tangle-network · drewstone · Apr 10, 2026 · Apr 10, 2026 · Apr 10, 2026 · Apr 10, 2026
diff --git a/pages/_meta.ts b/pages/_meta.ts
@@ -18,6 +18,10 @@ const meta: Meta = {
     title: "Workbench",
     type: "page",
   },
+  gateway: {
+    title: "Gateway",
+    type: "page",
+  },
   infrastructure: {
     title: "Runtime",
     type: "page",

diff --git a/pages/ai/_meta.ts b/pages/ai/_meta.ts
@@ -2,6 +2,26 @@ import type { Meta } from "nextra";
 
 const meta: Meta = {
   index: "AI Introduction",
+  "-- gateway": {
+    type: "separator",
+    title: "Inference Gateway",
+  },
+  "gateway-intro": {
+    title: "Introduction",
+    href: "/gateway",
+  },
+  "gateway-start": {
+    title: "Getting Started",
+    href: "/gateway/getting-started",
+  },
+  "gateway-models": {
+    title: "Models & Providers",
+    href: "/gateway/models",
+  },
+  "gateway-zdr": {
+    title: "Zero Data Retention",
+    href: "/gateway/zdr",
+  },
   "-- workbench": {
     type: "separator",
     title: "Agentic Workbench",

diff --git a/pages/ai/index.mdx b/pages/ai/index.mdx
@@ -44,8 +44,20 @@ Core capabilities:
 
 Each run produces task and agent evaluations. That data feeds back into the workbench to improve prompts, policies, and workflows over time.
 
+## Inference Gateway
+
+The [Tangle Gateway](/gateway) is the inference routing layer. Agents and applications call a single API to access hundreds of models across centralized providers and decentralized operators. The gateway handles model selection, compliance routing, billing, and payment settlement.
+
+Key capabilities:
+
+- **One API, any model.** OpenAI, Anthropic, Google, Groq, and 20+ providers.
+- **Decentralized operators.** Route to operators on the Tangle network who compete on price and latency.
+- **Compliance.** [Zero Data Retention](/gateway/zdr) and [no-train](/gateway/no-train) routing with verified provider agreements.
+- **On-chain payments.** [SpendAuth](/gateway/spend-auth) — pay operators directly without a credit card.
+
 ## Learn More
 
+- [Gateway — Getting Started](/gateway/getting-started)
 - [Workbench details](/vibe/introduction)
 - [Runtime and sandboxing](/infrastructure/introduction)
 - [Operator onboarding](/operators/introduction)
diff --git a/pages/developers/blueprints/use-cases.mdx b/pages/developers/blueprints/use-cases.mdx
@@ -21,7 +21,21 @@ Tangle Network enables developers to rapidly build and deploy secure multi-party
   displayStyle="row"
 />
 
-## AI
+## AI & Inference
+
+<GithubRepoCard
+  name="llm-inference-blueprint"
+  description="LLM inference serving via vLLM/Ollama with on-chain settlement. Powers the Tangle Gateway operator network."
+  url="https://github.com/tangle-network/llm-inference-blueprint"
+  displayStyle="row"
+/>
+
+<GithubRepoCard
+  name="tangle-inference-core"
+  description="Shared Rust crate for EIP-712 SpendAuth verification, nonce management, and on-chain payment settlement."
+  url="https://github.com/tangle-network/tangle-inference-core"
+  displayStyle="row"
+/>
 
 <GithubRepoCard
   name="coinbase-agentkit-blueprint"

diff --git a/pages/gateway/_meta.ts b/pages/gateway/_meta.ts
@@ -0,0 +1,64 @@
+import type { Meta } from "nextra";
+
+const meta: Meta = {
+  index: "Introduction",
+  "getting-started": "Getting Started",
+  "-- models": {
+    type: "separator",
+    title: "Models & Providers",
+  },
+  models: "Supported Models",
+  byok: "Bring Your Own Key",
+  fallbacks: "Model Fallbacks",
+  timeouts: "Provider Timeouts",
+  caching: "Automatic Caching",
+  "-- routing": {
+    type: "separator",
+    title: "Routing",
+  },
+  "how-routing-works": "How Routing Works",
+  "operator-routing": "Operator Routing",
+  "smart-routing": "Smart Routing",
+  "-- security": {
+    type: "separator",
+    title: "Security & Compliance",
+  },
+  authentication: "Authentication",
+  zdr: "Zero Data Retention",
+  "no-train": "Disallow Prompt Training",
+  guardrails: "Guardrails",
+  "rate-limiting": "Rate Limiting",
+  "-- billing": {
+    type: "separator",
+    title: "Billing",
+  },
+  pricing: "Credits & Pricing",
+  "free-tier": "Free Tier",
+  "spend-auth": "SpendAuth (On-Chain)",
+  "-- observability": {
+    type: "separator",
+    title: "Observability",
+  },
+  "generation-lookup": "Generation Lookup",
+  "routing-trace": "Routing Trace",
+  "-- reference": {
+    type: "separator",
+    title: "API Reference",
+  },
+  "api-chat": "POST /v1/chat/completions",
+  "api-generation": "GET /v1/generation",
+  "api-credits": "GET /v1/credits",
+  "api-compliance": "Provider Compliance API",
+  "provider-options": "providerOptions.gateway",
+  "response-headers": "Response Headers",
+  "feature-flags": "Feature Flags",
+  "-- guides": {
+    type: "separator",
+    title: "Guides",
+  },
+  "migrate-openai": "Migrate from OpenAI",
+  "migrate-vercel": "Migrate from Vercel AI Gateway",
+  "enterprise-zdr": "Enterprise ZDR Setup",
+};
+
+export default meta;
diff --git a/pages/gateway/api-chat.mdx b/pages/gateway/api-chat.mdx
@@ -0,0 +1,96 @@
+---
+title: POST /v1/chat/completions
+description: OpenAI-compatible chat completion endpoint with gateway extensions.
+---
+
+# POST /v1/chat/completions
+
+OpenAI-compatible chat completion endpoint. Supports streaming, tool use, and all standard parameters, plus gateway-specific extensions via `providerOptions.gateway`.
+
+## Request
+
+```bash
+POST https://router.tangle.tools/v1/chat/completions
+Authorization: Bearer sk-tan-YOUR_KEY
+Content-Type: application/json
+```
+
+### Body
+
+```json
+{
+  "model": "anthropic/claude-sonnet-4-6",
+  "messages": [
+    {"role": "system", "content": "You are a helpful assistant."},
+    {"role": "user", "content": "Hello"}
+  ],
+  "temperature": 0.7,
+  "max_tokens": 4096,
+  "stream": true,
+  "tools": [...],
+  "tool_choice": "auto",
+  "response_format": {"type": "json_object"},
+  "top_p": 0.9,
+  "frequency_penalty": 0,
+  "presence_penalty": 0,
+  "stop": ["\n\n"],
+  "providerOptions": {
+    "gateway": {
+      "byok": {"anthropic": [{"apiKey": "sk-ant-..."}]},
+      "zeroDataRetention": true,
+      "caching": "auto",
+      "models": ["openai/gpt-4o"],
+      "timeout": 5000
+    }
+  }
+}
+```
+
+All standard OpenAI parameters (`tools`, `tool_choice`, `response_format`, `top_p`, `frequency_penalty`, `presence_penalty`, `stop`, `logprobs`) are forwarded to the provider.
+
+### Routing headers (optional)
+
+| Header                | Effect                                          |
+| --------------------- | ----------------------------------------------- |
+| `X-Tangle-Routing`    | `operator`, `provider`, or `auto` (default)     |
+| `X-Tangle-Blueprint`  | Pin to operators under this Blueprint ID        |
+| `X-Tangle-Service`    | Pin to a specific service instance              |
+| `X-Tangle-Operator`   | Pin to a specific operator (slug or 0x address) |
+| `X-Payment-Signature` | SpendAuth JSON payload for on-chain payment     |
+
+### Validation
+
+| Field         | Constraint                                         |
+| ------------- | -------------------------------------------------- |
+| `model`       | Required. Alphanumeric + `/-.:\\_`, max 128 chars. |
+| `messages`    | Required. Non-empty array. Each must have `role`.  |
+| `max_tokens`  | Optional. 1-128,000. Default: 4,096.               |
+| `temperature` | Optional. 0-2. Default: 1.                         |
+| Body size     | Max 1MB.                                           |
+
+## Response (non-streaming)
+
+Standard OpenAI chat completion response:
+
+```json
+{
+  "id": "chatcmpl-...",
+  "choices": [{
+    "message": {"role": "assistant", "content": "Hello! How can I help?"},
+    "finish_reason": "stop"
+  }],
+  "usage": {
+    "prompt_tokens": 15,
+    "completion_tokens": 8,
+    "total_tokens": 23
+  }
+}
+```
+
+## Response (streaming)
+
+Server-sent events with `data: {...}` lines and `data: [DONE]` terminator.
+
+## Response headers
+
+See [Response Headers](/gateway/response-headers) for the full list.
diff --git a/pages/gateway/api-compliance.mdx b/pages/gateway/api-compliance.mdx
@@ -0,0 +1,49 @@
+---
+title: Provider Compliance API
+description: Query and manage provider ZDR and no-train compliance data.
+---
+
+# Provider Compliance API
+
+## GET /api/gateway/compliance
+
+List compliance data for all providers. Public endpoint (rate-limited).
+
+```bash
+curl https://router.tangle.tools/api/gateway/compliance
+```
+
+```json
+{
+  "providers": [
+    {
+      "provider": "anthropic",
+      "name": "Anthropic",
+      "zdr": true,
+      "no_train": true,
+      "supports_prompt_caching": true,
+      "caching_type": "explicit",
+      "policy_url": "https://platform.claude.com/docs/en/build-with-claude/zero-data-retention",
+      "verified_at": "2026-04-10T00:00:00.000Z"
+    }
+  ]
+}
+```
+
+## PUT /api/admin/compliance
+
+Update compliance data for a provider. Admin-only (requires `ADMIN_EMAILS` session).
+
+```bash
+curl -X PUT https://router.tangle.tools/api/admin/compliance \
+  -H "Cookie: session_token=ADMIN_SESSION" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "providerId": "openai",
+    "zdr": true,
+    "noTrain": true,
+    "policyUrl": "https://openai.com/policies/api-data-usage-policies"
+  }'
+```
+
+Only fields included in the request body are updated. Omitted fields remain unchanged. `verifiedAt` is automatically set to the current timestamp.
diff --git a/pages/gateway/api-credits.mdx b/pages/gateway/api-credits.mdx
@@ -0,0 +1,29 @@
+---
+title: GET /v1/credits
+description: Check your credit balance and total usage.
+---
+
+# GET /v1/credits
+
+Check your credit balance. Requires authentication.
+
+## Request
+
+```
+GET https://router.tangle.tools/v1/credits
+Authorization: Bearer sk-tan-YOUR_KEY
+```
+
+## Response
+
+```json
+{
+  "balance": "95.50",
+  "total_used": "4.50"
+}
+```
+
+| Field        | Description                    |
+| ------------ | ------------------------------ |
+| `balance`    | Remaining credit balance (USD) |
+| `total_used` | Total credits consumed (USD)   |
diff --git a/pages/gateway/api-generation.mdx b/pages/gateway/api-generation.mdx
@@ -0,0 +1,55 @@
+---
+title: GET /v1/generation
+description: Look up detailed information about a specific request.
+---
+
+# GET /v1/generation
+
+Retrieve detailed information about a specific generation by its ID. Requires authentication.
+
+## Request
+
+```
+GET https://router.tangle.tools/v1/generation?id=gen_01ARZ3NDEKTSV4RRFFQ69G5FAV
+Authorization: Bearer sk-tan-YOUR_KEY
+```
+
+## Parameters
+
+| Parameter | Required | Description                          |
+| --------- | -------- | ------------------------------------ |
+| `id`      | Yes      | Generation ID (format: `gen_<ulid>`) |
+
+## Response
+
+```json
+{
+  "data": {
+    "id": "gen_01ARZ3NDEKTSV4RRFFQ69G5FAV",
+    "total_cost": 0.00123,
+    "usage": 0.00123,
+    "created_at": "2026-04-10T12:00:00.000Z",
+    "model": "anthropic/claude-sonnet-4-6",
+    "is_byok": false,
+    "provider_name": "anthropic",
+    "streamed": true,
+    "latency": 200,
+    "generation_time": 1500,
+    "tokens_prompt": 100,
+    "tokens_completion": 50,
+    "native_tokens_cached": 80,
+    "native_tokens_reasoning": 0,
+    "status": "success",
+    "routing_trace": {...},
+    "cache_hit": false
+  }
+}
+```
+
+## Errors
+
+| Status | Code        | Description                                     |
+| ------ | ----------- | ----------------------------------------------- |
+| 400    | —           | Missing or invalid generation ID                |
+| 401    | —           | Authentication required                         |
+| 404    | `not_found` | Generation not found or belongs to another user |