diff --git a/api-reference/api-spec.mdx b/api-reference/api-spec.mdx index fce5500..fd94dd4 100644 --- a/api-reference/api-spec.mdx +++ b/api-reference/api-spec.mdx @@ -147,7 +147,7 @@ The `venice_parameters` object allows you to access Venice-specific features not | Parameter | Type | Description | Default | |-----------|------|-------------|---------| | `character_slug` | string | The character slug of a public Venice character (discoverable as "Public ID" on the published character page) | - | -| `strip_thinking_response` | boolean | Strip `` blocks from the response (models using legacy `` tag format). See [Reasoning Models](/overview/guides/reasoning-models). | `false` | +| `strip_thinking_response` | boolean | Strip `` blocks from the response (models using legacy `` tag format). See [Reasoning Models](/guides/features/reasoning-models). | `false` | | `disable_thinking` | boolean | On supported reasoning models, disable thinking and strip the `` blocks from the response | `false` | | `enable_web_search` | string | Enable web search for this request (`off`, `on`, `auto` - auto enables based on model's discretion)
Additional usage-based pricing applies, see [pricing](/overview/pricing#web-search-and-scraping). | `off` | | `enable_web_scraping` | boolean | Enable web scraping of up to 5 URLs detected in the user message. Scraped content augments responses and bypasses web search. Only successfully scraped URLs are billed.
Additional usage-based pricing applies, see [pricing](/overview/pricing#web-search-and-scraping). | `false` | @@ -169,7 +169,7 @@ Venice supports prompt caching on select models to reduce latency and costs for |-----------|------|-------------| | `prompt_cache_key` | string | Optional routing hint to improve cache hit rates. When supplied, Venice routes requests to the same backend infrastructure, increasing the likelihood of cache hits across multi-turn conversations. | -See [Prompt Caching](/overview/guides/prompt-caching) for details on how caching works, billing, and best practices. +See [Prompt Caching](/guides/features/prompt-caching) for details on how caching works, billing, and best practices. ## Response Headers Reference diff --git a/api-reference/endpoint/api_keys/generate_web3_key/get.mdx b/api-reference/endpoint/api_keys/generate_web3_key/get.mdx index e9bfdfd..a4978bf 100644 --- a/api-reference/endpoint/api_keys/generate_web3_key/get.mdx +++ b/api-reference/endpoint/api_keys/generate_web3_key/get.mdx @@ -5,6 +5,6 @@ openapi: 'GET /api_keys/generate_web3_key' --- ## Autonomous Agent API Key Creation -Please see [this guide](/overview/guides/generating-api-key-agent) on how to use this endpoint. +Please see [this guide](/guides/getting-started/generating-api-key-agent) on how to use this endpoint. ------- \ No newline at end of file diff --git a/api-reference/endpoint/api_keys/generate_web3_key/post.mdx b/api-reference/endpoint/api_keys/generate_web3_key/post.mdx index ef00d6e..712eb0b 100644 --- a/api-reference/endpoint/api_keys/generate_web3_key/post.mdx +++ b/api-reference/endpoint/api_keys/generate_web3_key/post.mdx @@ -4,6 +4,6 @@ openapi: 'POST /api_keys/generate_web3_key' --- ## Autonomous Agent API Key Creation -Please see [this guide](/overview/guides/generating-api-key-agent) on how to use this endpoint. +Please see [this guide](/guides/getting-started/generating-api-key-agent) on how to use this endpoint. ------- \ No newline at end of file diff --git a/docs.json b/docs.json index bf8511e..8a8c24f 100644 --- a/docs.json +++ b/docs.json @@ -22,34 +22,59 @@ "overview/about-venice", "overview/getting-started", "overview/privacy", + "overview/data-collection", + "overview/provider-privacy", "overview/pricing", "overview/deprecations", "overview/beta-models" ] - }, + } + ] + }, + { + "tab": "Guides", + "groups": [ { "group": "Guides", + "pages": ["guides/overview"] + }, + { + "group": "Getting Started", + "icon": "rocket", + "pages": [ + "guides/getting-started/generating-api-key", + "guides/getting-started/generating-api-key-agent", + "guides/getting-started/openai-migration", + "guides/getting-started/postman" + ] + }, + { + "group": "Features", + "icon": "wand-magic-sparkles", "pages": [ - "overview/guides/generating-api-key", - "overview/guides/generating-api-key-agent", - "overview/guides/ai-agents", - "overview/guides/postman", - "overview/guides/integrations", - "overview/guides/structured-responses", - "overview/guides/reasoning-models", - "overview/guides/video-generation", - "overview/guides/tee-e2ee-models", - "overview/guides/prompt-caching", - "overview/guides/claude-code", - "overview/guides/cursor", - "overview/guides/codex-cli", - "overview/guides/openclaw-bot", - "overview/guides/nanoclaw-venice", - "overview/guides/openai-migration", - "overview/guides/langchain", - "overview/guides/vercel-ai-sdk", - "overview/guides/crewai", - "overview/guides/reference-to-video" + "guides/features/structured-responses", + "guides/features/reasoning-models", + "guides/features/prompt-caching" + ] + }, + { + "group": "Integrations", + "icon": "puzzle-piece", + "pages": [ + "guides/integrations/integrations", + "guides/integrations/vercel-ai-sdk", + "guides/integrations/langchain", + "guides/integrations/crewai", + "guides/integrations/claude-code", + "guides/integrations/openclaw-bot", + "guides/integrations/ai-agents", + "guides/integrations/video-generation", + "guides/integrations/tee-e2ee-models", + "guides/integrations/cursor", + "guides/integrations/codex-cli", + "guides/integrations/nanoclaw-venice", + "guides/integrations/openai-migration", + "guides/integrations/reference-to-video" ] } ] @@ -122,9 +147,7 @@ }, { "group": "Embeddings", - "pages": [ - "api-reference/endpoint/embeddings/generate" - ] + "pages": ["api-reference/endpoint/embeddings/generate"] }, { "group": "Models", @@ -264,7 +287,63 @@ }, { "source": "/overview/guides/molt-bot", - "destination": "/overview/guides/openclaw-bot" + "destination": "/guides/integrations/openclaw-bot" + }, + { + "source": "/overview/guides/generating-api-key", + "destination": "/guides/getting-started/generating-api-key" + }, + { + "source": "/overview/guides/generating-api-key-agent", + "destination": "/guides/getting-started/generating-api-key-agent" + }, + { + "source": "/overview/guides/openai-migration", + "destination": "/guides/getting-started/openai-migration" + }, + { + "source": "/overview/guides/postman", + "destination": "/guides/getting-started/postman" + }, + { + "source": "/overview/guides/structured-responses", + "destination": "/guides/features/structured-responses" + }, + { + "source": "/overview/guides/reasoning-models", + "destination": "/guides/features/reasoning-models" + }, + { + "source": "/overview/guides/prompt-caching", + "destination": "/guides/features/prompt-caching" + }, + { + "source": "/overview/guides/vercel-ai-sdk", + "destination": "/guides/integrations/vercel-ai-sdk" + }, + { + "source": "/overview/guides/langchain", + "destination": "/guides/integrations/langchain" + }, + { + "source": "/overview/guides/crewai", + "destination": "/guides/integrations/crewai" + }, + { + "source": "/overview/guides/claude-code", + "destination": "/guides/integrations/claude-code" + }, + { + "source": "/overview/guides/ai-agents", + "destination": "/guides/integrations/ai-agents" + }, + { + "source": "/overview/guides/integrations", + "destination": "/guides/integrations/integrations" + }, + { + "source": "/overview/guides/openclaw-bot", + "destination": "/guides/integrations/openclaw-bot" } ] } diff --git a/overview/guides/prompt-caching.mdx b/guides/features/prompt-caching.mdx similarity index 100% rename from overview/guides/prompt-caching.mdx rename to guides/features/prompt-caching.mdx diff --git a/overview/guides/reasoning-models.mdx b/guides/features/reasoning-models.mdx similarity index 100% rename from overview/guides/reasoning-models.mdx rename to guides/features/reasoning-models.mdx diff --git a/overview/guides/structured-responses.mdx b/guides/features/structured-responses.mdx similarity index 100% rename from overview/guides/structured-responses.mdx rename to guides/features/structured-responses.mdx diff --git a/overview/guides/generating-api-key-agent.mdx b/guides/getting-started/generating-api-key-agent.mdx similarity index 98% rename from overview/guides/generating-api-key-agent.mdx rename to guides/getting-started/generating-api-key-agent.mdx index 0c36263..a5e9a7c 100644 --- a/overview/guides/generating-api-key-agent.mdx +++ b/guides/getting-started/generating-api-key-agent.mdx @@ -43,7 +43,7 @@ To autonomously generate an API key within an agent, you must: Now you can call this same [API endpoint](https://docs.venice.ai/api-reference/endpoint/api_keys/generate_web3_key/get) `https://api.venice.ai/api/v1/api_keys/generate_web3_key` to create your API key. - You will need the following information to proceed, which is described further within the "[Generating API Key Guide](https://docs.venice.ai/overview/guides/generating-api-key)": + You will need the following information to proceed, which is described further within the "[Generating API Key Guide](https://docs.venice.ai/guides/getting-started/generating-api-key)": * API Key Type: Inference or Admin diff --git a/overview/guides/generating-api-key.mdx b/guides/getting-started/generating-api-key.mdx similarity index 100% rename from overview/guides/generating-api-key.mdx rename to guides/getting-started/generating-api-key.mdx diff --git a/overview/guides/openai-migration.mdx b/guides/getting-started/openai-migration.mdx similarity index 100% rename from overview/guides/openai-migration.mdx rename to guides/getting-started/openai-migration.mdx diff --git a/overview/guides/postman.mdx b/guides/getting-started/postman.mdx similarity index 100% rename from overview/guides/postman.mdx rename to guides/getting-started/postman.mdx diff --git a/overview/guides/ai-agents.mdx b/guides/integrations/ai-agents.mdx similarity index 95% rename from overview/guides/ai-agents.mdx rename to guides/integrations/ai-agents.mdx index 0fb07b1..91f58ff 100644 --- a/overview/guides/ai-agents.mdx +++ b/guides/integrations/ai-agents.mdx @@ -24,7 +24,7 @@ git clone https://github.com/ai16z/eliza.git * Copy `.env.example` to `.env` -* Update `.env` specifying your `VENICE_API_KEY`, and model selections for `SMALL_VENICE_MODEL`, `MEDIUM_VENICE_MODEL`, `LARGE_VENICE_MODEL`, `IMAGE_VENICE_MODEL`, instructions on generating your key can be found [here](/overview/guides/generating-api-key). +* Update `.env` specifying your `VENICE_API_KEY`, and model selections for `SMALL_VENICE_MODEL`, `MEDIUM_VENICE_MODEL`, `LARGE_VENICE_MODEL`, `IMAGE_VENICE_MODEL`, instructions on generating your key can be found [here](/guides/getting-started/generating-api-key). * Create a new character in the `/characters/` folder with a filename similar to `your_character.character.json`to specify the character profile, tools/functions, and Venice.ai as the model provider: diff --git a/overview/guides/claude-code.mdx b/guides/integrations/claude-code.mdx similarity index 99% rename from overview/guides/claude-code.mdx rename to guides/integrations/claude-code.mdx index afb422d..37fd81c 100644 --- a/overview/guides/claude-code.mdx +++ b/guides/integrations/claude-code.mdx @@ -221,7 +221,7 @@ The router provides several useful features beyond basic routing: ## Caching Behavior -Venice [prompt caching](/overview/guides/prompt-caching) works alongside Claude Code's native cache markers. Venice automatically detects when Claude Code sends `cache_control` fields and adjusts its caching strategy accordingly. +Venice [prompt caching](/guides/features/prompt-caching) works alongside Claude Code's native cache markers. Venice automatically detects when Claude Code sends `cache_control` fields and adjusts its caching strategy accordingly. | Scenario | Cache TTL | Who Controls | |----------|-----------|--------------| diff --git a/overview/guides/codex-cli.mdx b/guides/integrations/codex-cli.mdx similarity index 100% rename from overview/guides/codex-cli.mdx rename to guides/integrations/codex-cli.mdx diff --git a/overview/guides/crewai.mdx b/guides/integrations/crewai.mdx similarity index 99% rename from overview/guides/crewai.mdx rename to guides/integrations/crewai.mdx index 8e6835f..26d2acc 100644 --- a/overview/guides/crewai.mdx +++ b/guides/integrations/crewai.mdx @@ -190,7 +190,7 @@ print(result) Enhance agents with web search and other tools: -`SerperDevTool` requires a `SERPER_API_KEY` environment variable from [serper.dev](https://serper.dev). As an alternative, you can use Venice's built-in web search by passing `venice_parameters: {"enable_web_search": "auto"}` via `model_kwargs` — no extra API key needed. See the LangChain guide's [Web Search Integration](/overview/guides/langchain#web-search-integration) for an example. +`SerperDevTool` requires a `SERPER_API_KEY` environment variable from [serper.dev](https://serper.dev). As an alternative, you can use Venice's built-in web search by passing `venice_parameters: {"enable_web_search": "auto"}` via `model_kwargs` — no extra API key needed. See the LangChain guide's [Web Search Integration](/guides/integrations/langchain#web-search-integration) for an example. ```python diff --git a/overview/guides/cursor.mdx b/guides/integrations/cursor.mdx similarity index 100% rename from overview/guides/cursor.mdx rename to guides/integrations/cursor.mdx diff --git a/overview/guides/integrations.mdx b/guides/integrations/integrations.mdx similarity index 100% rename from overview/guides/integrations.mdx rename to guides/integrations/integrations.mdx diff --git a/overview/guides/langchain.mdx b/guides/integrations/langchain.mdx similarity index 100% rename from overview/guides/langchain.mdx rename to guides/integrations/langchain.mdx diff --git a/overview/guides/nanoclaw-venice.mdx b/guides/integrations/nanoclaw-venice.mdx similarity index 100% rename from overview/guides/nanoclaw-venice.mdx rename to guides/integrations/nanoclaw-venice.mdx diff --git a/overview/guides/openclaw-bot.mdx b/guides/integrations/openclaw-bot.mdx similarity index 100% rename from overview/guides/openclaw-bot.mdx rename to guides/integrations/openclaw-bot.mdx diff --git a/overview/guides/reference-to-video.mdx b/guides/integrations/reference-to-video.mdx similarity index 100% rename from overview/guides/reference-to-video.mdx rename to guides/integrations/reference-to-video.mdx diff --git a/overview/guides/tee-e2ee-models.mdx b/guides/integrations/tee-e2ee-models.mdx similarity index 100% rename from overview/guides/tee-e2ee-models.mdx rename to guides/integrations/tee-e2ee-models.mdx diff --git a/overview/guides/vercel-ai-sdk.mdx b/guides/integrations/vercel-ai-sdk.mdx similarity index 100% rename from overview/guides/vercel-ai-sdk.mdx rename to guides/integrations/vercel-ai-sdk.mdx diff --git a/overview/guides/video-generation.mdx b/guides/integrations/video-generation.mdx similarity index 100% rename from overview/guides/video-generation.mdx rename to guides/integrations/video-generation.mdx diff --git a/guides/overview.mdx b/guides/overview.mdx new file mode 100644 index 0000000..966c746 --- /dev/null +++ b/guides/overview.mdx @@ -0,0 +1,45 @@ +--- +title: Guides +description: "Step-by-step tutorials for building with Venice AI" +"og:title": "Guides | Venice API Docs" +"og:description": "Step-by-step tutorials for getting started, using features, and integrating Venice AI with popular frameworks." +--- + +Learn how to build with Venice AI through hands-on guides organized by what you're trying to do. + + + + Generate your API key, test with Postman, and migrate from OpenAI. + + + Structured output, reasoning models, and prompt caching. + + + Vercel AI SDK, LangChain, CrewAI, Claude Code, OpenClaw, and more. + + + +--- + +## Popular guides + + + + Same SDK, two lines changed. Drop-in replacement with privacy. + + + Stream Venice AI responses in Next.js, React, Svelte, and Vue. + + + Use Claude Code CLI with Venice's Claude models. + + + Step-by-step thinking with visible reasoning chains. + + + Cut latency by 80% and costs by 90% on repeated prompts. + + + Build chains, agents, and RAG pipelines with Venice. + + diff --git a/llms.txt b/llms.txt index d1b3580..8ae6eab 100644 --- a/llms.txt +++ b/llms.txt @@ -2,14 +2,14 @@ > Venice is a privacy-first, uncensored AI API platform offering text generation, image generation, audio synthesis, video generation, music, and embeddings 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 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 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](https://docs.venice.ai/overview/getting-started): Get your API key and make your first request in minutes -- [API Key Generation](https://docs.venice.ai/overview/guides/generating-api-key): Step-by-step guide to creating API keys +- [API Key Generation](https://docs.venice.ai/guides/getting-started/generating-api-key): Step-by-step guide to creating API keys - [About Venice](https://docs.venice.ai/overview/about-venice): Overview of Venice's capabilities and OpenAI compatibility ## API Reference @@ -44,18 +44,29 @@ Venice offers four tiers of privacy: **Anonymized** (third-party models with ide ## Guides -- [Structured Responses](https://docs.venice.ai/overview/guides/structured-responses): Get JSON responses with guaranteed schemas -- [Reasoning Models](https://docs.venice.ai/overview/guides/reasoning-models): Use models with step-by-step reasoning -- [TEE & E2EE Models](https://docs.venice.ai/overview/guides/tee-e2ee-models): Privacy-enhanced AI with Trusted Execution Environments (TEE) and End-to-End Encryption (E2EE)—cryptographic guarantees that your data remains private, even from Venice -- [AI Agents](https://docs.venice.ai/overview/guides/ai-agents): Build autonomous agents with Eliza framework -- [Integrations](https://docs.venice.ai/overview/guides/integrations): Third-party integrations like Brave Leo -- [Postman Collection](https://docs.venice.ai/overview/guides/postman): Import ready-to-use API examples +- [Guides Overview](https://docs.venice.ai/guides/overview): All guides organized by category +- [Migrate from OpenAI](https://docs.venice.ai/guides/getting-started/openai-migration): Drop-in replacement - same SDK, two lines changed +- [Structured Responses](https://docs.venice.ai/guides/features/structured-responses): Get JSON responses with guaranteed schemas +- [Reasoning Models](https://docs.venice.ai/guides/features/reasoning-models): Use models with step-by-step reasoning +- [Prompt Caching](https://docs.venice.ai/guides/features/prompt-caching): Reduce costs and latency with prompt caching +- [Vercel AI SDK](https://docs.venice.ai/guides/integrations/vercel-ai-sdk): Stream Venice AI in Next.js and React apps +- [LangChain](https://docs.venice.ai/guides/integrations/langchain): Build chains, agents, and RAG pipelines +- [CrewAI](https://docs.venice.ai/guides/integrations/crewai): Multi-agent AI systems with Venice +- [Claude Code](https://docs.venice.ai/guides/integrations/claude-code): Use Claude Code CLI with Venice +- [AI Agents](https://docs.venice.ai/guides/integrations/ai-agents): Build autonomous agents with Eliza framework +- [Integrations](https://docs.venice.ai/guides/integrations/integrations): Third-party integrations like Brave Leo +- [Postman Collection](https://docs.venice.ai/guides/getting-started/postman): Import ready-to-use API examples +- [TEE & E2EE Models](https://docs.venice.ai/guides/tee-e2ee-models): Privacy-enhanced AI with Trusted Execution Environments (TEE) and End-to-End Encryption (E2EE)—cryptographic guarantees that your data remains private, even from Venice + +## Privacy & Data + +- [Privacy](https://docs.venice.ai/overview/privacy): Zero data retention policy and privacy architecture +- [Data Collection](https://docs.venice.ai/overview/data-collection): What Venice collects (metadata only) and what it never collects (prompts, responses) +- [Provider Privacy](https://docs.venice.ai/overview/provider-privacy): Private vs Anonymized model tiers and third-party provider policies ## Optional - [Pricing](https://docs.venice.ai/overview/pricing): Pay-as-you-go and DIEM staking options -- [Privacy Architecture](https://docs.venice.ai/overview/privacy): Zero data retention, TEE/E2EE encrypted models, and privacy guarantees - [Deprecations](https://docs.venice.ai/overview/deprecations): Model deprecation notices - [Beta Models](https://docs.venice.ai/overview/beta-models): Experimental models in beta - [OpenAPI Spec](https://docs.venice.ai/swagger.yaml): Full OpenAPI/Swagger specification - diff --git a/overview/about-venice.mdx b/overview/about-venice.mdx index 12f7dfe..26e115c 100644 --- a/overview/about-venice.mdx +++ b/overview/about-venice.mdx @@ -1259,11 +1259,11 @@ Get your API key and make your first request. Complete API documentation and endpoints - + Ready-to-use API examples and testing - + Build with Eliza and other agent frameworks diff --git a/overview/data-collection.mdx b/overview/data-collection.mdx new file mode 100644 index 0000000..a6f4054 --- /dev/null +++ b/overview/data-collection.mdx @@ -0,0 +1,58 @@ +--- +title: Data Collection +description: "What data Venice collects and what it does not" +"og:title": "Data Collection | Venice API Docs" +"og:description": "Venice collects minimal metadata to operate the platform. Prompts, responses, and generated content are never stored." +--- + +This page describes what data Venice collects when you use the API or the web app, and how that data is used. Venice does not collect prompt content, model responses, or generated media. For details on how that works, see [Privacy](/overview/privacy). + +For more information, see the [Venice Privacy Policy](https://venice.ai/legal/privacy-policy). + +## API usage metadata + +Each API request generates operational metadata used for billing, rate limiting, and platform health. This metadata does not include prompt or response content. + +| Field | Example | Purpose | +|---|---|---| +| Token counts (input/output) | `512 in, 1024 out` | Billing | +| Model ID | `zai-org-glm-4.7` | Billing and routing | +| Request timestamp | `2026-02-20T15:30:00Z` | Rate limiting | +| Response latency | `1.2s` | Performance monitoring | +| HTTP status code | `200` | Error tracking | +| API key identifier | `vk_...abc` | Authentication and billing | + +## Account information + +What Venice stores depends on your account type: + +| Account type | Data collected | +|---|---| +| No account | Basic metadata: timezone, browser type, IP address. Used for abuse prevention and experience optimization. | +| Free account | Email address for account verification, or public wallet address if signing up with a crypto wallet. | +| Pro account | Credit card payments are processed by [Stripe](https://stripe.com) and never shared with Venice. Crypto payments record only the public wallet address. | + +Each tier includes the data from the tiers above it. + + +Use a VPN to mask your IP address. Use a disposable email or a web3 wallet to avoid sharing your real email. + + +## Product telemetry + +Venice logs product usage events such as sign-ins, chat creation, chat deletion, and filter changes. These events describe actions you take on the platform, not the content of those actions. + +## Third-party services + +| Service | Purpose | Data shared | +|---|---|---| +| [Stripe](https://stripe.com) | Credit card payments | Card details (not shared with Venice) | +| [Clerk](https://clerk.com) | Email authentication | Email address | +| WalletConnect | Web3 login | Public wallet address | +| [Customer.io](https://customer.io) | Email communications and event tracking | Email address, product events | +| [Plausible](https://plausible.io) | Privacy-friendly analytics | Page views (no cookies, no personal data) | + +## Related + +- [Privacy](/overview/privacy) - Venice's retention policy and architecture +- [Provider Privacy](/overview/provider-privacy) - data handling for Private vs Anonymized models diff --git a/overview/getting-started.mdx b/overview/getting-started.mdx index 87764fd..33acacb 100644 --- a/overview/getting-started.mdx +++ b/overview/getting-started.mdx @@ -11,7 +11,7 @@ Get up and running with the Venice API in minutes. Generate an API key, make you Head to your [Venice API Settings](https://venice.ai/settings/api) and generate a new API key. - For a detailed walkthrough with screenshots, check out the [API Key guide](/overview/guides/generating-api-key). + For a detailed walkthrough with screenshots, check out the [API Key guide](/guides/getting-started/generating-api-key). @@ -968,10 +968,10 @@ Now that you've made your first requests, explore more of what Venice API has to Explore detailed API documentation with all endpoints and parameters - + Learn how to get JSON responses with guaranteed schemas - + Build autonomous AI agents with Venice API and frameworks like Eliza @@ -985,7 +985,7 @@ Now that you've made your first requests, explore more of what Venice API has to Reference for handling API errors and troubleshooting issues - + Import our complete Postman collection for easy testing diff --git a/overview/pricing.mdx b/overview/pricing.mdx index 86ea85d..281358a 100644 --- a/overview/pricing.mdx +++ b/overview/pricing.mdx @@ -293,13 +293,13 @@ These charges apply in addition to standard model token pricing. ## Payment Options - + Buy API credits with credit card. Credits never expire. - + Buy API credits with cryptocurrency. Same rates as USD. - + Each Diem = $1/day of credits that refresh daily. diff --git a/overview/privacy.mdx b/overview/privacy.mdx index cb2da97..b3136bd 100644 --- a/overview/privacy.mdx +++ b/overview/privacy.mdx @@ -1,20 +1,74 @@ --- title: Privacy "og:title": "Privacy | Venice API Docs" +"og:description": "Venice does not store or log any prompt or model responses. Learn how the privacy architecture works." --- -Nearly all AI apps and services collect user data (personal information, prompt text, and AI text and image responses) in central servers, which they can access, and which they can (and do) share with third parties, ranging from ad networks to governments. Even if a company wants to keep this data safe, data breaches happen [all the time](https://www.wired.com/story/wired-guide-to-data-breaches/), often unreported. +Venice does not store or log any prompt or model responses on its servers. This is an architectural default, not an opt-in setting. -> The only way to achieve reasonable user privacy is to avoid collecting this information in the first place. This is harder to do from an engineering perspective, but we believe it’s the correct approach. +## How requests are processed -### Privacy as a principle +When you send a request to the Venice API: -One of Venice’s guiding principles is user privacy. The platform's architecture flows from this philosophical principle, and every component is designed with this objective in mind. +1. Your request is transmitted over SSL to Venice's proxy server +2. The proxy routes the request to the model's inference endpoint. No prompt content is logged at the proxy layer. +3. The model processes the prompt in memory and streams the response back +4. The prompt and response are purged from memory. Nothing is written to disk. -#### Architecture +``` +Your app --SSL--> Venice Proxy --SSL--> Inference --SSL--> Response + (no logging) (purged after response) +``` -The Venice API replicates the same technical architecture as the Venice platform from a backend perspective. +Venice manages a fleet of GPUs across multiple infrastructure providers. These providers are bound by ZDR agreements and run Venice-operated software that processes only the raw prompt context - no user identity, IP address, or account data is forwarded to the GPU. -**Venice does not store or log any prompt or model responses on our servers.** API calls are forwarded directly to GPUs running across a collection of decentralized providers over encrypted HTTPS paths. +## Private vs Anonymized models + +Venice serves models through two infrastructure paths. + +**Private models** run on Venice's GPU fleet using open-source models. The full request stays within Venice's infrastructure and no third party is involved. Zero Data Retention applies end-to-end. + +**Anonymized models** are served by third-party providers (Anthropic, OpenAI, Google, xAI, and others). Venice strips all identifying information before forwarding the request. Venice's own ZDR still applies - nothing is logged or stored by Venice - but the third-party provider may retain the anonymized request content according to their own policies. + +See [Provider Privacy](/overview/provider-privacy) for details on how each path works and each provider's retention policies. + +## TEE and E2EE models + +Some of our hosted Private models add stronger, cryptographically verifiable protections. + +**TEE models** run inside Trusted Execution Environments - hardware-secured enclaves. This adds a verification layer on top of Venice's standard Zero Data Retention architecture. Clients can verify that a model is running in a genuine TEE with attestation verification - which you can learn about in our [TEE & E2EE model guide.](/guides/integrations/tee-e2ee-models) + +**E2EE models** build on TEE protection by encrypting prompts client-side before they leave your application. Venice relays encrypted data, and only the attested enclave can decrypt it. E2EE models require client-side integration and `stream: true`; see [TEE & E2EE Models](/guides/integrations/tee-e2ee-models) for the full protocol. + + +In the `/models` API, TEE and E2EE appear as capabilities on Private models through `supportsTeeAttestation` and `supportsE2EE`. The base `privacy` field remains `private`. + + +## What Venice does not store + +- Text prompts and model responses +- Generated images, audio, and video +- Uploaded files and documents +- Conversation history (stored in your browser only) + +## What Venice does store + +Venice retains operational metadata for billing, rate limiting, and platform health. This metadata does not include the content of your prompts or responses. See [Data Collection](/overview/data-collection) for the full breakdown. + +## Training + +Data sent to the Venice API is not used to train or improve any model. For Private models, this is guaranteed by architecture. For Anonymized models, this is based on each provider's current policies - see the [provider policy table](/overview/provider-privacy#provider-policies). + +## Caching + +Some models support [prompt caching](/guides/features/prompt-caching), which keeps repeated prompt prefixes in GPU memory to reduce latency and cost. Venice considers in-memory caching consistent with zero data retention. Cached data is transient, never written to disk, and automatically evicted when memory is needed. + +## Shared chats + +When you share a chat through the Venice web app, the conversation is encrypted in your browser before upload. The encrypted data is stored on Venice servers for 14 days. The decryption key exists only in the share URL - Venice cannot read shared chat content. + +## Verification + +Venice is pursuing third-party audits to independently verify its privacy architecture. The guarantees described on this page are architectural: the system is designed so that data is not retained, rather than relying on a policy commitment alone. ![Venice AI Privacy Architecture](/images/privacy-architecture.png "Venice AI Privacy Architecture") diff --git a/overview/provider-privacy.mdx b/overview/provider-privacy.mdx new file mode 100644 index 0000000..6fcf4b5 --- /dev/null +++ b/overview/provider-privacy.mdx @@ -0,0 +1,67 @@ +--- +title: Provider Privacy +description: "Data handling for Private and Anonymized models" +"og:title": "Provider Privacy | Venice API Docs" +"og:description": "Understand data handling across Venice's Private and Anonymized model tiers." +--- + +Venice serves models through two infrastructure paths, each with different data handling characteristics. Every model on the [pricing page](/overview/pricing) and in the [model catalog](/models/overview) is labeled with its privacy tier. + +For an overview of how requests are processed and Venice's own retention policy, see [Privacy](/overview/privacy). + +## Private models + +Private models run on Venice's GPU fleet using open-source models. Requests do not leave Venice's infrastructure and no third party is involved in processing. Zero Data Retention applies end-to-end. + +The GPU receives only the raw prompt context. No user ID, IP address, or account information is forwarded. + +**Examples:** Venice Uncensored, GLM 4.7, Qwen 3, DeepSeek V3.2, Llama 3.3, Mistral, Kokoro TTS + +## Anonymized models + +Anonymized models are served by third-party providers. Venice acts as an anonymizing proxy, stripping all identifying information before forwarding requests. + +Venice removes your API key, IP address, headers, and all account data. The anonymized request is forwarded to the provider under Venice's own credentials. The provider sees Venice as the customer, not you. + +Venice does not log or store any prompt or response content from these requests. However, the provider's own retention and training policies apply to the anonymized request. + +**Examples:** Claude Opus/Sonnet, GPT-5.2, Gemini 3, Grok 4.1 + +## TEE models + +TEE ("Trusted Exeecution Environment") models are a subset of Private models that run inside hardware-secured enclaves. By using TEE-enabled models, you don't have to trust us that your inference is secure - you can prove it, by verifying the attestation yourself. See [TEE & E2EE Models](/guides/integrations/tee-e2ee-models) for the full flow. + +In the `/models` API, TEE models appear as `privacy: private`, with `supportsTeeAttestation: true`. + +**Examples:** `tee-*` models such as `tee-qwen3-5-122b-a10b` + +## E2EE models + +E2EE ("End to End Encryption") models add client-side encryption on top of TEE protection. Your prompt is encrypted before it leaves your application, remains encrypted through Venice, and is only decrypted inside the attested enclave. + +In the `/models` API, E2EE models appear as `privacy: private` with `supportsE2EE: true`. E2EE requests require client-side integration and `stream: true`; see [TEE & E2EE Models](/guides/integrations/tee-e2ee-models) for the full flow. + +**Examples:** `e2ee-qwen3-5-122b-a10b`, `e2ee-glm-4-7-p`, `e2ee-venice-uncensored-24b-p` + +## Provider policies + +Each third-party provider has its own data handling policies for training and retention. The table below reflects the current policies as they apply to API requests. + +| Provider | Models on Venice | Trains on data | Retains data | Retention period | Policy | +|---|---|---|---|---|---| +| Anthropic | Claude Opus 4.5/4.6, Sonnet 4.5/4.6 | No | Yes (default) | Up to 30 days. ZDR-eligible with arrangement. | [Privacy center](https://privacy.anthropic.com/en/articles/7996866-how-long-do-you-store-my-organization-s-data) | +| OpenAI | GPT-5.2, GPT-5.2 Codex, GPT OSS 120B | No | Yes | Up to 30 days (abuse monitoring) | [Data usage policy](https://openai.com/policies/api-data-usage-policies) | +| Google | Gemini 3 Pro/Flash, Gemini 3.1 Pro | No | Yes | 55 days (abuse monitoring) | [Usage policies](https://ai.google.dev/gemini-api/docs/usage-policies) | +| xAI | Grok 4.1 Fast, Grok Code Fast 1 | No | Yes | 30 days (auto-deleted) | [Enterprise FAQ](https://x.ai/legal/faq-enterprise) | +| Moonshot | Kimi K2, Kimi K2.5 | Not documented | Not documented | Not documented | [Terms of service](https://platform.moonshot.ai/docs/agreement/modeluse) | +| MiniMax | MiniMax M2.1, M2.5 | Not documented | Yes | 90 days (API logs) | [Privacy policy](https://minimaxm2.io/privacy) | + + +Provider policies can change. Where Venice is unable to establish a clear policy for a provider, the table reflects that. Venice works with providers to maintain privacy-respecting arrangements but cannot guarantee their policies long-term. + + +## Related + +- [Privacy](/overview/privacy) - Venice's own retention policy and architecture +- [TEE & E2EE Models](/guides/integrations/tee-e2ee-models) - attestation and end-to-end encryption guide +- [Data Collection](/overview/data-collection) - what metadata Venice retains