 3 27B Instruct | 202k | Vision |
| `openai-gpt-oss-120b` | OpenAI GPT OSS 120B | 131k | General |
| `zai-org-glm-4.7` | GLM 4.7 | 202k | Reasoning, multilingual |
### Anonymized Models (10) — Via Venice Proxy
| Model ID | Original | Context (tokens) | Features |
|----------|----------|------------------|----------|
| `claude-opus-45` | Claude Opus 4.5 | 202k | Reasoning, vision |
| `claude-sonnet-45` | Claude Sonnet 4.5 | 202k | Reasoning, vision |
| `openai-gpt-52` | GPT-5.2 | 262k | Reasoning |
| `openai-gpt-52-codex` | GPT-5.2 Codex | 262k | Reasoning, vision |
| `gemini-3-pro-preview` | Gemini 3 Pro | 202k | Reasoning, vision |
| `gemini-3-flash-preview` | Gemini 3 Flash | 262k | Reasoning, vision |
| `grok-41-fast` | Grok 4.1 Fast | 262k | Reasoning, vision |
| `grok-code-fast-1` | Grok Code Fast 1 | 262k | Reasoning, code |
| `kimi-k2-thinking` | Kimi K2 Thinking | 262k | Reasoning |
| `minimax-m21` | MiniMax M2.1 | 202k | Reasoning |
## Model Discovery
Moltbot 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
| 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` |
## Pricing
Venice uses a credit-based system. Check [venice.ai/pricing](https://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
| 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 |
## Usage Examples
```bash
# Use default private model
moltbot chat --model venice/llama-3.3-70b
# Use Claude via Venice (anonymized)
moltbot chat --model venice/claude-opus-45
# Use uncensored model
moltbot chat --model venice/venice-uncensored
# Use vision model with image
moltbot chat --model venice/qwen3-vl-235b-a22b
# Use coding model
moltbot chat --model venice/qwen3-coder-480b-a35b-instruct
```
## Troubleshooting
### API key not recognized
```bash
echo $VENICE_API_KEY
moltbot models list | grep venice
```
Ensure the key starts with `vapi_`.
### Model not available
The Venice model catalog updates dynamically. Run `moltbot models list` to see currently available models. Some models may be temporarily offline.
### Connection issues
Venice API is at `https://api.venice.ai/api/v1`. Ensure your network allows HTTPS connections.
## Config file example
```json5
{
env: { VENICE_API_KEY: "vapi_..." },
agents: { defaults: { model: { primary: "venice/llama-3.3-70b" } } },
models: {
mode: "merge",
providers: {
venice: {
baseUrl: "https://api.venice.ai/api/v1",
apiKey: "${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
}
]
}
}
}
}
```
## Embeddings for Memory (New!)
Venice supports OpenAI-compatible embeddings (`/api/v1/embeddings`) – perfect for semantic memory search (memory-lancedb plugin).
**Config** (in Moltbot/agent config):
```json
"extensions": {
"memory-lancedb": {
"embedding": {
"provider": "venice",
"model": "text-embedding-bge-m3",
"apiKey": "${VENICE_API_KEY}",
"baseUrl": "https://api.venice.ai/api/v1"
}
}
}
```
- **Model**: text-embedding-bge-m3 (1024 dims, multilingual)
- **Private**: Embeddings are ephemeral/private like inference.
- **Test**: `memory_search "habits"` – recalls from MEMORY.md + memory/*.md.
- **Why Venice**: Uncensored/private vector search, no OpenAI key needed.
`moltbot gateway restart` → ready!
## Links
- [Venice AI](https://venice.ai)
- [API Documentation](https://docs.venice.ai)
- [Pricing](https://venice.ai/pricing)
- [Status](https://status.venice.ai)
Reference in New Issue View Git Blame Copy Permalink