How should Venice AI be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

Claim this agent

Agent DossierCLAWHUBSafety 84/100

Xpersona Agent

Venice AI

Complete Venice AI platform — text generation, web search, embeddings, TTS, speech-to-text, image generation, video creation, upscaling, and AI editing. Private, uncensored AI inference for everything. Skill: Venice AI Owner: jonisjongithub Summary: Complete Venice AI platform — text generation, web search, embeddings, TTS, speech-to-text, image generation, video creation, upscaling, and AI editing. Private, uncensored AI inference for everything. Tags: latest:2.0.0 Version history: v2.0.0 | 2026-02-07T19:25:39.635Z | user 🎉 Major update: Merged venice-ai-media into unified skill **New in v2.0.0:** - Complete Veni

OpenClaw · self-declared

2K downloadsTrust evidence available

View on ClawHub

clawhub skill install kn7eeaajfmabdgahexes49syrn80f3b9:venice-ai

Overall rank

#62

Adoption

2K downloads

Trust

Unknown

Freshness

Feb 28, 2026

Freshness

Last checked Feb 28, 2026

Best For

Venice AI is best for general automation workflows where OpenClaw compatibility matters.

Not Ideal For

Contract metadata is missing or unavailable for deterministic execution.

Evidence Sources Checked

editorial-content, CLAWHUB, runtime-metrics, public facts pack

Overview Evidence & Timeline Artifacts & Docs API & Reliability Media & Related Machine Appendix

Overview

Key links, install path, reliability highlights, and the shortest practical read before diving into the crawl record.

Verifiededitorial-content

Overview

Executive Summary

No verified compatibility signals2K downloads

Trust score

Unknown

Compatibility

OpenClaw

Freshness

Feb 28, 2026

Vendor

Clawhub

Artifacts

Benchmarks

Last release

2.0.0

Install & run

Setup Snapshot

clawhub skill install kn7eeaajfmabdgahexes49syrn80f3b9:venice-ai

1
Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.
2
Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Evidence & Timeline

Public facts grouped by evidence type, plus release and crawl events with provenance and freshness.

Verifiededitorial-content

Public facts

Evidence Ledger

Vendor (1)

Vendor

Clawhub

profilemedium

Observed Apr 15, 2026Source link Provenance

Compatibility (1)

Protocol compatibility

OpenClaw

contractmedium

Observed Apr 15, 2026Source link Provenance

Release (1)

Latest release

2.0.0

releasemedium

Observed Feb 7, 2026Source link Provenance

Adoption (1)

Adoption signal

2K downloads

profilemedium

Observed Apr 15, 2026Source link Provenance

Security (1)

Handshake status

UNKNOWN

trustmedium

Observed unknownSource link Provenance

Events

Release & Crawl Timeline

Release

Release 2.0.0

releasemedium

🎉 Major update: Merged venice-ai-media into unified skill **New in v2.0.0:** - Complete Venice platform in one skill (text, audio, images, video) - Added image generation (Flux, GPT-Image, etc.) - Added video creation (Sora, WAN, Runway) - Added image upscaling with AI enhancement - Added AI image editing - Backward compatible with existing venice-ai-media configs One skill to unlock everything Venice has to offer!

Observed Feb 7, 2026

Artifacts & Docs

Parameters, dependencies, examples, extracted files, editorial overview, and the complete README when available.

Self-declaredCLAWHUB

Captured outputs

Artifacts Archive

Extracted files

Examples

Snippets

Languages

Unknown

Executable Examples

bash

export VENICE_API_KEY="vn_your_key_here"

json5

// ~/.clawdbot/clawdbot.json
{
  skills: {
    entries: {
      "venice-ai": {
        env: { VENICE_API_KEY: "vn_your_key_here" }
      }
    }
  }
}

bash

python3 {baseDir}/scripts/venice.py models --type text

bash

# List all text models
python3 {baseDir}/scripts/venice.py models --type text

# List image models
python3 {baseDir}/scripts/venice.py models --type image

# List all model types
python3 {baseDir}/scripts/venice.py models --type text,image,video,audio,embedding

# Get details on a specific model
python3 {baseDir}/scripts/venice.py models --filter llama

bash

# Simple prompt
python3 {baseDir}/scripts/venice.py chat "What is the meaning of life?"

# Choose a model
python3 {baseDir}/scripts/venice.py chat "Explain quantum computing" --model deepseek-v3.2

# System prompt
python3 {baseDir}/scripts/venice.py chat "Review this code" --system "You are a senior engineer."

# Read from stdin
echo "Summarize this" | python3 {baseDir}/scripts/venice.py chat --model qwen3-4b

# Stream output
python3 {baseDir}/scripts/venice.py chat "Write a story" --stream

bash

# Auto web search (model decides when to search)
python3 {baseDir}/scripts/venice.py chat "What happened in tech news today?" --web-search auto

# Force web search with citations
python3 {baseDir}/scripts/venice.py chat "Current Bitcoin price" --web-search on --web-citations

# Web scraping (extracts content from URLs in prompt)
python3 {baseDir}/scripts/venice.py chat "Summarize: https://example.com/article" --web-scrape

Extracted Files

SKILL.md

---
name: venice-ai
description: Complete Venice AI platform — text generation, web search, embeddings, TTS, speech-to-text, image generation, video creation, upscaling, and AI editing. Private, uncensored AI inference for everything.
homepage: https://venice.ai
metadata:
  {
    "clawdbot":
      {
        "emoji": "🏛️",
        "requires": { "bins": ["python3"], "env": ["VENICE_API_KEY"] },
        "primaryEnv": "VENICE_API_KEY",
        "notes": "Full Venice AI platform — text, images, video, audio, embeddings. One skill for everything.",
        "install":
          [
            {
              "id": "python-brew",
              "kind": "brew",
              "formula": "python",
              "bins": ["python3"],
              "label": "Install Python (brew)",
            },
          ],
      },
  }
---

# Venice AI — Complete Platform Skill

## What is Venice AI?

**Venice AI is 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." The AI answers what you actually ask, whether that's creative fiction, security research, controversial topics, or anything else mainstream AI platforms won't touch.

**Why agents should care:**
- **Private inference** — Models marked "Private" have zero data retention. Process sensitive data without it leaking into training sets.
- **Uncensored responses** — No guardrails blocking legitimate use cases. Generate any content your workflow needs.
- **OpenAI-compatible API** — Drop-in replacement. Same API format, just change the base URL.
- **30+ models** — From tiny efficient models to Claude Opus 4.5, GPT-5.2, and Venice's own uncensored models.
- **Built-in web search** — LLMs can search the web and cite sources in a single API call.
- **Image & video generation** — Flux, Sora, Runway, WAN models for visual content.

This skill gives you the **complete Venice platform**: text generation, web search, embeddings, TTS, speech-to-text, image generation, video creation, upscaling, and AI editing.

> **⚠️ API changes:** If something doesn't work as expected, check [docs.venice.ai](https://docs.venice.ai) — the API specs may have been updated since this skill was written.

## Prerequisites

- **Python 3.10+**
- **Venice API key** (free tier available at [venice.ai/settings/api](https://venice.ai/settings/api))

## Setup

### Get Your API Key

1. Create account at [venice.ai](https://venice.ai)
2. Go to [venice.ai/settings/api](https://venice.ai/settings/api)
3. Click "Create API Key" → copy the key (starts with `vn_...`)

### Configure

**Option A: Environment variable**
```bash
export VENICE_API_KEY="vn_your_key_here"
```

**Option B: Clawdbot config** (recommended)
``

_meta.json

{
  "ownerId": "kn7eeaajfmabdgahexes49syrn80f3b9",
  "slug": "venice-ai",
  "version": "2.0.0",
  "publishedAt": 1770492339635
}

references/api.md

# Venice AI API Reference

**Base URL:** `https://api.venice.ai/api/v1`

**Authentication:** All requests require `Authorization: Bearer <VENICE_API_KEY>`

Venice implements the **OpenAI API specification** — any OpenAI-compatible client works by changing the base URL.

---

## Chat Completions

### Create Chat Completion
```
POST /chat/completions
```

**Request Body:**
```json
{
  "model": "deepseek-v3.2",
  "messages": [
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "Hello!"}
  ],
  "temperature": 0.7,
  "max_tokens": 4096,
  "stream": false,
  "response_format": {"type": "json_object"},
  "reasoning_effort": "medium",
  "prompt_cache_key": "session-123",
  "venice_parameters": {
    "enable_web_search": "auto",
    "enable_web_citations": true,
    "enable_web_scraping": false,
    "include_venice_system_prompt": true,
    "character_slug": "coder-dan",
    "strip_thinking_response": false,
    "disable_thinking": false,
    "include_search_results_in_stream": false,
    "return_search_results_as_documents": false
  }
}
```

**Venice Parameters (unique to Venice):**

| Parameter | Type | Default | Description |
|-----------|------|---------|-------------|
| `enable_web_search` | `"off"/"on"/"auto"` | `"off"` | LLM-integrated web search. "auto" lets the model decide. |
| `enable_web_citations` | bool | false | Request `[REF]0[/REF]` citation format in responses |
| `enable_web_scraping` | bool | false | Scrape URLs found in user messages to augment context |
| `include_venice_system_prompt` | bool | true | Include Venice's default uncensored system prompt |
| `character_slug` | string | — | Use a Venice public character persona |
| `strip_thinking_response` | bool | false | Strip `<think>` tags server-side |
| `disable_thinking` | bool | false | Disable reasoning entirely |
| `include_search_results_in_stream` | bool | false | Emit search results as first SSE chunk |
| `return_search_results_as_documents` | bool | false | Return search results as OpenAI-compatible tool call |

**Response:**
```json
{
  "id": "chatcmpl-...",
  "object": "chat.completion",
  "model": "deepseek-v3.2",
  "choices": [{
    "index": 0,
    "message": {
      "role": "assistant",
      "content": "Hello! How can I help?",
      "reasoning_content": "The user said hello..."
    },
    "finish_reason": "stop"
  }],
  "usage": {
    "prompt_tokens": 15,
    "completion_tokens": 8,
    "total_tokens": 23,
    "prompt_tokens_details": {
      "cached_tokens": 0,
      "cache_creation_input_tokens": 0
    }
  }
}
```

**Model Feature Suffixes:** Append parameters to model name: `qwen3-4b:strip_thinking_response=true:disable_thinking=true`

### Reasoning Models

Supported: `claude-opus-4-6`, `grok-41-fast`, `kimi-k2-5`, `gemini-3-pro-preview`, `qwen3-235b-a22b-thinking-2507`, `qwen3-4b`, `deepseek-ai-DeepSeek-R1`

Control via `reasoning_effort`: `low` | `medium` | `high`

### Prompt Caching

Automatic for most models (>10

Editorial read

Docs & README

Docs source

CLAWHUB

Editorial quality

ready

Full README

Skill: Venice AI

Owner: jonisjongithub

Summary: Complete Venice AI platform — text generation, web search, embeddings, TTS, speech-to-text, image generation, video creation, upscaling, and AI editing. Private, uncensored AI inference for everything.

Tags: latest:2.0.0

Version history:

v2.0.0 | 2026-02-07T19:25:39.635Z | user

🎉 Major update: Merged venice-ai-media into unified skill

New in v2.0.0:

Complete Venice platform in one skill (text, audio, images, video)
Added image generation (Flux, GPT-Image, etc.)
Added video creation (Sora, WAN, Runway)
Added image upscaling with AI enhancement
Added AI image editing
Backward compatible with existing venice-ai-media configs

One skill to unlock everything Venice has to offer!

v1.0.1 | 2026-02-07T06:21:13.865Z | user

Updated skill

v1.0.0 | 2026-02-03T22:50:52.393Z | auto

Venice AI 1.0.0 — Initial Release

Introduces the full Venice AI platform skill with private, uncensored AI inference.
Supports model discovery, text generation with web search/citations, embeddings, TTS, speech-to-text, and model comparison.
Compatible with 30+ models, including GPT-5.2 and Claude Opus 4.5; supports advanced features like character personas and reasoning control.
OpenAI-compatible API; easy setup using environment variables or Clawdbot config.
Includes a comprehensive CLI for all workflows with detailed usage instructions.

Archive index:

Archive v2.0.0: 9 files, 31743 bytes

Files: references/api.md (7106b), scripts/venice_common.py (7463b), scripts/venice-edit.py (6527b), scripts/venice-image.py (14862b), scripts/venice-upscale.py (9651b), scripts/venice-video.py (16858b), scripts/venice.py (22146b), SKILL.md (14084b), _meta.json (128b)

File v2.0.0:SKILL.md

name: venice-ai description: Complete Venice AI platform — text generation, web search, embeddings, TTS, speech-to-text, image generation, video creation, upscaling, and AI editing. Private, uncensored AI inference for everything. homepage: https://venice.ai metadata: { "clawdbot": { "emoji": "🏛️", "requires": { "bins": ["python3"], "env": ["VENICE_API_KEY"] }, "primaryEnv": "VENICE_API_KEY", "notes": "Full Venice AI platform — text, images, video, audio, embeddings. One skill for everything.", "install": [ { "id": "python-brew", "kind": "brew", "formula": "python", "bins": ["python3"], "label": "Install Python (brew)", }, ], }, }

Venice AI — Complete Platform Skill

What is Venice AI?

Venice AI is 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." The AI answers what you actually ask, whether that's creative fiction, security research, controversial topics, or anything else mainstream AI platforms won't touch.

Why agents should care:

Private inference — Models marked "Private" have zero data retention. Process sensitive data without it leaking into training sets.
Uncensored responses — No guardrails blocking legitimate use cases. Generate any content your workflow needs.
OpenAI-compatible API — Drop-in replacement. Same API format, just change the base URL.
30+ models — From tiny efficient models to Claude Opus 4.5, GPT-5.2, and Venice's own uncensored models.
Built-in web search — LLMs can search the web and cite sources in a single API call.
Image & video generation — Flux, Sora, Runway, WAN models for visual content.

This skill gives you the complete Venice platform: text generation, web search, embeddings, TTS, speech-to-text, image generation, video creation, upscaling, and AI editing.

⚠️ API changes: If something doesn't work as expected, check docs.venice.ai — the API specs may have been updated since this skill was written.

Prerequisites

Python 3.10+
Venice API key (free tier available at venice.ai/settings/api)

Setup

Get Your API Key

Create account at venice.ai
Go to venice.ai/settings/api
Click "Create API Key" → copy the key (starts with vn_...)

Configure

Option A: Environment variable

export VENICE_API_KEY="vn_your_key_here"

Option B: Clawdbot config (recommended)

// ~/.clawdbot/clawdbot.json
{
  skills: {
    entries: {
      "venice-ai": {
        env: { VENICE_API_KEY: "vn_your_key_here" }
      }
    }
  }
}

Verify

python3 {baseDir}/scripts/venice.py models --type text

Scripts Overview

| Script | Purpose | |--------|---------| | venice.py | Text generation, models, embeddings, TTS, transcription | | venice-image.py | Image generation (Flux, etc.) | | venice-video.py | Video generation (Sora, WAN, Runway) | | venice-upscale.py | Image upscaling | | venice-edit.py | AI image editing |

Part 1: Text & Audio

Model Discovery & Selection

Venice has a huge model catalog spanning text, image, video, audio, and embeddings.

Browse Models

# List all text models
python3 {baseDir}/scripts/venice.py models --type text

# List image models
python3 {baseDir}/scripts/venice.py models --type image

# List all model types
python3 {baseDir}/scripts/venice.py models --type text,image,video,audio,embedding

# Get details on a specific model
python3 {baseDir}/scripts/venice.py models --filter llama

Model Selection Guide

| Need | Recommended Model | Why | |------|------------------|-----| | Cheapest text | qwen3-4b ($0.05/M in) | Tiny, fast, efficient | | Best uncensored | venice-uncensored ($0.20/M in) | Venice's own uncensored model | | Best private + smart | deepseek-v3.2 ($0.40/M in) | Great reasoning, efficient | | Vision/multimodal | qwen3-vl-235b-a22b ($0.25/M in) | Sees images | | Best coding | qwen3-coder-480b-a35b-instruct ($0.75/M in) | Massive coder model | | Frontier (budget) | grok-41-fast ($0.50/M in) | Fast, 262K context | | Frontier (max quality) | claude-opus-4-6 ($6/M in) | Best overall quality | | Reasoning | kimi-k2-5 ($0.75/M in) | Strong chain-of-thought | | Web search | Any model + enable_web_search | Built-in web search |

Text Generation (Chat Completions)

Basic Generation

# Simple prompt
python3 {baseDir}/scripts/venice.py chat "What is the meaning of life?"

# Choose a model
python3 {baseDir}/scripts/venice.py chat "Explain quantum computing" --model deepseek-v3.2

# System prompt
python3 {baseDir}/scripts/venice.py chat "Review this code" --system "You are a senior engineer."

# Read from stdin
echo "Summarize this" | python3 {baseDir}/scripts/venice.py chat --model qwen3-4b

# Stream output
python3 {baseDir}/scripts/venice.py chat "Write a story" --stream

Web Search Integration

# Auto web search (model decides when to search)
python3 {baseDir}/scripts/venice.py chat "What happened in tech news today?" --web-search auto

# Force web search with citations
python3 {baseDir}/scripts/venice.py chat "Current Bitcoin price" --web-search on --web-citations

# Web scraping (extracts content from URLs in prompt)
python3 {baseDir}/scripts/venice.py chat "Summarize: https://example.com/article" --web-scrape

Uncensored Mode

# Use Venice's own uncensored model
python3 {baseDir}/scripts/venice.py chat "Your question" --model venice-uncensored

# Disable Venice system prompts for raw model output
python3 {baseDir}/scripts/venice.py chat "Your prompt" --no-venice-system-prompt

Reasoning Models

# Use a reasoning model with effort control
python3 {baseDir}/scripts/venice.py chat "Solve this math problem..." --model kimi-k2-5 --reasoning-effort high

# Strip thinking from output
python3 {baseDir}/scripts/venice.py chat "Debug this code" --model qwen3-4b --strip-thinking

Advanced Options

# Temperature and token control
python3 {baseDir}/scripts/venice.py chat "Be creative" --temperature 1.2 --max-tokens 4000

# JSON output mode
python3 {baseDir}/scripts/venice.py chat "List 5 colors as JSON" --json

# Prompt caching (for repeated context)
python3 {baseDir}/scripts/venice.py chat "Question" --cache-key my-session-123

# Show usage stats
python3 {baseDir}/scripts/venice.py chat "Hello" --show-usage

Embeddings

Generate vector embeddings for semantic search, RAG, and recommendations:

# Single text
python3 {baseDir}/scripts/venice.py embed "Venice is a private AI platform"

# Multiple texts (batch)
python3 {baseDir}/scripts/venice.py embed "first text" "second text" "third text"

# From file (one text per line)
python3 {baseDir}/scripts/venice.py embed --file texts.txt

# Output as JSON
python3 {baseDir}/scripts/venice.py embed "some text" --output json

Model: text-embedding-bge-m3 (private, $0.15/M tokens)

Text-to-Speech (TTS)

Convert text to speech with 60+ multilingual voices:

# Default voice
python3 {baseDir}/scripts/venice.py tts "Hello, welcome to Venice AI"

# Choose a voice
python3 {baseDir}/scripts/venice.py tts "Exciting news!" --voice af_nova

# List available voices
python3 {baseDir}/scripts/venice.py tts --list-voices

# Custom output path
python3 {baseDir}/scripts/venice.py tts "Some text" --output /tmp/speech.mp3

# Adjust speed
python3 {baseDir}/scripts/venice.py tts "Speaking slowly" --speed 0.8

Popular voices: af_sky, af_nova, am_liam, bf_emma, zf_xiaobei (Chinese), jm_kumo (Japanese)

Model: tts-kokoro (private, $3.50/M characters)

Speech-to-Text (Transcription)

Transcribe audio files to text:

# Transcribe a file
python3 {baseDir}/scripts/venice.py transcribe audio.wav

# With timestamps
python3 {baseDir}/scripts/venice.py transcribe recording.mp3 --timestamps

# From URL
python3 {baseDir}/scripts/venice.py transcribe --url https://example.com/audio.wav

Supported formats: WAV, FLAC, MP3, M4A, AAC, MP4

Model: nvidia/parakeet-tdt-0.6b-v3 (private, $0.0001/audio second)

Check Balance

python3 {baseDir}/scripts/venice.py balance

Part 2: Images & Video

Pricing Overview

| Feature | Cost | |---------|------| | Image generation | ~$0.01-0.03 per image | | Image upscale | ~$0.02-0.04 | | Image edit | $0.04 | | Video (WAN) | ~$0.10-0.50 | | Video (Sora) | ~$0.50-2.00 | | Video (Runway) | ~$0.20-1.00 |

Use --quote with video commands to check pricing before generation.

Image Generation

# Basic generation
python3 {baseDir}/scripts/venice-image.py --prompt "a serene canal in Venice at sunset"

# Multiple images
python3 {baseDir}/scripts/venice-image.py --prompt "cyberpunk city" --count 4

# Custom dimensions
python3 {baseDir}/scripts/venice-image.py --prompt "portrait" --width 768 --height 1024

# List available models and styles
python3 {baseDir}/scripts/venice-image.py --list-models
python3 {baseDir}/scripts/venice-image.py --list-styles

# Use specific model and style
python3 {baseDir}/scripts/venice-image.py --prompt "fantasy" --model flux-2-pro --style-preset "Cinematic"

# Reproducible results with seed
python3 {baseDir}/scripts/venice-image.py --prompt "abstract" --seed 12345

Key flags: --prompt, --model (default: flux-2-max), --count, --width, --height, --format (webp/png/jpeg), --resolution (1K/2K/4K), --aspect-ratio, --negative-prompt, --style-preset, --cfg-scale (0-20), --seed, --safe-mode, --hide-watermark, --embed-exif

Image Upscale

# 2x upscale
python3 {baseDir}/scripts/venice-upscale.py photo.jpg --scale 2

# 4x with AI enhancement
python3 {baseDir}/scripts/venice-upscale.py photo.jpg --scale 4 --enhance

# Enhanced with custom prompt
python3 {baseDir}/scripts/venice-upscale.py photo.jpg --enhance --enhance-prompt "sharpen details"

# From URL
python3 {baseDir}/scripts/venice-upscale.py --url "https://example.com/image.jpg" --scale 2

Key flags: --scale (1-4, default: 2), --enhance (AI enhancement), --enhance-prompt, --enhance-creativity (0.0-1.0), --url, --output

Image Edit

AI-powered image editing:

# Add elements
python3 {baseDir}/scripts/venice-edit.py photo.jpg --prompt "add sunglasses"

# Modify scene
python3 {baseDir}/scripts/venice-edit.py photo.jpg --prompt "change the sky to sunset"

# Remove objects
python3 {baseDir}/scripts/venice-edit.py photo.jpg --prompt "remove the person in background"

# From URL
python3 {baseDir}/scripts/venice-edit.py --url "https://example.com/image.jpg" --prompt "colorize"

Note: The edit endpoint uses Qwen-Image which has some content restrictions.

Video Generation

# Get price quote first
python3 {baseDir}/scripts/venice-video.py --quote --model wan-2.6-image-to-video --duration 10s

# Image-to-video (WAN - default)
python3 {baseDir}/scripts/venice-video.py --image photo.jpg --prompt "camera pans slowly" --duration 10s

# Image-to-video (Sora)
python3 {baseDir}/scripts/venice-video.py --image photo.jpg --prompt "cinematic" \
  --model sora-2-image-to-video --duration 8s --aspect-ratio 16:9 --skip-audio-param

# Video-to-video (Runway Gen4)
python3 {baseDir}/scripts/venice-video.py --video input.mp4 --prompt "anime style" \
  --model runway-gen4-turbo-v2v

# List models with available durations
python3 {baseDir}/scripts/venice-video.py --list-models

Key flags: --image or --video, --prompt, --model (default: wan-2.6-image-to-video), --duration, --resolution (480p/720p/1080p), --aspect-ratio, --audio/--no-audio, --quote, --timeout

Models:

WAN — Image-to-video, configurable audio, 5s-21s
Sora — Requires --aspect-ratio, use --skip-audio-param
Runway — Video-to-video transformation

Tips & Ideas

🔍 Web Search + LLM = Research Assistant

Use --web-search on --web-citations to build a research workflow. Venice searches the web, synthesizes results, and cites sources — all in one API call.

🔓 Uncensored Creative Content

Venice's uncensored models work for both text AND images. No guardrails blocking legitimate creative use cases.

🎯 Prompt Caching for Agents

If you're running an agent loop that sends the same system prompt repeatedly, use --cache-key to get up to 90% cost savings.

🎤 Audio Pipeline

Combine TTS and transcription: generate spoken content with tts, process audio with transcribe. Both are private inference.

🎬 Video Workflow

Generate or find a base image
Use --quote to estimate video cost
Generate with appropriate duration/model
Videos take 1-5 minutes depending on settings

Troubleshooting

| Problem | Solution | |---------|----------| | VENICE_API_KEY not set | Set env var or configure in ~/.clawdbot/clawdbot.json | | Invalid API key | Verify at venice.ai/settings/api | | Model not found | Run --list-models to see available; use --no-validate for new models | | Rate limited | Check --show-usage output | | Video stuck | Videos can take 1-5 min; use --timeout 600 for long ones |

Resources

API Docs: docs.venice.ai
Status: veniceai-status.com
Discord: discord.gg/askvenice

File v2.0.0:_meta.json

{ "ownerId": "kn7eeaajfmabdgahexes49syrn80f3b9", "slug": "venice-ai", "version": "2.0.0", "publishedAt": 1770492339635 }

File v2.0.0:references/api.md

Venice AI API Reference

Base URL: https://api.venice.ai/api/v1

Authentication: All requests require Authorization: Bearer <VENICE_API_KEY>

Venice implements the OpenAI API specification — any OpenAI-compatible client works by changing the base URL.

Chat Completions

Create Chat Completion

POST /chat/completions

Request Body:

{
  "model": "deepseek-v3.2",
  "messages": [
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "Hello!"}
  ],
  "temperature": 0.7,
  "max_tokens": 4096,
  "stream": false,
  "response_format": {"type": "json_object"},
  "reasoning_effort": "medium",
  "prompt_cache_key": "session-123",
  "venice_parameters": {
    "enable_web_search": "auto",
    "enable_web_citations": true,
    "enable_web_scraping": false,
    "include_venice_system_prompt": true,
    "character_slug": "coder-dan",
    "strip_thinking_response": false,
    "disable_thinking": false,
    "include_search_results_in_stream": false,
    "return_search_results_as_documents": false
  }
}

Venice Parameters (unique to Venice):

| Parameter | Type | Default | Description | |-----------|------|---------|-------------| | enable_web_search | "off"/"on"/"auto" | "off" | LLM-integrated web search. "auto" lets the model decide. | | enable_web_citations | bool | false | Request [REF]0[/REF] citation format in responses | | enable_web_scraping | bool | false | Scrape URLs found in user messages to augment context | | include_venice_system_prompt | bool | true | Include Venice's default uncensored system prompt | | character_slug | string | — | Use a Venice public character persona | | strip_thinking_response | bool | false | Strip <think> tags server-side | | disable_thinking | bool | false | Disable reasoning entirely | | include_search_results_in_stream | bool | false | Emit search results as first SSE chunk | | return_search_results_as_documents | bool | false | Return search results as OpenAI-compatible tool call |

Response:

{
  "id": "chatcmpl-...",
  "object": "chat.completion",
  "model": "deepseek-v3.2",
  "choices": [{
    "index": 0,
    "message": {
      "role": "assistant",
      "content": "Hello! How can I help?",
      "reasoning_content": "The user said hello..."
    },
    "finish_reason": "stop"
  }],
  "usage": {
    "prompt_tokens": 15,
    "completion_tokens": 8,
    "total_tokens": 23,
    "prompt_tokens_details": {
      "cached_tokens": 0,
      "cache_creation_input_tokens": 0
    }
  }
}

Model Feature Suffixes: Append parameters to model name: qwen3-4b:strip_thinking_response=true:disable_thinking=true

Reasoning Models

Supported: claude-opus-4-6, grok-41-fast, kimi-k2-5, gemini-3-pro-preview, qwen3-235b-a22b-thinking-2507, qwen3-4b, deepseek-ai-DeepSeek-R1

Control via reasoning_effort: low | medium | high

Prompt Caching

Automatic for most models (>1024 tokens). Use prompt_cache_key for routing affinity. Claude requires explicit cache_control: {"type": "ephemeral"} markers.

| Model | Min Tokens | Cache Life | Read Discount | |-------|-----------|------------|---------------| | Claude Opus 4.6 | ~4,000 | 5 min | 90% | | GPT-5.2 | 1,024 | 5-10 min | 90% | | Gemini | ~1,024 | 1 hour | 75-90% | | DeepSeek | ~1,024 | 5 min | 50% |

Models

List Models

GET /models?type={text|image|video|audio|embedding}

Response:

{
  "data": [{
    "id": "deepseek-v3.2",
    "type": "text",
    "model_spec": {
      "description": "DeepSeek V3.2",
      "offline": false,
      "beta": false,
      "availableForPrivateInference": true,
      "deprecation": {"date": null},
      "constraints": {
        "max_context_length": 164000
      }
    }
  }]
}

Embeddings

Generate Embeddings

POST /embeddings

Request:

{
  "model": "text-embedding-bge-m3",
  "input": "Your text here"
}

Or batch: "input": ["text1", "text2", "text3"]

Response:

{
  "data": [{
    "index": 0,
    "embedding": [0.123, -0.456, ...],
    "object": "embedding"
  }],
  "usage": {"prompt_tokens": 5, "total_tokens": 5}
}

Audio

Text-to-Speech

POST /audio/speech

Request:

{
  "model": "tts-kokoro",
  "input": "Hello world",
  "voice": "af_sky",
  "speed": 1.0
}

Response: Audio bytes (MP3). Content-Type: audio/mpeg

Available voices (60+):

English US: af_sky, af_nova, af_bella, am_adam, am_liam
English UK: bf_emma, bf_isabella, bm_daniel, bm_george
Chinese: zf_xiaobei, zf_xiaoni, zm_yunjian
Japanese: jf_alpha, jm_kumo
And many more (French, Hindi, Italian, Portuguese, Spanish)

Prefix: a=American, b=British, z=Chinese, j=Japanese; f=female, m=male

Speech-to-Text (Transcription)

POST /audio/transcriptions

Request: Multipart form data

file: Audio file (WAV, FLAC, MP3, M4A, AAC, MP4)
model: nvidia/parakeet-tdt-0.6b-v3
timestamps: true (optional, word-level timing)

Response:

{
  "text": "Transcribed text here..."
}

Images

Generate Image

POST /images/generations

Edit Image

POST /images/edits

Upscale Image

POST /images/upscale

See venice-image.py, venice-upscale.py, and venice-edit.py in the scripts folder for CLI usage.

Video

Generate Video

POST /video/generate

Get Video Quote

POST /video/generate/quote

See venice-video.py in the scripts folder for CLI usage.

Response Headers

All authenticated requests include useful headers:

| Header | Description | |--------|-------------| | x-venice-balance-usd | USD credit balance | | x-venice-balance-diem | DIEM token balance | | x-venice-balance-vcu | Venice Compute Units | | x-venice-model-id | Model used for inference | | x-ratelimit-remaining-requests | Remaining request quota | | x-ratelimit-remaining-tokens | Remaining token quota | | CF-RAY | Request ID (for support) |

Pricing Quick Reference

Text (per 1M tokens)

| Model | Input | Output | Privacy | |-------|-------|--------|---------| | qwen3-4b | $0.05 | $0.15 | Private | | venice-uncensored | $0.20 | $0.90 | Private | | deepseek-v3.2 | $0.40 | $1.00 | Private | | mistral-31-24b | $0.50 | $2.00 | Private | | llama-3.3-70b | $0.70 | $2.80 | Private | | grok-41-fast | $0.50 | $1.25 | Anonymized | | openai-gpt-52 | $2.19 | $17.50 | Anonymized | | claude-opus-4-6 | $6.00 | $30.00 | Anonymized |

Other

| Feature | Cost | |---------|------| | Embeddings (BGE-M3) | $0.15/M tokens input | | TTS (Kokoro) | $3.50/M characters | | Speech-to-Text (Parakeet) | $0.0001/audio second | | Web Search | $10/1K calls | | Web Scraping | $10/1K calls | | Images | $0.01-$0.23/image | | Video | Variable (use quote API) |

Resources

Docs: https://docs.venice.ai
Status: https://veniceai-status.com
Discord: https://discord.gg/askvenice
Twitter: https://x.com/AskVenice

Archive v1.0.1: 4 files, 15060 bytes

Files: references/api.md (7105b), scripts/venice.py (22146b), SKILL.md (12623b), _meta.json (128b)

File v1.0.1:SKILL.md

name: venice-ai description: Full-platform Venice AI skill — model discovery, text generation with web search, embeddings, TTS, speech-to-text, and model comparison. Private, uncensored AI inference. Use when you need to generate text with specific models, search the web through an LLM, transcribe audio, create embeddings, or explore what models are available. homepage: https://venice.ai metadata: { "clawdbot": { "emoji": "🏛️", "requires": { "bins": ["python3"], "env": ["VENICE_API_KEY"] }, "primaryEnv": "VENICE_API_KEY", "notes": "Full Venice AI platform access. For image/video generation, see venice-ai-media skill.", "install": [ { "id": "python-brew", "kind": "brew", "formula": "python", "bins": ["python3"], "label": "Install Python (brew)", }, ], }, }

Venice AI — Full Platform Skill

What is Venice AI?

Why agents should care:

Private inference — Models marked "Private" have zero data retention. Process sensitive data without it leaking into training sets.
Uncensored responses — No guardrails blocking legitimate use cases. Generate any content your workflow needs.
OpenAI-compatible API — Drop-in replacement. Same API format, just change the base URL.
30+ models — From tiny efficient models to Claude Opus 4.5, GPT-5.2, and Venice's own uncensored models.
Built-in web search — LLMs can search the web and cite sources in a single API call.

This skill gives you the full Venice platform: model discovery, text generation with Venice-specific superpowers (web search, uncensored mode, character personas, reasoning control), embeddings, TTS, speech-to-text, and intelligent model selection.

For image & video generation, use the companion venice-ai-media skill which has dedicated tools for those workflows.

⚠️ API changes: If something doesn't work as expected, check docs.venice.ai — the API specs may have been updated since this skill was written.

Prerequisites

Python 3.10+
Venice API key (free tier available at venice.ai/settings/api)

Setup

Get Your API Key

Create account at venice.ai
Go to venice.ai/settings/api
Click "Create API Key" → copy the key (starts with vn_...)

Configure

Option A: Environment variable

export VENICE_API_KEY="vn_your_key_here"

Option B: Clawdbot config (recommended)

// ~/.clawdbot/clawdbot.json
{
  skills: {
    entries: {
      "venice-ai": {
        env: { VENICE_API_KEY: "vn_your_key_here" }
      }
    }
  }
}

Verify

python3 {baseDir}/scripts/venice.py models --type text

Scripts

All operations go through a single CLI tool:

python3 {baseDir}/scripts/venice.py [command] [options]

Model Discovery & Selection

Venice has a huge model catalog spanning text, image, video, audio, and embeddings. The right model for a task depends on your needs: cost, speed, privacy, context length, and capabilities.

Browse Models

# List all text models
python3 {baseDir}/scripts/venice.py models --type text

# List image models
python3 {baseDir}/scripts/venice.py models --type image

# List all model types
python3 {baseDir}/scripts/venice.py models --type text,image,video,audio,embedding

# Get details on a specific model
python3 {baseDir}/scripts/venice.py models --filter llama

Model Selection Guide

| Need | Recommended Model | Why | |------|------------------|-----| | Cheapest text | qwen3-4b ($0.05/M in) | Tiny, fast, efficient | | Best uncensored | venice-uncensored ($0.20/M in) | Venice's own uncensored model | | Best private + smart | deepseek-v3.2 ($0.40/M in) | Great reasoning, efficient | | Vision/multimodal | qwen3-vl-235b-a22b ($0.25/M in) | Sees images | | Best coding | qwen3-coder-480b-a35b-instruct ($0.75/M in) | Massive coder model | | Frontier (budget) | grok-41-fast ($0.50/M in) | Fast, 262K context | | Frontier (max quality) | claude-opus-4-6 ($6/M in) | Best overall quality (latest Opus) | | Reasoning | kimi-k2-5 ($0.75/M in) | Strong chain-of-thought (K2.5) | | Web search | Any model + enable_web_search | Built-in web search |

Privacy tiers: "Private" = zero data retention. "Anonymized" = logs stripped of identity but may be retained.

Text Generation (Chat Completions)

Venice implements the OpenAI chat completions API with extra superpowers.

Basic Generation

# Simple prompt
python3 {baseDir}/scripts/venice.py chat "What is the meaning of life?"

# Choose a model
python3 {baseDir}/scripts/venice.py chat "Explain quantum computing" --model deepseek-v3.2

# System prompt
python3 {baseDir}/scripts/venice.py chat "Review this code" --system "You are a senior engineer. Be direct and critical."

# Read from stdin (pipe content in)
echo "Summarize this" | python3 {baseDir}/scripts/venice.py chat --model qwen3-4b

# Stream output
python3 {baseDir}/scripts/venice.py chat "Write a story" --stream

Web Search Integration

Venice can search the web before answering — no external tools needed:

# Auto web search (model decides when to search)
python3 {baseDir}/scripts/venice.py chat "What happened in tech news today?" --web-search auto

# Force web search
python3 {baseDir}/scripts/venice.py chat "Current Bitcoin price" --web-search on

# Web search with citations
python3 {baseDir}/scripts/venice.py chat "Latest AI research papers" --web-search on --web-citations

# Web scraping (extracts content from URLs in prompt)
python3 {baseDir}/scripts/venice.py chat "Summarize this article: https://example.com/article" --web-scrape

Uncensored Mode

# Use Venice's own uncensored model
python3 {baseDir}/scripts/venice.py chat "Your uncensored question" --model venice-uncensored

# Disable Venice system prompts for raw model output
python3 {baseDir}/scripts/venice.py chat "Your prompt" --no-venice-system-prompt

Reasoning Models

# Use a reasoning model with effort control
python3 {baseDir}/scripts/venice.py chat "Solve this math problem..." --model kimi-k2-5 --reasoning-effort high

# Strip thinking from output
python3 {baseDir}/scripts/venice.py chat "Debug this code" --model qwen3-4b --strip-thinking

# Disable thinking entirely (faster, cheaper)
python3 {baseDir}/scripts/venice.py chat "Simple question" --model qwen3-4b --disable-thinking

Character Personas

Venice has public character personas that customize model behavior:

# Use a Venice character
python3 {baseDir}/scripts/venice.py chat "Tell me a story" --character coder-dan

Advanced Options

# Temperature and token control
python3 {baseDir}/scripts/venice.py chat "Be creative" --temperature 1.2 --max-tokens 4000

# JSON output mode
python3 {baseDir}/scripts/venice.py chat "List 5 colors as JSON" --json

# Prompt caching (for multi-turn or repeated context)
python3 {baseDir}/scripts/venice.py chat "Question about the doc" --cache-key my-session-123

# Show usage stats (tokens, cost, cache hits)
python3 {baseDir}/scripts/venice.py chat "Hello" --show-usage

Embeddings

Generate vector embeddings for semantic search, RAG, and recommendations:

# Single text
python3 {baseDir}/scripts/venice.py embed "Venice is a private AI platform"

# Multiple texts (batch)
python3 {baseDir}/scripts/venice.py embed "first text" "second text" "third text"

# From file (one text per line)
python3 {baseDir}/scripts/venice.py embed --file texts.txt

# Output as JSON
python3 {baseDir}/scripts/venice.py embed "some text" --output json

Model: text-embedding-bge-m3 (private, $0.15/M tokens input)

Text-to-Speech (TTS)

Convert text to speech with 60+ multilingual voices:

# Default voice
python3 {baseDir}/scripts/venice.py tts "Hello, welcome to Venice AI"

# Choose a voice
python3 {baseDir}/scripts/venice.py tts "Exciting news!" --voice af_nova

# List available voices
python3 {baseDir}/scripts/venice.py tts --list-voices

# Custom output path
python3 {baseDir}/scripts/venice.py tts "Some text" --output /tmp/speech.mp3

# Adjust speed
python3 {baseDir}/scripts/venice.py tts "Speaking slowly" --speed 0.8

Popular voices: af_sky, af_nova, am_liam, bf_emma, zf_xiaobei (Chinese), jm_kumo (Japanese)

Model: tts-kokoro (private, $3.50/M characters)

Speech-to-Text (Transcription)

Transcribe audio files to text:

# Transcribe a file
python3 {baseDir}/scripts/venice.py transcribe audio.wav

# With timestamps
python3 {baseDir}/scripts/venice.py transcribe recording.mp3 --timestamps

# From URL
python3 {baseDir}/scripts/venice.py transcribe --url https://example.com/audio.wav

Supported formats: WAV, FLAC, MP3, M4A, AAC, MP4

Model: nvidia/parakeet-tdt-0.6b-v3 (private, $0.0001/audio second — essentially free)

Check Balance

python3 {baseDir}/scripts/venice.py balance

Shows your Diem, USD, and VCU balances.

Tips & Ideas to Try

🔍 Web Search + LLM = Research Assistant

Use --web-search on --web-citations to build a research workflow. Venice searches the web, synthesizes results, and cites sources — all in one API call. Try different models to see which gives the best summaries.

🔓 Uncensored Creative Writing

Venice's uncensored models don't have the guardrails that restrict other AI platforms. Great for fiction, roleplay scenarios, security research, or any topic other AIs refuse to engage with.

🧠 Model A/B Testing

Not sure which model is best for your task? Use the chat command with different --model flags and compare. Smaller models are surprisingly capable and much cheaper.

🔒 Privacy-First Workflows

If you're processing sensitive data, stick to "Private" models (shown in models output). Zero data retention means your prompts literally can't leak.

🎯 Prompt Caching for Agents

If you're running an agent loop that sends the same system prompt repeatedly, use --cache-key to get up to 90% cost savings on the cached portion.

🎤 Audio Pipeline

Combine TTS and transcription for audio workflows: generate spoken content with tts, process audio with transcribe. Both are private inference.

💡 Share What You Build

Created something cool with Venice? The community at discord.gg/askvenice loves seeing creative uses. Venice's Twitter @AskVenice also showcases community projects.

Model Feature Suffixes

Venice supports inline model configuration via suffixes — append parameters directly to the model name:

model_name:param1=value1:param2=value2

Examples:

# Strip thinking tags server-side
--model "qwen3-4b:strip_thinking_response=true"

# Disable thinking entirely
--model "qwen3-4b:disable_thinking=true"

Useful when you can't pass venice_parameters directly (e.g., through OpenAI-compatible clients).

Troubleshooting

| Problem | Solution | |---------|----------| | VENICE_API_KEY not set | Set env var or configure in ~/.clawdbot/clawdbot.json | | Invalid API key | Verify at venice.ai/settings/api — keys start with vn_ | | Model not found | Run models --type text to see available models | | Rate limited | Check --show-usage output for rate limit info | | Slow responses | Try a smaller/faster model, or reduce --max-tokens |

Resources

API Docs: docs.venice.ai
Status: veniceai-status.com
Discord: discord.gg/askvenice
Full API reference: See references/api.md in this skill

File v1.0.1:_meta.json

{ "ownerId": "kn7eeaajfmabdgahexes49syrn80f3b9", "slug": "venice-ai", "version": "1.0.1", "publishedAt": 1770445273865 }

File v1.0.1:references/api.md

Venice AI API Reference

Base URL: https://api.venice.ai/api/v1

Authentication: All requests require Authorization: Bearer <VENICE_API_KEY>

Venice implements the OpenAI API specification — any OpenAI-compatible client works by changing the base URL.

Chat Completions

Create Chat Completion

POST /chat/completions

Request Body:

{
  "model": "deepseek-v3.2",
  "messages": [
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "Hello!"}
  ],
  "temperature": 0.7,
  "max_tokens": 4096,
  "stream": false,
  "response_format": {"type": "json_object"},
  "reasoning_effort": "medium",
  "prompt_cache_key": "session-123",
  "venice_parameters": {
    "enable_web_search": "auto",
    "enable_web_citations": true,
    "enable_web_scraping": false,
    "include_venice_system_prompt": true,
    "character_slug": "coder-dan",
    "strip_thinking_response": false,
    "disable_thinking": false,
    "include_search_results_in_stream": false,
    "return_search_results_as_documents": false
  }
}

Venice Parameters (unique to Venice):

Response:

{
  "id": "chatcmpl-...",
  "object": "chat.completion",
  "model": "deepseek-v3.2",
  "choices": [{
    "index": 0,
    "message": {
      "role": "assistant",
      "content": "Hello! How can I help?",
      "reasoning_content": "The user said hello..."
    },
    "finish_reason": "stop"
  }],
  "usage": {
    "prompt_tokens": 15,
    "completion_tokens": 8,
    "total_tokens": 23,
    "prompt_tokens_details": {
      "cached_tokens": 0,
      "cache_creation_input_tokens": 0
    }
  }
}

Model Feature Suffixes: Append parameters to model name: qwen3-4b:strip_thinking_response=true:disable_thinking=true

Reasoning Models

Supported: claude-opus-4-6, grok-41-fast, kimi-k2-5, gemini-3-pro-preview, qwen3-235b-a22b-thinking-2507, qwen3-4b, deepseek-ai-DeepSeek-R1

Control via reasoning_effort: low | medium | high

Prompt Caching

Automatic for most models (>1024 tokens). Use prompt_cache_key for routing affinity. Claude requires explicit cache_control: {"type": "ephemeral"} markers.

Models

List Models

GET /models?type={text|image|video|audio|embedding}

Response:

{
  "data": [{
    "id": "deepseek-v3.2",
    "type": "text",
    "model_spec": {
      "description": "DeepSeek V3.2",
      "offline": false,
      "beta": false,
      "availableForPrivateInference": true,
      "deprecation": {"date": null},
      "constraints": {
        "max_context_length": 164000
      }
    }
  }]
}

Embeddings

Generate Embeddings

POST /embeddings

Request:

{
  "model": "text-embedding-bge-m3",
  "input": "Your text here"
}

Or batch: "input": ["text1", "text2", "text3"]

Response:

{
  "data": [{
    "index": 0,
    "embedding": [0.123, -0.456, ...],
    "object": "embedding"
  }],
  "usage": {"prompt_tokens": 5, "total_tokens": 5}
}

Audio

Text-to-Speech

POST /audio/speech

Request:

{
  "model": "tts-kokoro",
  "input": "Hello world",
  "voice": "af_sky",
  "speed": 1.0
}

Response: Audio bytes (MP3). Content-Type: audio/mpeg

Available voices (60+):

English US: af_sky, af_nova, af_bella, am_adam, am_liam
English UK: bf_emma, bf_isabella, bm_daniel, bm_george
Chinese: zf_xiaobei, zf_xiaoni, zm_yunjian
Japanese: jf_alpha, jm_kumo
And many more (French, Hindi, Italian, Portuguese, Spanish)

Prefix: a=American, b=British, z=Chinese, j=Japanese; f=female, m=male

Speech-to-Text (Transcription)

POST /audio/transcriptions

Request: Multipart form data

file: Audio file (WAV, FLAC, MP3, M4A, AAC, MP4)
model: nvidia/parakeet-tdt-0.6b-v3
timestamps: true (optional, word-level timing)

Response:

{
  "text": "Transcribed text here..."
}

Images

Generate Image

POST /images/generations

Edit Image

POST /images/edits

Upscale Image

POST /images/upscale

For detailed image/video API usage, see the venice-ai-media skill which has dedicated scripts.

Video

Generate Video

POST /video/generate

Get Video Quote

POST /video/generate/quote

For detailed video API usage, see the venice-ai-media skill.

Response Headers

All authenticated requests include useful headers:

Pricing Quick Reference

Text (per 1M tokens)

Other

Resources

Docs: https://docs.venice.ai
Status: https://veniceai-status.com
Discord: https://discord.gg/askvenice
Twitter: https://x.com/AskVenice

API & Reliability

Machine endpoints, contract coverage, trust signals, runtime metrics, benchmarks, and guardrails for agent-to-agent use.

MissingCLAWHUB

Machine interfaces

Contract & API

Endpoints

Dossier API Snapshot API Contract API Trust API

Contract coverage

Status

missing

Auth

None

Streaming

Data region

Unspecified

Protocol support

OpenClaw: self-declared

Requires: none

Forbidden: none

Guardrails

Operational confidence: low

No positive guardrails captured.

Invocation examples

curl -s "https://xpersona.co/api/v1/agents/clawhub-jonisjongithub-venice-ai/snapshot"

curl -s "https://xpersona.co/api/v1/agents/clawhub-jonisjongithub-venice-ai/contract"

curl -s "https://xpersona.co/api/v1/agents/clawhub-jonisjongithub-venice-ai/trust"

Operational fit

Reliability & Benchmarks

Trust signals

Handshake

UNKNOWN

Confidence

unknown

Attempts 30d

unknown

Fallback rate

unknown

Runtime metrics

Observed P50

unknown

Observed P95

unknown

Rate limit

unknown

Estimated cost

unknown

Do not use if

Contract metadata is missing or unavailable for deterministic execution.

No benchmark suites or observed failure patterns are available.

Machine Appendix

Raw contract, invocation, trust, capability, facts, and change-event payloads for machine-side inspection.

MissingCLAWHUB

Contract JSON

{
  "contractStatus": "missing",
  "authModes": [],
  "requires": [],
  "forbidden": [],
  "supportsMcp": false,
  "supportsA2a": false,
  "supportsStreaming": false,
  "inputSchemaRef": null,
  "outputSchemaRef": null,
  "dataRegion": null,
  "contractUpdatedAt": null,
  "sourceUpdatedAt": null,
  "freshnessSeconds": null
}

Invocation Guide

{
  "preferredApi": {
    "snapshotUrl": "https://xpersona.co/api/v1/agents/clawhub-jonisjongithub-venice-ai/snapshot",
    "contractUrl": "https://xpersona.co/api/v1/agents/clawhub-jonisjongithub-venice-ai/contract",
    "trustUrl": "https://xpersona.co/api/v1/agents/clawhub-jonisjongithub-venice-ai/trust"
  },
  "curlExamples": [
    "curl -s \"https://xpersona.co/api/v1/agents/clawhub-jonisjongithub-venice-ai/snapshot\"",
    "curl -s \"https://xpersona.co/api/v1/agents/clawhub-jonisjongithub-venice-ai/contract\"",
    "curl -s \"https://xpersona.co/api/v1/agents/clawhub-jonisjongithub-venice-ai/trust\""
  ],
  "jsonRequestTemplate": {
    "query": "summarize this repo",
    "constraints": {
      "maxLatencyMs": 2000,
      "protocolPreference": [
        "OPENCLEW"
      ]
    }
  },
  "jsonResponseTemplate": {
    "ok": true,
    "result": {
      "summary": "...",
      "confidence": 0.9
    },
    "meta": {
      "source": "CLAWHUB",
      "generatedAt": "2026-04-17T03:17:57.320Z"
    }
  },
  "retryPolicy": {
    "maxAttempts": 3,
    "backoffMs": [
      500,
      1500,
      3500
    ],
    "retryableConditions": [
      "HTTP_429",
      "HTTP_503",
      "NETWORK_TIMEOUT"
    ]
  }
}

Trust JSON

{
  "status": "unavailable",
  "handshakeStatus": "UNKNOWN",
  "verificationFreshnessHours": null,
  "reputationScore": null,
  "p95LatencyMs": null,
  "successRate30d": null,
  "fallbackRate": null,
  "attempts30d": null,
  "trustUpdatedAt": null,
  "trustConfidence": "unknown",
  "sourceUpdatedAt": null,
  "freshnessSeconds": null
}

Capability Matrix

{
  "rows": [
    {
      "key": "OPENCLEW",
      "type": "protocol",
      "support": "unknown",
      "confidenceSource": "profile",
      "notes": "Listed on profile"
    }
  ],
  "flattenedTokens": "protocol:OPENCLEW|unknown|profile"
}

Facts JSON

[
  {
    "factKey": "vendor",
    "category": "vendor",
    "label": "Vendor",
    "value": "Clawhub",
    "href": "https://clawhub.ai/jonisjongithub/venice-ai",
    "sourceUrl": "https://clawhub.ai/jonisjongithub/venice-ai",
    "sourceType": "profile",
    "confidence": "medium",
    "observedAt": "2026-04-15T00:45:39.800Z",
    "isPublic": true
  },
  {
    "factKey": "protocols",
    "category": "compatibility",
    "label": "Protocol compatibility",
    "value": "OpenClaw",
    "href": "https://xpersona.co/api/v1/agents/clawhub-jonisjongithub-venice-ai/contract",
    "sourceUrl": "https://xpersona.co/api/v1/agents/clawhub-jonisjongithub-venice-ai/contract",
    "sourceType": "contract",
    "confidence": "medium",
    "observedAt": "2026-04-15T00:45:39.800Z",
    "isPublic": true
  },
  {
    "factKey": "traction",
    "category": "adoption",
    "label": "Adoption signal",
    "value": "2K downloads",
    "href": "https://clawhub.ai/jonisjongithub/venice-ai",
    "sourceUrl": "https://clawhub.ai/jonisjongithub/venice-ai",
    "sourceType": "profile",
    "confidence": "medium",
    "observedAt": "2026-04-15T00:45:39.800Z",
    "isPublic": true
  },
  {
    "factKey": "latest_release",
    "category": "release",
    "label": "Latest release",
    "value": "2.0.0",
    "href": "https://clawhub.ai/jonisjongithub/venice-ai",
    "sourceUrl": "https://clawhub.ai/jonisjongithub/venice-ai",
    "sourceType": "release",
    "confidence": "medium",
    "observedAt": "2026-02-07T19:25:39.635Z",
    "isPublic": true
  },
  {
    "factKey": "handshake_status",
    "category": "security",
    "label": "Handshake status",
    "value": "UNKNOWN",
    "href": "https://xpersona.co/api/v1/agents/clawhub-jonisjongithub-venice-ai/trust",
    "sourceUrl": "https://xpersona.co/api/v1/agents/clawhub-jonisjongithub-venice-ai/trust",
    "sourceType": "trust",
    "confidence": "medium",
    "observedAt": null,
    "isPublic": true
  }
]

Change Events JSON

[
  {
    "eventType": "release",
    "title": "Release 2.0.0",
    "description": "🎉 Major update: Merged venice-ai-media into unified skill **New in v2.0.0:** - Complete Venice platform in one skill (text, audio, images, video) - Added image generation (Flux, GPT-Image, etc.) - Added video creation (Sora, WAN, Runway) - Added image upscaling with AI enhancement - Added AI image editing - Backward compatible with existing venice-ai-media configs One skill to unlock everything Venice has to offer!",
    "href": "https://clawhub.ai/jonisjongithub/venice-ai",
    "sourceUrl": "https://clawhub.ai/jonisjongithub/venice-ai",
    "sourceType": "release",
    "confidence": "medium",
    "observedAt": "2026-02-07T19:25:39.635Z",
    "isPublic": true
  }
]