fix(brand+serve): docs is not an AI gateway; pin canonical static v0.5.1

Our own docs branded a Hanzo product as an 'AI Gateway' (/docs/llm title+H1, skills index, and ~90 files across docs/bot-docs/cloud). Renamed to 'AI API' to match hanzo.ai/app/bot. Third-party product names are facts about someone else's product and are NOT rewritten: 'Vercel AI Gateway' restored verbatim (same carve-out as LiteLLM); HanzoBot's own 'Gateway' transport untouched. Pins ghcr.io/hanzoai/static 0.4.1 -> v0.5.1: only v0.5.1 carries 79ac4f9 (serve directory index in place), so docs was the last host 301ing /docs/x/ -> /docs/x/index.html, which poisons Next's router into prefetching .../index.html/__next._tree.txt — 8 failed requests per page load.
2026-07-27 04:31:57 +00:00 · 2026-07-25 12:56:52 -07:00
parent d557d63aa3
commit 975a0bac18
89 changed files with 139 additions and 139 deletions
@@ -23,7 +23,7 @@ ENV NEXT_EXPORT=1 \
    NODE_OPTIONS=--max-old-space-size=24576
 RUN pnpm build --filter=docs

-FROM ghcr.io/hanzoai/static:0.4.1
+FROM ghcr.io/hanzoai/static:v0.5.1
 COPY --from=build /src/apps/docs/out /public
 EXPOSE 3000
 ENTRYPOINT ["/static", "-port", "3000", "-root", "/public"]
@@ -98,7 +98,7 @@ pnpm types:check      # Type check
 ### Hanzo Docs (hanzoai.github.io/docs)

 Documentation for Hanzo AI infrastructure including:
- AI Gateway
+- AI API
 - Agent SDK
 - MCP Tools
 - Chat Platform
@@ -5,7 +5,7 @@ const billingFaqs = [
  },
  {
    q: 'What does the $5/mo Cloud plan include?',
-    a: 'A full Linux desktop VM running in Hanzo Cloud with access to 100+ AI models via the Hanzo AI Gateway. Your bot is always on, backed up daily, and accessible from any device. All chat integrations are included.',
+    a: 'A full Linux desktop VM running in Hanzo Cloud with access to 100+ AI models via the Hanzo AI API. Your bot is always on, backed up daily, and accessible from any device. All chat integrations are included.',
  },
  {
    q: 'Why is Cloud Pro $25/mo?',
@@ -50,7 +50,7 @@ const plans = [
    badge: '14-day free trial',
    features: [
      'Full Linux desktop VM (Ubuntu)',
-      '100+ AI models via Hanzo AI Gateway',
+      '100+ AI models via Hanzo AI API',
      'Always-on with daily backups',
      'Web dashboard at app.hanzo.bot',
    ],
@@ -412,7 +412,7 @@ export default function Page() {
        </h2>
        <div className="grid grid-cols-2 sm:grid-cols-3 gap-3">
          {[
-            { name: 'AI Gateway', desc: '200+ AI models, one API', href: 'https://docs.hanzo.ai/docs/llm' },
+            { name: 'AI API', desc: '200+ AI models, one API', href: 'https://docs.hanzo.ai/docs/llm' },
            { name: 'Marketplace', desc: 'Buy & sell AI capacity', href: 'https://app.hanzo.bot' },
            { name: 'MCP', desc: '260+ tools for agents', href: 'https://docs.hanzo.ai/docs/mcp' },
            { name: 'Commerce', desc: 'Billing & on-chain settlement', href: 'https://docs.hanzo.ai/docs/commerce' },
@@ -257,7 +257,7 @@ export default function PlatformPage() {

        <div className="flex justify-center mt-3">
          <div className="flex flex-col items-center gap-0.5 text-fd-muted-foreground/40">
-            <span className="text-[10px] font-mono">AI Gateway</span>
+            <span className="text-[10px] font-mono">AI API</span>
            <span className="text-xs">|</span>
            <span className="text-[10px] font-mono">llm.hanzo.ai</span>
          </div>
@@ -44,7 +44,7 @@ const tiers = [
    badge: 'Most Popular',
    features: [
      'Full Linux desktop VM (Ubuntu)',
-      '100+ AI models included via Hanzo AI Gateway',
+      '100+ AI models included via Hanzo AI API',
      'Always-on — never goes to sleep',
      'All chat integrations',
      'Persistent memory, files & storage',
@@ -80,7 +80,7 @@ type CellValue = true | false | string;
 const comparisonRows: { feature: string; free: CellValue; cloud: CellValue; pro: CellValue }[] = [
  { feature: 'Self-hosted (Mac/Win/Linux)', free: true, cloud: false, pro: false },
  { feature: 'Cloud VM (always-on)', free: false, cloud: 'Linux (Ubuntu)', pro: 'macOS or Windows' },
-  { feature: 'AI models included', free: false, cloud: '100+ via AI Gateway', pro: '100+ with priority access' },
+  { feature: 'AI models included', free: false, cloud: '100+ via AI API', pro: '100+ with priority access' },
  { feature: 'Bring your own API keys', free: true, cloud: true, pro: true },
  { feature: 'Chat integrations', free: 'All', cloud: 'All', pro: 'All' },
  { feature: 'Browser automation', free: true, cloud: true, pro: 'Advanced (Playwright)' },
@@ -1,6 +1,6 @@
 ---
 title: "Security 🔒"
-description: "Security considerations and threat model for running an AI gateway with shell access"
+description: "Security considerations and threat model for running an AI API with shell access"
 ---

 ## Quick check: `bot security audit`
@@ -43,7 +43,7 @@ The wizard starts with **QuickStart** (defaults) vs **Advanced** (full control).
 ## What the wizard does

 **Local mode (default)** walks you through:
-  - Model/auth (OpenAI Code (Codex) subscription OAuth, Anthropic API key (recommended) or setup-token (paste), plus MiniMax/GLM/Moonshot/AI Gateway options)
+  - Model/auth (OpenAI Code (Codex) subscription OAuth, Anthropic API key (recommended) or setup-token (paste), plus MiniMax/GLM/Moonshot/AI API options)
 - Workspace location + bootstrap files
 - Gateway settings (port/bind/auth/tailscale)
 - Providers (Telegram, WhatsApp, Discord, Google Chat, Mattermost (plugin), Signal)
@@ -16,11 +16,11 @@ const mono = Geist_Mono({
 export const metadata: Metadata = {
  title: 'Hanzo Cloud — AI Infrastructure Platform',
  description:
-    'Unified AI infrastructure platform. AI gateway, usage analytics, team management, and API key provisioning.',
+    'Unified AI infrastructure platform. AI API, usage analytics, team management, and API key provisioning.',
  openGraph: {
    title: 'Hanzo Cloud — AI Infrastructure Platform',
    description:
-      'Unified AI infrastructure platform with AI gateway, analytics, and team management.',
+      'Unified AI infrastructure platform with AI API, analytics, and team management.',
    url: 'https://cloud.hanzo.ai',
    siteName: 'Hanzo Cloud',
    type: 'website',
@@ -40,7 +40,7 @@ const buttonVariants = cva(
 const features = [
  {
    icon: BrainCircuitIcon,
-    title: 'AI Gateway',
+    title: 'AI API',
    description:
      'Unified API for 100+ AI providers. OpenAI, Anthropic, Together, Deepseek, and more through a single API.',
  },
@@ -95,7 +95,7 @@ const showcases: ShowcaseObject[] = [
  },
  {
    image: '/showcases/llm-gateway.png',
-    name: 'AI Gateway',
+    name: 'AI API',
    url: 'https://llmgateway.io',
  },
  {
@@ -5,7 +5,7 @@ description: Build, deploy, and run autonomous agents — personas with a model,

 # Agents

-Build, deploy, and run autonomous agents: configured personas with a model, a tool list, guardrails, and shared memory. Agents are wired into [MCP](/docs/mcp) for tools, Hanzo Brain for memory, and the [AI Gateway](/docs/llm) for inference. Tenant-scoped by org.
+Build, deploy, and run autonomous agents: configured personas with a model, a tool list, guardrails, and shared memory. Agents are wired into [MCP](/docs/mcp) for tools, Hanzo Brain for memory, and the [AI API](/docs/llm) for inference. Tenant-scoped by org.

 ## Quickstart

@@ -13,7 +13,7 @@ Compose a workflow on an infinite canvas: drop in LLM, vision, and audio nodes,

 ## Test & Iterate

-Run the graph directly in the canvas and inspect every node's input and output as data flows through. Swap a model, tweak a prompt, and re-run — iteration is immediate, and the models are the same ones you can call through the [AI Gateway](/docs/llm).
+Run the graph directly in the canvas and inspect every node's input and output as data flows through. Swap a model, tweak a prompt, and re-run — iteration is immediate, and the models are the same ones you can call through the [AI API](/docs/llm).

 ## Ship as an API

@@ -35,4 +35,4 @@ The exact route for a published workflow is shown when you publish it; see the [

 - [Marketplace](/docs/marketplace) — models to drop into a graph
 - [Crawl](/docs/crawl) — feed web content into a workflow
- [AI Gateway](/docs/llm) · [MCP](/docs/mcp) · [Chat](/docs/chat)
+- [AI API](/docs/llm) · [MCP](/docs/mcp) · [Chat](/docs/chat)
@@ -19,7 +19,7 @@ Hanzo uses key prefixes so you can identify a credential at a glance and catch a

 ### API Keys (`hk-*`)

-These are your primary credentials. One `hk-*` key gives access to all Hanzo services for the project it belongs to: AI gateway, search, storage, tasks, and everything else.
+These are your primary credentials. One `hk-*` key gives access to all Hanzo services for the project it belongs to: AI API, search, storage, tasks, and everything else.

 ```bash
 # All Hanzo API calls use the same header format
@@ -85,7 +85,7 @@ This works uniformly across every endpoint:
 | Service | Base URL | Example |
 |---------|----------|---------|
 | API Gateway | `api.hanzo.ai` | `api.hanzo.ai/v1/models` |
-| AI Gateway | `llm.hanzo.ai` | `llm.hanzo.ai/v1/chat/completions` |
+| AI API | `llm.hanzo.ai` | `llm.hanzo.ai/v1/chat/completions` |
 | Tasks | `tasks-api.hanzo.ai` | gRPC with metadata header |
 | Search | `search.hanzo.ai` | `search.hanzo.ai/v1/search` |

@@ -27,7 +27,7 @@ Each service is namespaced under `/v1`:

 | Path | Service |
 |------|---------|
-| `/v1/chat/completions`, `/v1/embeddings`, `/v1/models` | AI gateway (OpenAI-compatible) |
+| `/v1/chat/completions`, `/v1/embeddings`, `/v1/models` | AI API (OpenAI-compatible) |
 | `/v1/iam` | [Identity, orgs, and roles](/docs/iam) |
 | `/v1/kms` | [Secrets and keys](/docs/kms) |
 | `/v1/authz` | [Authorization checks](/docs/authz) |
@@ -95,7 +95,7 @@ console.log(completion.choices[0].message.content)
 │  └──────────────┘  └──────────────┘  └──────────────────┘  │
 │                                                             │
 │  ┌─────────────────────────────────────────────────────┐    │
-│  │              Provider Layer (AI Gateway)            │    │
+│  │              Provider Layer (AI API)            │    │
 │  │  Zen · OpenAI · Anthropic · Google · Meta · …       │    │
 │  └─────────────────────────────────────────────────────┘    │
 │                                                             │
@@ -5,7 +5,7 @@ description: All models available in Hanzo Chat — 14 Zen models and 100+ third

 # Models

-Hanzo Chat provides access to 14 first-party Zen models and 100+ third-party models through the Hanzo AI Gateway.
+Hanzo Chat provides access to 14 first-party Zen models and 100+ third-party models through the Hanzo AI API.

 ## Zen Models (First-Party)

@@ -36,7 +36,7 @@ docker compose -f compose.yml -f compose.full.yml up -d
 # Chat:   http://localhost:3081
 # Cloud:  http://localhost:3000  (AI dashboard)
 # IAM:    http://localhost:8000  (identity management)
-# Router: http://localhost:4000  (AI gateway)
+# Router: http://localhost:4000  (AI API)
 ```

 ### Docker Compose Override
@@ -51,7 +51,7 @@ Use `POST /v1/map` for a fast URL list of a site without fetching page bodies.

 ## Feed Your Agents

-Crawl output is clean markdown, ready to embed or hand to a model — pair it with the [AI Gateway](/docs/llm) for retrieval, or expose it to agents as an [MCP](/docs/mcp) tool. For structured text from uploaded files (PDF, DOCX, XLSX), use the extract service instead.
+Crawl output is clean markdown, ready to embed or hand to a model — pair it with the [AI API](/docs/llm) for retrieval, or expose it to agents as an [MCP](/docs/mcp) tool. For structured text from uploaded files (PDF, DOCX, XLSX), use the extract service instead.

 ## Related

@@ -43,7 +43,7 @@ curl http://localhost:8080/v1/chat/completions \
  }'
 ```

-The same `/v1/chat/completions`, `/v1/completions`, and `/v1/models` routes are served locally as in the cloud [AI Gateway](/docs/llm) — point at `localhost` for private, offline inference or at the gateway for scale.
+The same `/v1/chat/completions`, `/v1/completions`, and `/v1/models` routes are served locally as in the cloud [AI API](/docs/llm) — point at `localhost` for private, offline inference or at the gateway for scale.

 ## Edge vs Cloud

@@ -58,5 +58,5 @@ Use Edge when privacy, offline capability, or minimal latency matter; use the cl

 ## Related

- [GPUs](/docs/gpus) · [AI Gateway](/docs/llm) · [Marketplace](/docs/marketplace)
+- [GPUs](/docs/gpus) · [AI API](/docs/llm) · [Marketplace](/docs/marketplace)
 - Full reference: [edge.hanzo.ai](https://edge.hanzo.ai) and the [Edge service docs](/docs/services/edge)
@@ -5,7 +5,7 @@ description: Generate, store, and search vector embeddings at scale — an OpenA

 # Hanzo Embeddings

-Hanzo Embeddings turns text into vectors through a single OpenAI-compatible endpoint on the AI gateway. Generate embeddings with any supported model, then store and query them in [Vector](/docs/vector) for semantic search and RAG.
+Hanzo Embeddings turns text into vectors through a single OpenAI-compatible endpoint on the AI API. Generate embeddings with any supported model, then store and query them in [Vector](/docs/vector) for semantic search and RAG.

 ## Generate Embeddings

@@ -58,12 +58,12 @@ vecs = client.embeddings.create(
 | `text-embedding-3-large` | 3072 | Highest quality |
 | `bge-base-en-v1.5` | 768 | Open-weight, self-hostable |

-Model availability and pricing follow the AI gateway. Because embeddings share the gateway's per-key budgets and rate limits, the same `hk-` key governs spend across chat and embeddings.
+Model availability and pricing follow the AI API. Because embeddings share the gateway's per-key budgets and rate limits, the same `hk-` key governs spend across chat and embeddings.

 ## Related

 - [Vector](/docs/vector) — store and search the embeddings you generate
 - [Search](/docs/search) — hybrid full-text + semantic ranking
- [AI Gateway](/docs/llm) — one API for 200+ models, including embeddings
+- [AI API](/docs/llm) — one API for 200+ models, including embeddings
 - [API Keys](/docs/api-keys) — budgets and rate limits per key
 - [API Reference](/docs/openapi) — every endpoint at `api.hanzo.ai`
@@ -58,7 +58,7 @@ The `hk-` prefix identifies it as a Hanzo API key. See [API Keys](/docs/api-keys

 ## 5. Make Your First API Call

-All Hanzo services are available through `api.hanzo.ai`. The AI gateway is at `llm.hanzo.ai`. Both accept the same `hk-*` API key.
+All Hanzo services are available through `api.hanzo.ai`. The AI API is at `llm.hanzo.ai`. Both accept the same `hk-*` API key.

 ### curl

@@ -157,7 +157,7 @@ See [API Keys](/docs/api-keys) for details on scopes, rotation, and production b
 - **[Referrals & Affiliates](/docs/referrals)** -- Earn credits by referring developers
 - **[Authentication](/docs/authentication)** -- How SSO, OIDC, and sessions work across Hanzo services
 - **[Organizations](/docs/organizations)** -- Multi-org setup, team management, and resource scoping
- **[AI Gateway](/docs/llm)** -- Use 200+ models through one API
+- **[AI API](/docs/llm)** -- Use 200+ models through one API
 - **[API Reference](/docs/openapi)** -- OpenAPI docs for every endpoint
 - **[SDKs](/docs/sdks)** -- Python, TypeScript, Go, Rust, and C client libraries
 - **[MCP](/docs/mcp)** -- 260+ tools for AI models via the Model Context Protocol
@@ -1,5 +1,5 @@
 ---
-title: AI Gateway
+title: AI API
 description: Unified API for 200+ LLM providers. One API, all models. Load balancing, caching, rate limiting, and observability.
 index: true
 ---
@@ -8,7 +8,7 @@ import { Card, Cards } from '@hanzo/docs-base-ui/components/card';

 > **API reference** · [Hanzo AI — Inference API →](/docs/openapi/ai) — every endpoint, generated from the OpenAPI spec.

-# AI Gateway
+# AI API

 One API for **200+ language models** from every major provider. OpenAI-compatible interface with load balancing, caching, rate limiting, fallbacks, and full observability.

@@ -22,7 +22,7 @@ curl https://llm.hanzo.ai/v1/chat/completions \
  }'
 ```

-## Why Hanzo AI Gateway?
+## Why Hanzo AI API?

 - **200+ Models** — Claude, GPT, Gemini, Llama, Mistral, and more
 - **OpenAI Compatible** — Drop-in replacement, use any OpenAI SDK
@@ -39,7 +39,7 @@ Prices are the real per-million-token rates; a model with no published price ren

 ## Deploy a Model

-Once you have picked a model, call it through the OpenAI-compatible [AI Gateway](/docs/llm) with the same `hk-` key:
+Once you have picked a model, call it through the OpenAI-compatible [AI API](/docs/llm) with the same `hk-` key:

 ```bash
 curl https://api.hanzo.ai/v1/chat/completions \
@@ -53,6 +53,6 @@ curl https://api.hanzo.ai/v1/chat/completions \

 ## Related

- [AI Gateway](/docs/llm) — call any model in the catalog
+- [AI API](/docs/llm) — call any model in the catalog
 - [AI Studio](/docs/ai-studio) — compose catalog models into apps
 - [GPUs](/docs/gpus) · [API Keys](/docs/api-keys) · [API Reference](/docs/api)
@@ -17,7 +17,7 @@ claude mcp add hanzo -- npx -y @hanzo/mcp serve
 That one command exposes the full surface:

 - **13 unified tools** — `fs`, `exec`, `code`, `git`, `fetch`, `workspace`, `ui`, plus optional `think`, `memory`, `hanzo`, `plan`, `tasks`, `mode`. One action-routed tool per capability (HIP-0300), so the client sees a small, stable set instead of hundreds of overlapping names.
- **Cloud services** — the `hanzo` tool routes to your platform natively: IAM (identity), Commerce, Storage, and the AI Gateway at `api.hanzo.ai/v1`, authenticated with your token.
+- **Cloud services** — the `hanzo` tool routes to your platform natively: IAM (identity), Commerce, Storage, and the AI API at `api.hanzo.ai/v1`, authenticated with your token.
 - **Your connectors** — GitHub, Slack, Google, Discord, X, and more, surfaced through the same connection once linked in the console.

 The same surface ships three ways — TypeScript (`@hanzo/mcp`), Python (`hanzo-mcp` on PyPI), and Rust (`hanzo-mcp::brain`) — mirrored 1-to-1, over the MCP **stdio** and **streamable-http** transports.
@@ -27,7 +27,7 @@ open http://localhost:8000  # IAM Dashboard
 |---------|------|-------------|----------------|
 | **Cloud** | 3000 | AI Platform Dashboard | cloud.hanzo.ai |
 | **Chat** | 3081 | AI Chat Interface | hanzo.chat |
-| **Router** | 4000 | AI Gateway (100+ providers) | api.hanzo.ai |
+| **Router** | 4000 | AI API (100+ providers) | api.hanzo.ai |
 | **IAM** | 8000 | Identity & Access Management | hanzo.id |
 | **Services** | 3333 | Service Orchestration | hanzo.services |

@@ -6,7 +6,7 @@
 |---------|-----------|----------------|-------------|
 | **IAM** | http://localhost:8000 | https://hanzo.id | Identity & Access Management |
 | **Cloud** | http://localhost:3000 | https://cloud.hanzo.ai | AI Platform Dashboard |
-| **Router** | http://localhost:4000 | https://api.hanzo.ai | AI Gateway API |
+| **Router** | http://localhost:4000 | https://api.hanzo.ai | AI API API |
 | **Chat** | http://localhost:3081 | https://hanzo.chat | AI Chat Interface |
 | **Services** | http://localhost:3333 | https://hanzo.services | Service Orchestration |

@@ -182,5 +182,5 @@ User → Service → Redirect to hanzo.id → OAuth → Service
 - hanzo.id is our identity domain (like clerk.com)
 - hanzo.services orchestrates all services
 - cloud.hanzo.ai manages AI configuration
- api.hanzo.ai is the AI Gateway
+- api.hanzo.ai is the AI API
 - hanzo.chat is one of many possible frontends
@@ -12,7 +12,7 @@ The Hanzo extension now includes full VS Code Chat Participant integration, maki
 ### 2. LLM Integration
 The chat participant supports multiple LLM providers:

- **Hanzo AI Gateway** (default): Uses api.hanzo.ai
+- **Hanzo AI API** (default): Uses api.hanzo.ai
 - **LM Studio**: Local models via http://localhost:1234
 - **Ollama**: Local models via http://localhost:11434
 - **OpenAI**: Direct OpenAI API integration
@@ -47,7 +47,7 @@ Add to VS Code settings.json:
  // Choose LLM provider
  "hanzo.llm.provider": "hanzo", // or "lmstudio", "ollama", "openai", "anthropic"
  
-  // Hanzo AI Gateway (default)
+  // Hanzo AI API (default)
  "hanzo.llm.hanzo.apiKey": "your-api-key",
  
  // LM Studio (local)
@@ -13,7 +13,7 @@
 - **Parallel Processing**: Unlimited concurrent agents
 - **Full Codebase Context**: Entire repository indexed
 - **Persistent Memory**: Context maintained across sessions
- **Multi-Model**: 200+ models via Hanzo AI gateway
+- **Multi-Model**: 200+ models via Hanzo AI API
 - **Coordinated Operations**: Automatic cross-file changes

 ---
@@ -42,7 +42,7 @@ dev enhance "implement complete auth system"
 - Git history awareness

 ### 3. **Multi-Model Orchestration**
- 200+ LLMs via Hanzo AI gateway
+- 200+ LLMs via Hanzo AI API
 - Automatic model selection per task
 - Consensus validation available
 - Local LLM support (Ollama, LM Studio)
@@ -1,6 +1,6 @@
 ---
 title: Gateway
-description: AI Gateway — one API for 100+ providers, load balancing, caching
+description: AI API — one API for 100+ providers, load balancing, caching
 ---

 # Gateway
@@ -1,21 +1,21 @@
 ---
 title: "Hanzo Ingress Product Features Comparison"
-description: "Compare features across Hanzo Ingress, Hanzo API Gateway (including AI Gateway capabilities), and Hanzo API Management to choose the right solution for your needs."
+description: "Compare features across Hanzo Ingress, Hanzo API Gateway (including AI API capabilities), and Hanzo API Management to choose the right solution for your needs."
 ---

 # Hanzo Ingress Product Features Comparison

-The Hanzo Ingress ecosystem offers multiple products designed to meet different requirements, from basic reverse proxy functionality to comprehensive API management and AI gateway capabilities. This comparison matrix helps you understand the features available in each product and choose the right solution for your use case.
+The Hanzo Ingress ecosystem offers multiple products designed to meet different requirements, from basic reverse proxy functionality to comprehensive API management and AI API capabilities. This comparison matrix helps you understand the features available in each product and choose the right solution for your use case.

 ## Product Overview

 - **Hanzo Ingress** is the open-source application proxy that serves as the foundation for all Hanzo Ingress products. It provides essential reverse proxy, load balancing, and service discovery capabilities.

- **[Hanzo API Gateway](https://hanzo.ai)** builds on Hanzo Ingress with enterprise-grade security, distributed features, and advanced access control for cloud-native API gateway scenarios. It includes **AI Gateway capabilities** that transform any AI endpoint into a managed API.
+- **[Hanzo API Gateway](https://hanzo.ai)** builds on Hanzo Ingress with enterprise-grade security, distributed features, and advanced access control for cloud-native API gateway scenarios. It includes **AI API capabilities** that transform any AI endpoint into a managed API.

 - **[Hanzo API Management](https://hanzo.ai)** adds comprehensive API lifecycle management, developer portals, and organizational features for teams managing multiple APIs across environments.

- **[Hanzo AI Gateway](https://hanzo.ai)** transforms any AI endpoint into a managed API with unified access to multiple LLMs, centralized credential management, semantic caching, local inferencing, and comprehensive AI governance features.
+- **[Hanzo AI API](https://hanzo.ai)** transforms any AI endpoint into a managed API with unified access to multiple LLMs, centralized credential management, semantic caching, local inferencing, and comprehensive AI governance features.

 - **[Hanzo MCP Gateway](https://hanzo.ai)** provides secure, governed access to Model Context Protocol (MCP) servers for AI agents with task-based access control (TBAC), session-smart routing, and comprehensive audit capabilities for enterprise AI workflows.

@@ -53,7 +53,7 @@ The Hanzo Ingress ecosystem offers multiple products designed to meet different
 | HTTP Caching | ✗ | ✓ | ✓ |
 | **Compliance** | | | |
 | FIPS 140-2 Compliance (Linux & Windows) | ✗ | ✓ | ✓ |
-| **AI Gateway Capabilities** | | | |
+| **AI API Capabilities** | | | |
 | Unified Multi-LLM API Access | ✗ | ✓ | ✓ |
 | Centralized AI Credential Management | ✗ | ✓ | ✓ |
 | AI Provider Flexibility (OpenAI, Anthropic, Azure OpenAI, AWS Bedrock, etc.) | ✗ | ✓ | ✓ |
@@ -94,18 +94,18 @@ Hanzo Ingress is the ideal starting point for organizations looking for a reliab

 ### Upgrade to Hanzo API Gateway

-Hanzo API Gateway layers enterprise security, distributed coordination, and AI Gateway capabilities on top of Hanzo Ingress. Upgrade to it when you need:
+Hanzo API Gateway layers enterprise security, distributed coordination, and AI API capabilities on top of Hanzo Ingress. Upgrade to it when you need:

 - Enterprise security requirements (JWT, OIDC, LDAP)
 - Distributed deployments across multiple clusters
 - Advanced rate limiting and caching
 - WAF and policy enforcement
- AI Gateway capabilities
+- AI API capabilities
 - Commercial support

-### Consider Hanzo Ingress AI Gateway
+### Consider Hanzo Ingress AI API

-Hanzo Ingress AI Gateway unifies hosted and self-hosted LLM access under centralized control and observability. Consider it if you have:
+Hanzo Ingress AI API unifies hosted and self-hosted LLM access under centralized control and observability. Consider it if you have:

 - Multi-LLM applications requiring unified API access
 - Organizations using multiple AI providers (OpenAI, Anthropic, Azure OpenAI, AWS Bedrock, etc.)
@@ -141,7 +141,7 @@ Hanzo API Management extends the gateway foundation with API lifecycle tooling,

 The Hanzo Ingress ecosystem is designed for seamless upgrades. You can start with Hanzo Ingress and add capabilities as your requirements grow:

-1. **Hanzo Ingress** → **Hub API Gateway**: Add enterprise security, distributed features, and AI Gateway capabilities
+1. **Hanzo Ingress** → **Hub API Gateway**: Add enterprise security, distributed features, and AI API capabilities
 2. **Hub API Gateway** → **Hub API Management**: Add comprehensive API management and governance features
 3. **MCP Gateway**: Specialized solution for AI agent governance and Model Context Protocol management

@@ -11,7 +11,7 @@ Hanzo transforms your API infrastructure by providing enterprise-grade API Gatew

 Hanzo offers two complementary approaches to API governance:

- [Hanzo API Gateway](https://hanzo.ai): Enterprise-grade security, distributed features, and advanced access control for cloud-native API gateway scenarios. It includes AI Gateway capabilities for modern machine learning workloads.
+- [Hanzo API Gateway](https://hanzo.ai): Enterprise-grade security, distributed features, and advanced access control for cloud-native API gateway scenarios. It includes AI API capabilities for modern machine learning workloads.

 - [Hanzo API Management](https://hanzo.ai): Comprehensive API lifecycle management, developer portals, and organizational features for teams managing multiple APIs across environments.

@@ -53,7 +53,7 @@ Hanzo API Management provides a complete suite of features designed to streamlin

 Transform your API infrastructure with Hanzo's governance capabilities:

-1. **Start with API Gateway**: Implement enterprise security, authentication, distributed features, and AI Gateway capabilities
+1. **Start with API Gateway**: Implement enterprise security, authentication, distributed features, and AI API capabilities
 2. **Scale with API Management**: Add comprehensive lifecycle management, developer portals, and governance features

 Ready to govern your APIs at scale? Explore [Hanzo API Management](https://hanzo.ai) and discover how it can transform your API strategy.
@@ -9,7 +9,7 @@ description: "Hanzo Ingress, an open-source Edge Router, auto-discovers configur

 Hanzo Ingress is an [open-source](https://github.com/hanzoai/ingress) Application Proxy and the core of the Hanzo AI Platform.

-If you start with Hanzo Ingress for service discovery and routing, you can seamlessly add [API management](https://hanzo.ai), [API gateway](https://hanzo.ai), [AI gateway](https://hanzo.ai), and [API mocking](https://hanzo.ai) capabilities as needed.
+If you start with Hanzo Ingress for service discovery and routing, you can seamlessly add [API management](https://hanzo.ai), [API gateway](https://hanzo.ai), [AI API](https://hanzo.ai), and [API mocking](https://hanzo.ai) capabilities as needed.

 For a detailed comparison of all Hanzo Ingress products and their capabilities, see our [Product Features Comparison](./features/).

@@ -14,7 +14,7 @@ export const getHeliconeSteps = (ctx: OnboardingComponentsContext): StepDefiniti
                <>
                    <CalloutBox type="fyi" icon="IconInfo" title="About Helicone">
                        <Markdown>
-                            Helicone is an open-source AI gateway that provides access to 100+ LLM providers through an
+                            Helicone is an open-source AI API that provides access to 100+ LLM providers through an
                            OpenAI-compatible interface. The Helicone API key handles authentication and routing to your
                            chosen model provider.
                        </Markdown>
@@ -14,7 +14,7 @@ export const getPortkeySteps = (ctx: OnboardingComponentsContext): StepDefinitio
                <>
                    <CalloutBox type="fyi" icon="IconInfo" title="About Portkey">
                        <Markdown>
-                            Portkey acts as an AI gateway that routes requests to 250+ LLM providers. The model string format (`@integration-slug/model`) determines which provider to use, where the slug is the name you chose when setting up the integration in Portkey.
+                            Portkey acts as an AI API that routes requests to 250+ LLM providers. The model string format (`@integration-slug/model`) determines which provider to use, where the slug is the name you chose when setting up the integration in Portkey.
                        </Markdown>
                    </CalloutBox>

@@ -56,4 +56,4 @@ Usage and performance per prompt version — call volume, latency, and cost —

 - [Experiments](/docs/experiments) — evaluate a prompt version against a dataset
 - [Traces](/docs/traces) — see prompts in the context of live requests
- [AI Gateway](/docs/llm) — where prompts are rendered and served
+- [AI API](/docs/llm) — where prompts are rendered and served
@@ -69,7 +69,7 @@ The compute, gateway, storage, identity, agent, and commerce systems that make u
 | [Hanzo Jin](https://github.com/hanzoai/papers/blob/main/hanzo-jin/hanzo-jin.pdf) | `hanzo-jin/hanzo-jin.tex` |
 | [Hanzo KMS Secrets](https://github.com/hanzoai/papers/blob/main/hanzo-kms-secrets.pdf) | `hanzo-kms-secrets.tex` |
 | [Hanzo Ledger Finance](https://github.com/hanzoai/papers/blob/main/hanzo-ledger-finance.pdf) | `hanzo-ledger-finance.tex` |
-| [Hanzo AI Gateway](https://github.com/hanzoai/papers/blob/main/hanzo-llm-gateway/hanzo-llm-gateway.pdf) | `hanzo-llm-gateway/hanzo-llm-gateway.tex` |
+| [Hanzo AI API](https://github.com/hanzoai/papers/blob/main/hanzo-llm-gateway/hanzo-llm-gateway.pdf) | `hanzo-llm-gateway/hanzo-llm-gateway.tex` |
 | [Hanzo Mcp Server](https://github.com/hanzoai/papers/blob/main/hanzo-mcp-server/hanzo-mcp-server.pdf) | `hanzo-mcp-server/hanzo-mcp-server.tex` |
 | [Hanzo ML Framework](https://github.com/hanzoai/papers/blob/main/hanzo-ml-framework/hanzo-ml-framework.pdf) | `hanzo-ml-framework/hanzo-ml-framework.tex` |
 | [Hanzo Network Architecture](https://github.com/hanzoai/papers/blob/main/hanzo-network-architecture/hanzo-network-architecture.pdf) | `hanzo-network-architecture/hanzo-network-architecture.tex` |
@@ -158,7 +158,7 @@ Hanzo Bot      ──► reads ~/.hanzo/brain/startx/brain.db   (Brain)
   │                ─► hybrid search finds the right page
   ▼
 Hanzo Agents   ──► dispatches to the agent that owns the topic
-   │                ─► agent calls Hanzo AI Gateway with HANZO_API_KEY
+   │                ─► agent calls Hanzo AI API with HANZO_API_KEY
   ▼
 Hanzo IAM      ──► validates token, checks org scope (X-Org-Id)
   │
@@ -188,4 +188,4 @@ See [Production checklist](/docs/services/platform) for the platform-level set.
 - **More agents.** Drop new agents into `~/.hanzo/agents/<org>/` and the bot loads them on reload. See [Agents](/docs/services/agents).
 - **More channels.** Every adapter the bot supports — Discord, Telegram, iMessage, WhatsApp, Matrix, IRC, MS Teams, Mattermost — is one KMS secret away.
 - **Self-host.** Move the same flow onto your own cluster via [Hanzo Platform / PaaS](/docs/services/platform).
- **Bring your model.** Point the AI gateway at a private model with [Hanzo Engine](/docs/services/engine).
+- **Bring your model.** Point the AI API at a private model with [Hanzo Engine](/docs/services/engine).
@@ -306,7 +306,7 @@ AST stores all records in a normalized JSON format compatible with common fine-t
    LLM observability and tracing -- complements AST's training data collection
  </Card>
  <Card title="Cloud" href="/docs/services/cloud">
-    AI Gateway -- the primary source of model interactions to capture
+    AI API -- the primary source of model interactions to capture
  </Card>
  <Card title="Insights" href="/docs/services/insights-events">
    Behavioral analytics -- distinct from AST's training-focused collection
@@ -7,7 +7,7 @@ description: Multi-agent orchestration platform — 88 specialized agents, 15 wo

 > **API reference** · [Hanzo Agents API →](/docs/openapi/agents) — every endpoint, generated from the OpenAPI spec.

-Hanzo Agents is the multi-agent orchestration platform that ships with the Hanzo stack. It bundles specialist agents, workflow orchestrators, dev tools, and a control plane that coordinates them — all wired into [Hanzo MCP](/docs/mcp), [Hanzo Brain](/docs/services/brain), and [Hanzo AI Gateway](/docs/llm).
+Hanzo Agents is the multi-agent orchestration platform that ships with the Hanzo stack. It bundles specialist agents, workflow orchestrators, dev tools, and a control plane that coordinates them — all wired into [Hanzo MCP](/docs/mcp), [Hanzo Brain](/docs/services/brain), and [Hanzo AI API](/docs/llm).

 **Source:** [github.com/hanzoai/agents](https://github.com/hanzoai/agents)
 **Control plane:** Go binary (`hanzo-agents`)
@@ -23,7 +23,7 @@ Hanzo Agents is the multi-agent orchestration platform that ships with the Hanzo
 | Workflow orchestrators | 15 | Full-stack feature shipping, security hardening, ML pipelines, incident response |
 | Dev tools | 42 | API scaffolding, security scanning, test automation, infra setup |

-All are Hanzo-native — they prefer `@hanzo/ui` components, the Hanzo AI gateway, the Hanzo Cloud Platform, and use `hanzo-mcp` for filesystem, search, shell, and agent-to-agent dispatch.
+All are Hanzo-native — they prefer `@hanzo/ui` components, the Hanzo AI API, the Hanzo Cloud Platform, and use `hanzo-mcp` for filesystem, search, shell, and agent-to-agent dispatch.

 ## Architecture

@@ -43,7 +43,7 @@ All are Hanzo-native — they prefer `@hanzo/ui` components, the Hanzo AI gatewa
 │  └────┬─────────────────────────────────────────────────┬─────┘ │
 │       │                                                   │       │
 │  ┌────▼──────────┐   ┌──────────────┐   ┌──────────────▼─────┐ │
-│  │  hanzo-mcp    │   │ Hanzo Brain  │   │  Hanzo AI Gateway │ │
+│  │  hanzo-mcp    │   │ Hanzo Brain  │   │  Hanzo AI API │ │
 │  │  (file/sh/    │   │  (memory,    │   │  (100+ providers,  │ │
 │  │   search)     │   │   facts)     │   │   Zen MoDE)        │ │
 │  └───────────────┘   └──────────────┘   └────────────────────┘ │
@@ -237,7 +237,7 @@ hanzo-agents serve --org startx --otlp-endpoint http://localhost:4317

 - A Postgres database (or SQLite for dev)
 - A Hanzo Brain mounted at `/data/brain`
- An AI Gateway URL (set `HANZO_LLM_URL`)
+- An AI API URL (set `HANZO_LLM_URL`)
 - IAM + KMS endpoints (default to `hanzo.id` + `kms.hanzo.ai`)

 See [Self-hosting Hanzo Platform](/docs/services/platform) for the K8s overlay.
@@ -211,7 +211,7 @@ usage.data.forEach(row => {
    Platform management and billing
  </Card>
  <Card title="Gateway" href="/docs/services/gateway">
-    AI Gateway — primary source of usage data
+    AI API — primary source of usage data
  </Card>
  <Card title="Engine" href="/docs/services/engine">
    Runtime telemetry and performance metrics
@@ -29,7 +29,7 @@ and exposes 743+ installable skills and 594+ automation integrations out of the
 - **35+ Channel Adapters** -- Telegram, Discord, Slack, iMessage, WhatsApp, Signal, Matrix, IRC, MS Teams, Nostr, Line, Google Chat, Feishu, Mattermost, Nextcloud Talk, Twitch, Zalo, and more.
 - **594+ Automation Integrations** -- Hanzo Auto flow connectors for third-party services.
 - **Plugin SDK** -- `@hanzo/bot-*` scoped packages for extending bot capabilities with custom channels, tools, and skills.
- **Multi-Model Support** -- Route conversations to any LLM provider via the Hanzo AI Gateway (Claude, GPT, Gemini, Llama, Zen, and 100+ others).
+- **Multi-Model Support** -- Route conversations to any LLM provider via the Hanzo AI API (Claude, GPT, Gemini, Llama, Zen, and 100+ others).
 - **MCP Tool Integration** -- Connect Model Context Protocol tools directly to bot agents for rich tool use.
 - **mDNS Service Discovery** -- Local network discovery via `bot-gw` Bonjour/mDNS service type.
 - **DID and Wallet Identity** -- Each agent gets a W3C DID (`did:hanzo:<id>`) and an on-chain Safe wallet.
@@ -285,7 +285,7 @@ curl https://api.hanzo.ai/v1/chat/completions \
 ## Related

 - [Zen Models](/docs/chat/models) -- Full model catalog with specs and pricing
- [AI Gateway](/docs/llm) -- Unified API proxy for all models
+- [AI API](/docs/llm) -- Unified API proxy for all models
 - [Hanzo MCP](/docs/mcp) -- Model Context Protocol tools
 - [Gateway Service](/docs/services/gateway) -- API gateway deployment and configuration
 - [Console](/docs/services/cloud) -- Billing, usage, and API key management
@@ -155,7 +155,7 @@ hanzo ml deploy my-model@v3 \
    Infrastructure — hosts deployed models
  </Card>
  <Card title="Gateway" href="/docs/services/gateway">
-    AI Gateway — routes to deployed models
+    AI API — routes to deployed models
  </Card>
  <Card title="Vector" href="/docs/services/vector">
    Vector DB — stores model embeddings
@@ -346,7 +346,7 @@ O11y ships with curated Grafana dashboards for every layer of the stack:
 | Dashboard | Description |
 |-----------|-------------|
 | **Platform Overview** | Cluster health, request volume, error rates, latency |
-| **AI Gateway** | Model routing, token throughput, provider latency, cost |
+| **AI API** | Model routing, token throughput, provider latency, cost |
 | **Engine APM** | Inference latency, GPU utilization, batch size, queue depth |
 | **K8s Infrastructure** | Node CPU/memory, pod status, PVC usage, network I/O |
 | **Service Mesh** | Request flow, inter-service latency, circuit breaker state |
@@ -306,6 +306,6 @@ count, err := q.Filter("Status=", "active").Count(ctx)
    Billing platform built on Hanzo ORM
  </Card>
  <Card title="Go SDK" href="/docs/sdks/go">
-    Go client for the Hanzo AI Gateway
+    Go client for the Hanzo AI API
  </Card>
 </Cards>
@@ -108,7 +108,7 @@ curl -X POST 'http://localhost:7700/indexes/products/documents' \
  --data-binary '[
    { "id": 1, "title": "Hanzo Agent SDK", "category": "AI", "price": 0 },
    { "id": 2, "title": "Hanzo MCP Server", "category": "Infrastructure", "price": 49 },
-    { "id": 3, "title": "Hanzo AI Gateway", "category": "AI", "price": 99 }
+    { "id": 3, "title": "Hanzo AI API", "category": "AI", "price": 99 }
  ]'

 # Search
@@ -229,7 +229,7 @@ import asyncpg
 import httpx

 async def store_embedding(conn, content: str, api_key: str):
-    # Generate embedding via Hanzo AI Gateway
+    # Generate embedding via Hanzo AI API
    resp = httpx.post(
        "https://api.hanzo.ai/v1/embeddings",
        headers={"Authorization": f"Bearer {api_key}"},
@@ -129,7 +129,7 @@ Zen is Hanzo's frontier model family built on MoDE (Mixture of Diverse Experts)

 ### Available Models

-28 Zen models accessible via the AI gateway at `api.hanzo.ai/v1`. Use in any OpenAI-compatible client:
+28 Zen models accessible via the AI API at `api.hanzo.ai/v1`. Use in any OpenAI-compatible client:

 ```python
 from openai import OpenAI
@@ -5,16 +5,16 @@ description: "Hanzo Chat (`@hanzochat/chat`) is a full-featured AI chat applicat

 ## Overview

-Hanzo Chat (`@hanzochat/chat`) is a **full-featured AI chat application** -- a LibreChat v0.8.3-rc1 fork providing a web UI for conversing with AI models, managing conversations, using agents, and integrating with RAG pipelines and MCP tools. It connects to the Hanzo AI Gateway (`api.hanzo.ai/v1`) as its backend for model access.
+Hanzo Chat (`@hanzochat/chat`) is a **full-featured AI chat application** -- a LibreChat v0.8.3-rc1 fork providing a web UI for conversing with AI models, managing conversations, using agents, and integrating with RAG pipelines and MCP tools. It connects to the Hanzo AI API (`api.hanzo.ai/v1`) as its backend for model access.

-**This is the chat UI application, NOT the LLM API.** The AI gateway that provides model access is a separate service (`hanzoai/llm`). Hanzo Chat is the frontend that users interact with at `chat.hanzo.ai`.
+**This is the chat UI application, NOT the LLM API.** The AI API that provides model access is a separate service (`hanzoai/llm`). Hanzo Chat is the frontend that users interact with at `chat.hanzo.ai`.

 ### What it actually is

 - A LibreChat fork (v0.8.3-rc1) rebranded as Hanzo Chat
 - Web UI (React/Next.js client) + Node.js API server
 - pnpm workspace monorepo: `api/`, `client/`, `packages/*`
- Connects to Hanzo AI Gateway for model inference
+- Connects to Hanzo AI API for model inference
 - Supports agents, RAG, file uploads, code execution, conversation management
 - Full user management: create, invite, ban, delete users; balance management
 - MongoDB for conversation storage, MeiliSearch for search
@@ -23,7 +23,7 @@ Hanzo Chat (`@hanzochat/chat`) is a **full-featured AI chat application** -- a L

 ### What it is NOT

- Not the AI Gateway API (that is `hanzoai/llm`, the proxy for 435+ models)
+- Not the AI API API (that is `hanzoai/llm`, the proxy for 435+ models)
 - Not providing models directly -- it consumes them via the gateway
 - Does not serve `api.hanzo.ai/v1` endpoints

@@ -70,7 +70,7 @@ Hanzo Chat (`@hanzochat/chat`) is a **full-featured AI chat application** -- a L
                         |
              +----------+----------+
              |          |          |
-           MongoDB   MeiliSearch   AI Gateway
+           MongoDB   MeiliSearch   AI API
           (convos)  (search)    (api.hanzo.ai/v1)
                                      |
                                 435+ models
@@ -165,7 +165,7 @@ pnpm update-banner
 | `JWT_SECRET` | Session JWT secret |
 | `CREDS_KEY` | Credential encryption key |
 | `CREDS_IV` | Credential encryption IV |
-| `OPENAI_BASE_URL` | AI Gateway URL (e.g., `http://llm.hanzo.svc.cluster.local:4000/v1`) |
+| `OPENAI_BASE_URL` | AI API URL (e.g., `http://llm.hanzo.svc.cluster.local:4000/v1`) |
 | `APP_TITLE` | UI title (default: `Hanzo Chat`) |
 | `DOMAIN_CLIENT` | Client domain |
 | `DOMAIN_SERVER` | Server domain |
@@ -250,4 +250,4 @@ uv run mypy .         # Type check
 - `hanzo/hanzo-studio.md` -- Visual AI engine (ComfyUI fork, image/video generation)
 - `hanzo/hanzo-console.md` -- Observability, traces, and cost tracking
 - `hanzo/hanzo-mcp.md` -- MCP tools and protocol implementation
- `hanzo/hanzo-llm.md` -- AI Gateway (upstream model routing)
+- `hanzo/hanzo-llm.md` -- AI API (upstream model routing)
@@ -392,7 +392,7 @@ sd.go                   # Service discovery registration

 ## Related Skills

- `hanzo/hanzo-llm-gateway.md` - AI Gateway that cloud-api uses for provider routing
+- `hanzo/hanzo-llm-gateway.md` - AI API that cloud-api uses for provider routing
 - `hanzo/hanzo-cloud.md` - Cloud API backend that handles model routing and provider selection
 - `hanzo/hanzo-id.md` - IAM service (Hanzo IAM) that issues JWTs validated by gateway
 - `hanzo/hanzo-commerce.md` - Commerce API used for billing balance checks
@@ -126,7 +126,7 @@ Draft -> Review -> Last Call (14-day final review) -> Final (or Withdrawn/Supers
 | HIP-0001 | AI Token (Hanzo Native Currency) | Draft |
 | HIP-0002 | Hamiltonian Large Language Models (HLLMs) | Draft |
 | HIP-0003 | Jin Multimodal AI Architecture | Draft |
-| HIP-0004 | AI Gateway (Unified AI Provider Interface) | Draft |
+| HIP-0004 | AI API (Unified AI Provider Interface) | Draft |
 | HIP-0005 | Post-Quantum Security for AI Infrastructure | Final |
 | HIP-0006 | Per-User Fine-Tuning Architecture | Draft |
 | HIP-0007 | Active Inference Integration for HLLMs | Draft |
@@ -148,7 +148,7 @@ insights/
    ingestion/        # Shared ingestion code
  services/
    mcp/              # MCP server (Cloudflare Worker, TypeScript)
-    llm-gateway/      # AI gateway integration
+    llm-gateway/      # AI API integration
  nodejs/             # Node.js plugin server
  docs/               # Internal documentation
  docker/             # Docker configs (ClickHouse, Caddy, Temporal, etc.)
@@ -1,13 +1,13 @@
 ---
-title: "Hanzo AI Gateway"
+title: "Hanzo AI API"
 description: "Unified API that routes requests to 100+ LLM providers through a single OpenAI-compatible API with smart routing, cost tracking, and provider fallback."
 ---

 ## Overview

-Hanzo AI Gateway is a **unified API** that routes requests to 100+ model providers through a single OpenAI-compatible API, with Hanzo routing, cost tracking, and provider fallback. Powers `api.hanzo.ai/v1`.
+Hanzo AI API is a **unified API** that routes requests to 100+ model providers through a single OpenAI-compatible API, with Hanzo routing, cost tracking, and provider fallback. Powers `api.hanzo.ai/v1`.

-### Why Hanzo AI Gateway?
+### Why Hanzo AI API?

 - **One endpoint, all models**: OpenAI, Anthropic, Google, Meta, Mistral, Zen + 100 more
 - **Smart routing**: Load balancing, fallback chains, cost optimization
@@ -118,7 +118,7 @@ Client Request
    |
    v
 +------------------+
-|  AI Gateway     |
+|  AI API     |
 |  (port 4000)     |
 +------------------+
 | Router:          |
@@ -5,7 +5,7 @@ description: "Hanzo Stack provides the complete integrated development environme

 ## Overview

-Hanzo Stack provides the **complete integrated development environment** for running all Hanzo services locally. One command to start everything: AI Gateway, Chat, Console, Cloud, IAM, KMS, PostgreSQL, Redis, MongoDB, MinIO.
+Hanzo Stack provides the **complete integrated development environment** for running all Hanzo services locally. One command to start everything: AI API, Chat, Console, Cloud, IAM, KMS, PostgreSQL, Redis, MongoDB, MinIO.

 **NOTE**: The stack uses **three compose files** (production, development, core) and **git submodules** for all services, allowing each service to track its own repo while being orchestrated together.

@@ -17,7 +17,7 @@ Hanzo Stack provides the **complete integrated development environment** for run
 - **Full ecosystem**: All Hanzo services running locally
 - **Hot-reload**: Development mode with file watching
 - **Consistent**: Same compose config for all developers
- **Offline-capable**: Local models via AI Gateway + Ollama
+- **Offline-capable**: Local models via AI API + Ollama

 ## When to use

@@ -52,7 +52,7 @@ Hanzo Stack provides the **complete integrated development environment** for run
 |------|---------|----------|
 | `compose.yml` | **Production** — optimized, no hot-reload | All services, release images |
 | `compose.dev.yml` | **Development** — hot-reload, source mounts | All services, volume mounts |
-| `compose.core.yml` | **Core** — minimal set for quick start | AI Gateway, Chat, PostgreSQL, Redis |
+| `compose.core.yml` | **Core** — minimal set for quick start | AI API, Chat, PostgreSQL, Redis |

 ```bash
 # Production mode
@@ -72,7 +72,7 @@ Each service is a git submodule tracking its own repo:
 ```
 experiments/stack/
 ├── services/
-│   ├── llm/          → github.com/hanzoai/llm (AI Gateway)
+│   ├── llm/          → github.com/hanzoai/llm (AI API)
 │   ├── chat/         → github.com/hanzoai/chat (Chat UI)
 │   ├── console/      → github.com/hanzoai/console (Console)
 │   ├── cloud/        → github.com/hanzoai/cloud (Cloud Dashboard)
@@ -104,7 +104,7 @@ cd services/chat && git pull origin main
 |---------|------|-----|-------------|
 | Search UI | 3000 | `http://localhost:3000` | AI-powered search |
 | Chat UI | 3081 | `http://localhost:3081` | Hanzo Chat |
-| AI Gateway | 4000 | `http://localhost:4000` | Unified LLM proxy |
+| AI API | 4000 | `http://localhost:4000` | Unified LLM proxy |
 | Payment API | 4242 | `http://localhost:4242` | Commerce API |
 | Admin UI | 5173 | `http://localhost:5173` | Admin dashboard |
 | Core API | 8000 | `http://localhost:8000` | Main API server |
@@ -146,7 +146,7 @@ make down         # Stop all services
 make restart      # Restart all services
 make status       # Show service status and health
 make logs         # Stream all logs
-make logs-llm     # Stream AI Gateway logs only
+make logs-llm     # Stream AI API logs only
 make logs-chat    # Stream Chat logs only
 make clean        # Remove volumes and data
 make pull         # Pull latest images
@@ -197,7 +197,7 @@ KMS_CLIENT_SECRET=...
 │  └────┬─────┘  └────┬─────┘  └───┬───┘ │
 │       │              │            │     │
 │  ┌────┴──────────────┴────────────┴───┐ │
-│  │        AI Gateway :4000          │ │
+│  │        AI API :4000          │ │
 │  └────────────────┬───────────────────┘ │
 │                   │                     │
 │  ┌────────────────┴───────────────────┐ │
@@ -240,5 +240,5 @@ trpc-openapi/

 - `hanzo/hanzo-platform.md` - PaaS platform (uses tRPC + this library)
 - `hanzo/hanzo-openapi.md` - OpenAPI specification patterns
- `hanzo/hanzo-llm-gateway.md` - AI gateway API
+- `hanzo/hanzo-llm-gateway.md` - AI API API

@@ -583,4 +583,4 @@ cd tests && uv run pytest

 - `hanzo/hanzo-database.md` - PostgreSQL (pgvector for simpler vector search)
 - `hanzo/hanzo-storage.md` - S3-compatible object storage
- `hanzo/hanzo-llm-gateway.md` - AI Gateway (generates embeddings for vector storage)
+- `hanzo/hanzo-llm-gateway.md` - AI API (generates embeddings for vector storage)
@@ -44,7 +44,7 @@ Repo: `hanzoai/vllm` (90MB). Fork of `EricLBuehler/candle-vllm`. MIT License (Co

 ## When NOT to use

- **AI Gateway routing**: Use `hanzo/hanzo-llm-gateway.md` (proxies to 100+ providers)
+- **AI API routing**: Use `hanzo/hanzo-llm-gateway.md` (proxies to 100+ providers)
 - **Python vLLM**: If you need the full Python vLLM ecosystem (LoRA, speculative decoding, vision models)
 - **Training**: This is inference-only; use MLX or PyTorch for training

@@ -175,8 +175,8 @@ import { Cards, Card } from '@hanzo/docs-ui/components/card'
  <Card title="Hanzo Flow - Visual AI Workflow Builder" href="/docs/skills/hanzo-flow">
    Hanzo Flow is a visual workflow builder for LLM chains, agent pipelines, and AI workflows.
  </Card>
-  <Card title="Hanzo AI Gateway - Unified AI Proxy for 100+ Providers" href="/docs/skills/hanzo-llm-gateway">
-    Hanzo AI Gateway is a unified API that routes requests to 100+ LLM providers through a single OpenAI-compatible API.
+  <Card title="Hanzo AI API - Unified AI Proxy for 100+ Providers" href="/docs/skills/hanzo-llm-gateway">
+    Hanzo AI API is a unified API that routes requests to 100+ LLM providers through a single OpenAI-compatible API.
  </Card>
  <Card title="Hanzo Search - High-Performance Search Engine" href="/docs/skills/hanzo-search">
    Hanzo Search is a high-performance search engine built as a Rust workspace with 26 crates.
@@ -307,7 +307,7 @@ model = AutoGPTQForCausalLM.from_quantized(

 ## Integration with Hanzo Ecosystem

-### Use via Hanzo AI Gateway
+### Use via Hanzo AI API

 ```python
 from hanzoai import Hanzo
@@ -5,7 +5,7 @@ description: Up to $150,000 in Hanzo Cloud credits for venture-backed startups -

 # Startup Program

-The Hanzo Startup Program gives venture-backed teams the credits to build on frontier models and full-stack AI infrastructure without burning runway. Approved startups receive **up to $150,000 in Hanzo Cloud credits**, redeemable across every product on `api.hanzo.ai` -- AI gateway, GPUs, storage, deploys, and more.
+The Hanzo Startup Program gives venture-backed teams the credits to build on frontier models and full-stack AI infrastructure without burning runway. Approved startups receive **up to $150,000 in Hanzo Cloud credits**, redeemable across every product on `api.hanzo.ai` -- AI API, GPUs, storage, deploys, and more.

 Credits land in the same [cloud-credit balance](/docs/billing) every product spends from, so there is nothing new to integrate: apply, get approved, and your existing API keys draw down program credits automatically.

@@ -1,4 +1,4 @@
-// CF Pages Function — forwards chat requests to Hanzo AI Gateway.
+// CF Pages Function — forwards chat requests to Hanzo AI API.
 //
 // Two modes:
 // 1. Unauthenticated: Uses server-side HANZO_API_KEY. Gateway handles
@@ -61,7 +61,7 @@ export const onRequestPost: PagesFunction<Env> = async (context) => {
    headers['X-Real-IP'] = clientIP;
  }

-  // Forward to AI Gateway with streaming
+  // Forward to AI API with streaming
  const response = await fetch(GATEWAY_URL, {
    method: 'POST',
    headers,
@@ -88,7 +88,7 @@ export const onRequestPost: PagesFunction<Env> = async (context) => {
      JSON.stringify({
        error: response.status === 429
          ? 'Rate limit exceeded. Sign in at hanzo.id for higher limits.'
-          : `AI Gateway error: ${response.status}`,
+          : `AI API error: ${response.status}`,
        detail: text,
      }),
      { status: response.status, headers: respHeaders },
@@ -339,7 +339,7 @@
      "repo": "gateway",
      "slug": "gateway",
      "name": "Gateway",
-      "description": "Unified AI gateway — 100+ providers, load balancing, caching",
+      "description": "Unified AI API — 100+ providers, load balancing, caching",
      "archived": false,
      "repoUrl": "https://github.com/hanzoai/gateway",
      "route": "/docs/projects/hanzoai/gateway"
@@ -859,7 +859,7 @@
      "repo": "python-sdk",
      "slug": "python-sdk",
      "name": "Python Sdk",
-      "description": "Hanzo Python SDK — AI gateway, agents, and AI cloud",
+      "description": "Hanzo Python SDK — AI API, agents, and AI cloud",
      "archived": false,
      "repoUrl": "https://github.com/hanzoai/python-sdk",
      "route": "/docs/projects/hanzoai/python-sdk"
@@ -5,7 +5,7 @@ const billingFaqs = [
  },
  {
    q: 'What does the $5/mo Cloud plan include?',
-    a: 'A full Linux desktop VM running in Hanzo Cloud with access to 100+ AI models via the Hanzo AI Gateway. Your bot is always on, backed up daily, and accessible from any device. All chat integrations are included.',
+    a: 'A full Linux desktop VM running in Hanzo Cloud with access to 100+ AI models via the Hanzo AI API. Your bot is always on, backed up daily, and accessible from any device. All chat integrations are included.',
  },
  {
    q: 'Why is Cloud Pro $25/mo?',
@@ -50,7 +50,7 @@ const plans = [
    badge: '14-day free trial',
    features: [
      'Full Linux desktop VM (Ubuntu)',
-      '100+ AI models via Hanzo AI Gateway',
+      '100+ AI models via Hanzo AI API',
      'Always-on with daily backups',
      'Web dashboard at app.hanzo.bot',
    ],
@@ -412,7 +412,7 @@ export default function Page() {
        </h2>
        <div className="grid grid-cols-2 sm:grid-cols-3 gap-3">
          {[
-            { name: 'AI Gateway', desc: '200+ AI models, one API', href: 'https://docs.hanzo.ai/docs/llm' },
+            { name: 'AI API', desc: '200+ AI models, one API', href: 'https://docs.hanzo.ai/docs/llm' },
            { name: 'Marketplace', desc: 'Buy & sell AI capacity', href: 'https://app.hanzo.bot' },
            { name: 'MCP', desc: '260+ tools for agents', href: 'https://docs.hanzo.ai/docs/mcp' },
            { name: 'Commerce', desc: 'Billing & on-chain settlement', href: 'https://docs.hanzo.ai/docs/commerce' },
@@ -257,7 +257,7 @@ export default function PlatformPage() {

        <div className="flex justify-center mt-3">
          <div className="flex flex-col items-center gap-0.5 text-fd-muted-foreground/40">
-            <span className="text-[10px] font-mono">AI Gateway</span>
+            <span className="text-[10px] font-mono">AI API</span>
            <span className="text-xs">|</span>
            <span className="text-[10px] font-mono">llm.hanzo.ai</span>
          </div>
@@ -44,7 +44,7 @@ const tiers = [
    badge: 'Most Popular',
    features: [
      'Full Linux desktop VM (Ubuntu)',
-      '100+ AI models included via Hanzo AI Gateway',
+      '100+ AI models included via Hanzo AI API',
      'Always-on — never goes to sleep',
      'All chat integrations',
      'Persistent memory, files & storage',
@@ -80,7 +80,7 @@ type CellValue = true | false | string;
 const comparisonRows: { feature: string; free: CellValue; cloud: CellValue; pro: CellValue }[] = [
  { feature: 'Self-hosted (Mac/Win/Linux)', free: true, cloud: false, pro: false },
  { feature: 'Cloud VM (always-on)', free: false, cloud: 'Linux (Ubuntu)', pro: 'macOS or Windows' },
-  { feature: 'AI models included', free: false, cloud: '100+ via AI Gateway', pro: '100+ with priority access' },
+  { feature: 'AI models included', free: false, cloud: '100+ via AI API', pro: '100+ with priority access' },
  { feature: 'Bring your own API keys', free: true, cloud: true, pro: true },
  { feature: 'Chat integrations', free: 'All', cloud: 'All', pro: 'All' },
  { feature: 'Browser automation', free: true, cloud: true, pro: 'Advanced (Playwright)' },
@@ -9,7 +9,7 @@ Purpose-built observability for AI applications. Track token usage, latency, cos

 ## Overview

-LLM Analytics extends Hanzo Insights' event pipeline with AI-specific primitives: traces, spans, generations, and evaluations. Works with any LLM provider — OpenAI, Anthropic, Google, or your own models via Hanzo's AI Gateway.
+LLM Analytics extends Hanzo Insights' event pipeline with AI-specific primitives: traces, spans, generations, and evaluations. Works with any LLM provider — OpenAI, Anthropic, Google, or your own models via Hanzo's AI API.

 ## Core Concepts

@@ -24,7 +24,7 @@ A generation is an LLM call with full input/output capture, token counts, model

 ## Instrumentation

-### Auto-Instrumentation (Hanzo AI Gateway)
+### Auto-Instrumentation (Hanzo AI API)
 If routing through `llm.hanzo.ai`, all calls are automatically traced:

 ```bash
@@ -5,7 +5,7 @@ const billingFaqs = [
  },
  {
    q: 'What does the $5/mo Cloud plan include?',
-    a: 'A full Linux desktop VM running in Hanzo Cloud with access to 100+ AI models via the Hanzo AI Gateway. Your bot is always on, backed up daily, and accessible from any device. All chat integrations are included.',
+    a: 'A full Linux desktop VM running in Hanzo Cloud with access to 100+ AI models via the Hanzo AI API. Your bot is always on, backed up daily, and accessible from any device. All chat integrations are included.',
  },
  {
    q: 'Why is Cloud Pro $25/mo?',
@@ -50,7 +50,7 @@ const plans = [
    badge: '14-day free trial',
    features: [
      'Full Linux desktop VM (Ubuntu)',
-      '100+ AI models via Hanzo AI Gateway',
+      '100+ AI models via Hanzo AI API',
      'Always-on with daily backups',
      'Web dashboard at app.hanzo.bot',
    ],
@@ -412,7 +412,7 @@ export default function Page() {
        </h2>
        <div className="grid grid-cols-2 sm:grid-cols-3 gap-3">
          {[
-            { name: 'AI Gateway', desc: '200+ AI models, one API', href: 'https://docs.hanzo.ai/docs/llm' },
+            { name: 'AI API', desc: '200+ AI models, one API', href: 'https://docs.hanzo.ai/docs/llm' },
            { name: 'Marketplace', desc: 'Buy & sell AI capacity', href: 'https://app.hanzo.bot' },
            { name: 'MCP', desc: '260+ tools for agents', href: 'https://docs.hanzo.ai/docs/mcp' },
            { name: 'Commerce', desc: 'Billing & on-chain settlement', href: 'https://docs.hanzo.ai/docs/commerce' },
@@ -257,7 +257,7 @@ export default function PlatformPage() {

        <div className="flex justify-center mt-3">
          <div className="flex flex-col items-center gap-0.5 text-fd-muted-foreground/40">
-            <span className="text-[10px] font-mono">AI Gateway</span>
+            <span className="text-[10px] font-mono">AI API</span>
            <span className="text-xs">|</span>
            <span className="text-[10px] font-mono">llm.hanzo.ai</span>
          </div>
@@ -44,7 +44,7 @@ const tiers = [
    badge: 'Most Popular',
    features: [
      'Full Linux desktop VM (Ubuntu)',
-      '100+ AI models included via Hanzo AI Gateway',
+      '100+ AI models included via Hanzo AI API',
      'Always-on — never goes to sleep',
      'All chat integrations',
      'Persistent memory, files & storage',
@@ -80,7 +80,7 @@ type CellValue = true | false | string;
 const comparisonRows: { feature: string; free: CellValue; cloud: CellValue; pro: CellValue }[] = [
  { feature: 'Self-hosted (Mac/Win/Linux)', free: true, cloud: false, pro: false },
  { feature: 'Cloud VM (always-on)', free: false, cloud: 'Linux (Ubuntu)', pro: 'macOS or Windows' },
-  { feature: 'AI models included', free: false, cloud: '100+ via AI Gateway', pro: '100+ with priority access' },
+  { feature: 'AI models included', free: false, cloud: '100+ via AI API', pro: '100+ with priority access' },
  { feature: 'Bring your own API keys', free: true, cloud: true, pro: true },
  { feature: 'Chat integrations', free: 'All', cloud: 'All', pro: 'All' },
  { feature: 'Browser automation', free: true, cloud: true, pro: 'Advanced (Playwright)' },
@@ -222,7 +222,7 @@ export default function PricingPage() {
          <h2 className="text-2xl font-bold text-fd-foreground">AI Models</h2>
        </div>
        <p className="text-sm text-fd-muted-foreground mb-6 max-w-[540px]">
-          100+ models available via Hanzo AI Gateway. Pricing per 1M tokens.
+          100+ models available via Hanzo AI API. Pricing per 1M tokens.
          Zen models at 3x inference cost. Third-party models at 1.2x pass-through.
        </p>
        <DynamicAiModels />
@@ -5,7 +5,7 @@ const billingFaqs = [
  },
  {
    q: 'What does the $5/mo Cloud plan include?',
-    a: 'A full Linux desktop VM running in Hanzo Cloud with access to 100+ AI models via the Hanzo AI Gateway. Your bot is always on, backed up daily, and accessible from any device. All chat integrations are included.',
+    a: 'A full Linux desktop VM running in Hanzo Cloud with access to 100+ AI models via the Hanzo AI API. Your bot is always on, backed up daily, and accessible from any device. All chat integrations are included.',
  },
  {
    q: 'Why is Cloud Pro $25/mo?',
@@ -50,7 +50,7 @@ const plans = [
    badge: '14-day free trial',
    features: [
      'Full Linux desktop VM (Ubuntu)',
-      '100+ AI models via Hanzo AI Gateway',
+      '100+ AI models via Hanzo AI API',
      'Always-on with daily backups',
      'Web dashboard at app.hanzo.bot',
    ],
@@ -412,7 +412,7 @@ export default function Page() {
        </h2>
        <div className="grid grid-cols-2 sm:grid-cols-3 gap-3">
          {[
-            { name: 'AI Gateway', desc: '200+ AI models, one API', href: 'https://docs.hanzo.ai/docs/llm' },
+            { name: 'AI API', desc: '200+ AI models, one API', href: 'https://docs.hanzo.ai/docs/llm' },
            { name: 'Marketplace', desc: 'Buy & sell AI capacity', href: 'https://app.hanzo.bot' },
            { name: 'MCP', desc: '260+ tools for agents', href: 'https://docs.hanzo.ai/docs/mcp' },
            { name: 'Commerce', desc: 'Billing & on-chain settlement', href: 'https://docs.hanzo.ai/docs/commerce' },
@@ -257,7 +257,7 @@ export default function PlatformPage() {

        <div className="flex justify-center mt-3">
          <div className="flex flex-col items-center gap-0.5 text-fd-muted-foreground/40">
-            <span className="text-[10px] font-mono">AI Gateway</span>
+            <span className="text-[10px] font-mono">AI API</span>
            <span className="text-xs">|</span>
            <span className="text-[10px] font-mono">llm.hanzo.ai</span>
          </div>
@@ -44,7 +44,7 @@ const tiers = [
    badge: 'Most Popular',
    features: [
      'Full Linux desktop VM (Ubuntu)',
-      '100+ AI models included via Hanzo AI Gateway',
+      '100+ AI models included via Hanzo AI API',
      'Always-on — never goes to sleep',
      'All chat integrations',
      'Persistent memory, files & storage',
@@ -80,7 +80,7 @@ type CellValue = true | false | string;
 const comparisonRows: { feature: string; free: CellValue; cloud: CellValue; pro: CellValue }[] = [
  { feature: 'Self-hosted (Mac/Win/Linux)', free: true, cloud: false, pro: false },
  { feature: 'Cloud VM (always-on)', free: false, cloud: 'Linux (Ubuntu)', pro: 'macOS or Windows' },
-  { feature: 'AI models included', free: false, cloud: '100+ via AI Gateway', pro: '100+ with priority access' },
+  { feature: 'AI models included', free: false, cloud: '100+ via AI API', pro: '100+ with priority access' },
  { feature: 'Bring your own API keys', free: true, cloud: true, pro: true },
  { feature: 'Chat integrations', free: 'All', cloud: 'All', pro: 'All' },
  { feature: 'Browser automation', free: true, cloud: true, pro: 'Advanced (Playwright)' },
@@ -279,7 +279,7 @@ export default function Page() {
        <div className="grid grid-cols-2 sm:grid-cols-3 gap-3">
          {[
            { name: 'Platform', desc: 'Full PaaS for containers', href: 'https://platform.hanzo.ai' },
-            { name: 'AI Gateway', desc: '200+ AI models, one API', href: 'https://docs.hanzo.ai/docs/llm' },
+            { name: 'AI API', desc: '200+ AI models, one API', href: 'https://docs.hanzo.ai/docs/llm' },
            { name: 'Bot', desc: 'AI agent in a box', href: 'https://docs.hanzo.bot' },
            { name: 'MCP', desc: '260+ tools for agents', href: 'https://docs.hanzo.ai/docs/mcp' },
            { name: 'Commerce', desc: 'Payments and billing', href: 'https://docs.hanzo.ai/docs/commerce' },
@@ -12,13 +12,13 @@ The Zen model family is the product of three organizations with distinct but com

 **[hanzo.ai](https://hanzo.ai)** | AI infrastructure | Techstars '17

-Hanzo AI builds the infrastructure layer: the AI gateway, the API, the tooling developers actually use in production. Since 2017, Hanzo has been operating at scale — routing model traffic, managing provider fallback, handling the operational complexity that comes with running AI systems in production environments.
+Hanzo AI builds the infrastructure layer: the AI API, the API, the tooling developers actually use in production. Since 2017, Hanzo has been operating at scale — routing model traffic, managing provider fallback, handling the operational complexity that comes with running AI systems in production environments.

 Hanzo productizes Zen models for real-world use:

 - **[console.hanzo.ai](https://console.hanzo.ai)**: API access with an OpenAI-compatible endpoint, per-token billing, enterprise SLA
 - **[hanzo.chat](https://hanzo.chat)**: Consumer interface — try any Zen model free, no account required
- **AI Gateway** ([api.hanzo.ai](https://api.hanzo.ai)): Unified API routing to Zen models and 100+ third-party providers
+- **AI API** ([api.hanzo.ai](https://api.hanzo.ai)): Unified API routing to Zen models and 100+ third-party providers

 Hanzo's position in the infrastructure stack means every model improvement has a direct path to production. The feedback loop runs continuously: production signals inform training, training improves the models, better models improve the product.

@@ -14,7 +14,7 @@ This is the result of three years of joint work between Hanzo AI, Zoo Labs Found

 ## The Backstory

-Hanzo AI was founded in 2017 (Techstars '17) to build AI infrastructure at scale. We operate the AI gateway at [api.hanzo.ai](https://api.hanzo.ai), serving production traffic across 100+ model providers. We know what it costs to run models at scale, what developers actually need, and where proprietary APIs fall short.
+Hanzo AI was founded in 2017 (Techstars '17) to build AI infrastructure at scale. We operate the AI API at [api.hanzo.ai](https://api.hanzo.ai), serving production traffic across 100+ model providers. We know what it costs to run models at scale, what developers actually need, and where proprietary APIs fall short.

 Zoo Labs Foundation is a 501(c)(3) research organization advancing open AI and decentralized science. The Foundation runs the Zoo Improvement Proposals (ZIPs) process — open governance for model architecture, training methodology, and data standards. Training experiments happen in the open, negative results included.

@@ -33,7 +33,7 @@ description: Zen Agentic Dataset - 8.47 billion tokens of real-world agentic pro
 - Model Context Protocol (MCP) - 260+ tool implementations
 - Multi-agent orchestration
 - Agent frameworks - planning, memory, reflection
- AI Gateway - one API for 100+ providers
+- AI API - one API for 100+ providers

 ### Web3 & Blockchain
 - Smart contracts - Solidity, Vyper
@@ -196,7 +196,7 @@ async function main(): Promise<void> {
            {
              value: 'llmgateway',
              label: 'LLMGateway',
-              hint: 'open-source AI gateway, API key required',
+              hint: 'open-source AI API, API key required',
            },
            {
              value: 'hanzo',
@@ -20,7 +20,7 @@ export const hanzo = defineOrg({
    },
    {
      slug: 'llm',
-      name: 'AI Gateway',
+      name: 'AI API',
      description: 'One API for every model',
      icon: 'brain',
      category: 'Infrastructure',