Venice API

Venice is a privacy-first, uncensored AI API platform offering text generation, image generation, audio synthesis, video generation, music, embeddings, and developer tools (web search, document parsing, blockchain RPC) with zero data retention and OpenAI SDK compatibility.

Venice provides permissionless access to AI models with no content filtering, making it ideal for developers building applications that require uncensored outputs, privacy guarantees, and full control over AI interactions. The API is fully compatible with OpenAI's SDK—just change the base URL to https://api.venice.ai/api/v1. Venice also offers developer tools including web search, web scraping, document parsing, and blockchain RPC—see the Tools section below.

Venice offers four tiers of privacy: Anonymized (third-party models with identifying metadata stripped), Private (zero data retention, self-hosted open-source models), TEE (models running inside hardware-secured enclaves—Venice cannot access the computation), and E2EE (end-to-end encrypted models where prompts are encrypted client-side before being sent, and only the TEE can decrypt them).

Getting Started

• Quick Start Guide: Get your API key and make your first request in minutes
• API Key Generation: Step-by-step guide to creating API keys
• About Venice: Overview of Venice's capabilities and OpenAI compatibility

API Reference

Text & Chat

• API Specification: Complete API specification with Venice-specific parameters
• Chat Completions: Text generation endpoint with streaming, vision, audio input, video input, and tool calling
• Responses API (Alpha): OpenAI-compatible POST /responses endpoint with typed output blocks for reasoning, messages, function calls, and web search. Stateless, supports streaming via SSE, API key or x402 wallet auth. E2EE models not supported — use /chat/completions instead.
• Model Feature Suffixes: Enable features via model name suffixes (e.g., model-name:web for web search)

Image

• Image Generation: Create images from text prompts
• Image Generations (OpenAI-compatible): OpenAI-compatible image generation endpoint
• Image Upscaling: Enhance and upscale images
• Image Editing: AI-powered image inpainting
• Image Multi-Edit: Combine and edit up to 3 images with layered inputs
• Background Remove: Remove image backgrounds
• Image Styles: List available image generation styles

Audio

• Text-to-Speech: Convert text to audio with 50+ voices
• Speech-to-Text: Transcribe audio to text with optional word-level timestamps
• Music Generation (Queue): Queue music/sound effects generation
• Music Generation (Retrieve): Retrieve generated audio by ID
• Music Generation (Quote): Get price quote for audio generation
• Music Generation (Complete): Queue and wait for audio generation in one call

Video

• Video Generation (Queue): Queue video generation (text-to-video or image-to-video)
• Video Generation (Retrieve): Retrieve generated video by ID
• Video Generation (Quote): Get price quote for video generation
• Video Generation (Complete): Queue and wait for video generation in one call
• Video Transcription: Extract text/speech from videos

Tools

• Text Parser: Extract text from PDF, DOCX, XLSX, and plain text files. Runs in-memory on Venice infrastructure with zero data retention ($0.01/request)
• Web Scrape: Scrape a web page and return its content as markdown ($0.01/request)
• Web Search: Search the web with privacy-preserving providers — Brave (ZDR, zero data retention) or Google (proxied through Venice so your identity is not associated with the search) ($0.01/request)
• Crypto Networks: List all supported blockchain networks (public endpoint, no auth required)
• Crypto RPC: Venice provides blockchain RPC access — send JSON-RPC requests to Ethereum, Base, Arbitrum, Optimism, Polygon, Linea, Avalanche, BSC, Blast, zkSync Era, and Starknet (mainnet + testnets). One API key, unified billing in Venice credits. Supports batch requests (up to 100), idempotent retries, and x402 wallet auth. No separate RPC provider signup needed.
• Crypto RPC Postman Collection: 27 ready-to-run examples for crypto RPC calls

Embeddings

• Embeddings: Generate vector embeddings for semantic search

Models

• List Models: Get available models with capabilities and pricing
• Model Traits: List model trait categories (e.g., text:uncensored, image:fast)
• Compatibility Mapping: Map OpenAI model names to Venice equivalents

Characters

• List Characters: List available AI character personas
• Get Character: Get details for a specific character
• Character Reviews: Get reviews for a character

API Keys

• List API Keys: List your API keys
• Get API Key: Get details for a specific API key
• Create API Key: Create a new API key
• Update API Key: Update an existing API key
• Delete API Key: Delete an API key
• Generate Web3 Key: Generate API key via Web3 wallet signature
• Rate Limits: Get rate limit configuration for an API key
• Rate Limit Logs: Get rate limit event logs

Billing

• Balance: Get current account balance
• Usage: Get usage history
• Usage Analytics: Get detailed usage analytics

x402 Wallet Authentication

• x402 Balance: Get wallet credit balance
• x402 Top-Up: Add USDC credits via Ethereum wallet
• x402 Transactions: Get wallet transaction history

Reference

• Rate Limiting: Rate limits and best practices
• Error Codes: API error reference

Models

• Model Overview: Browse all available models
• Text Models: LLMs including venice-uncensored, GLM-4.7, Qwen3, Mistral, Llama, Grok, DeepSeek, Kimi
• Image Models: Diffusion models for image generation (Flux, Stable Diffusion)
• Text-to-Speech Models: TTS models with multilingual voice support (Kokoro, Qwen 3 TTS)
• Speech-to-Text Models: Audio transcription models (Whisper, Parakeet)
• Music Models: Music and sound effects generation with lyrics support
• Video Models: Text-to-video and image-to-video models
• Embedding Models: Vector embedding models

Guides

• Structured Responses: Get JSON responses with guaranteed schemas using response_format
• Reasoning Models: Use models with step-by-step reasoning (supports reasoning_effort parameter)
• TEE & E2EE Models: Privacy-enhanced AI with Trusted Execution Environments (TEE) and End-to-End Encryption (E2EE)
• Prompt Caching: Reduce latency and costs with prompt caching
• Image Generation Guide: Best practices for image generation
• Image Editing Guide: Image editing and inpainting techniques
• Video Generation Guide: Video generation best practices
• Reference to Video: Lock in characters, objects, and scenes across AI video generations using reference images on Kling O3 and Grok Imagine R2V
• Video Upscaling: Enhance existing videos to higher resolution (2x/4x) or quality using the Topaz Video Upscale model
• x402 Wallet API: Use Venice API with Ethereum wallet authentication (no API key required)
• AI Agents: Build autonomous agents with Eliza framework
• Autonomous Agent API Key Creation: Let agents programmatically mint their own Venice API key by staking VVV on Base — no human interaction required
• Crypto RPC for Agents: Give AI agents inference and on-chain access through a single Venice credential. Covers JSON-RPC across 11 chains, x402 wallet auth, autonomous VVV staking, and DIEM-funded credits
• LangChain Integration: Use Venice with LangChain
• Vercel AI SDK: Use Venice with Vercel AI SDK
• CrewAI Integration: Use Venice with CrewAI
• OpenAI Migration: Migrate from OpenAI to Venice
• Claude Code: Use Venice with Claude Code CLI
• Cursor IDE: Use Venice with Cursor IDE
• Codex CLI: Use Venice with OpenAI Codex CLI
• OpenClaw: Self-hosted AI gateway connecting Venice to WhatsApp, Telegram, Discord, iMessage, and Slack
• Hermes Agent: Self-improving AI agent by Nous Research with persistent memory, skills, and 15+ messaging platforms, powered by Venice as a custom provider
• NanoClaw: Lightweight self-hosted personal AI assistant for WhatsApp and Telegram powered by Venice
• Integrations: Third-party integrations (Brave Leo, etc.)
• Postman Collection: Import ready-to-use API examples

Key Features

Venice-Specific Parameters

The venice_parameters object in chat completions supports:

• enable_web_search: Enable real-time web search (auto, on, off)
• enable_web_scraping: Scrape URLs in user messages via Firecrawl
• enable_web_citations: Request inline citations in responses
• enable_x_search: Enable xAI native search (web + X/Twitter) for supported models
• character_slug: Use a Venice AI character persona
• include_venice_system_prompt: Include/exclude Venice's default system prompt
• strip_thinking_response: Remove <think> blocks from reasoning model responses
• disable_thinking: Disable thinking entirely on reasoning models
• enable_e2ee: Enable/disable E2EE on E2EE-capable models

Multimodal Support

Chat completions support multiple input types on compatible models:

• Text: Standard text messages
• Images: Via image_url content type (URL or base64)
• Audio: Via input_audio content type (base64-encoded)
• Video: Via video_url content type (URL, YouTube links, or base64)

Authentication Options

• API Key: Standard Bearer token authentication
• x402 Wallet: USDC credits via Ethereum wallet (no account required, pay-as-you-go)

Optional

• Pricing: Pay-as-you-go and DIEM staking options
• Privacy Architecture: Zero data retention, TEE/E2EE encrypted models, and privacy guarantees
• Deprecations: Model deprecation notices
• Beta Models: Experimental models in beta
• OpenAPI Spec: Full OpenAPI/Swagger specification