Skip to content
home / platform / ai-gateway
Hoody Platform

300+ AI models. One OpenAI-compatible URL.

ai.hoody.com runs on your bare metal. Swap the base URL in any OpenAI client and your code works against Claude, GPT, Gemini, Llama, or any of 15+ inference providers.

Containers authenticate with container-NAME tokens — no real API keys in your workloads. Revoke a container and its AI access dies with it.

300+ models15+ providersOpenAI-compatible5% markup
Any OpenAI-compatible code

# Before (OpenAI direct)

from openai import OpenAI

 

client = OpenAI(

base_url="https://api.openai.com/v1",

api_key="sk-..."

)

Point it at ai.hoody.com

# After (Hoody AI Gateway)

from openai import OpenAI

 

client = OpenAI(

base_url="https://ai.hoody.com/api/v1",

api_key="container-dev-env"

)

home / platform / ai-gateway / providers
The provider catalog

15+ inference providers. One API.

Text generation, image generation, embeddings. Every major provider you would otherwise wire up separately.

AnthropicText

Claude family — Opus, Sonnet, Haiku

OpenAIText

GPT family — flagship and cost-optimized tiers

GoogleText

Gemini family via Vertex AI

MetaText

Llama family — hosted via inference partners

MistralText

Mistral + Mixtral open-weight models

DeepseekText

V3 and Coder family

QwenText

Alibaba Qwen — 72B and QwQ reasoning

CohereEmbed

Command R family plus embeddings

xAIText

Grok family — including vision tier

PerplexityText

Sonar models with live-web grounding

Together AIText

Hosting platform for open-weight models

Fireworks AIText

Optimized inference for open-weight models

ReplicateImage

Flux, SDXL, and specialized vision models

Stability AIImage

Stable Diffusion variants

300+ models total. Bring Your Own Provider (§5 below) extends this to direct keys and local/private endpoints. Full catalog in the docs.

home / platform / ai-gateway / keyless
Container-native auth

No real API keys in your containers.

Every container gets a virtual key tied to its name: `container-NAME`. The token only works from the infrastructure it was issued in. Delete the container — the token is instantly useless.

Traditional AI integration

  • Real sk-... API key stored in env
  • Leaks live on in git history, logs, Slack
  • Rotation requires coordinated update across all workloads
  • Revocation kills everything using that key

Hoody AI gateway

  • Auto-issued container-NAME token at container create
  • Token only works from inside the container
  • Rotation = recreate container with the same name
  • Revoke container = that container is gone and so is its key

Safe for freelancer handoff, vibe-coded side-projects, and consumer SaaS. The gateway runs on your bare metal — Hoody never sees your prompts or responses. Zero-knowledge by architecture, not policy.

home / platform / ai-gateway / mitm
MITM layer

Intercept every AI request. Stack layers in order.

Route the gateway through hoody-exec to insert middleware before the provider call. Cache cheap. Inject context. Route to the right model. Gate destructive tool calls on human approval. Fan out to other agents. Log everything. The order is a pipeline — each layer runs before the next, and you pick which ones you need.

your apphoody-exec (MITM pipeline)ai.hoody.comprovider (Anthropic, OpenAI, …)

1 · Response cache

Hash the prompt; skip inference on a hit. Cheapest layer first.

2 · Context injection

Prepend system prompts from your knowledge base before the call.

3 · Cost routing

Easy prompts → cheaper models. Hard prompts → Claude. 40-70% savings documented.

4 · Tool-call tampering

Rewrite or block tool calls before they execute. Sandbox file writes.

5 · Human-in-the-loop

Stall high-stakes actions. Push a notification. Wait for approval.

6 · Agent cascade

Trigger another hoody-agent over HTTP. Multi-agent systems with no orchestrator.

7 · Audit log

Every request + response into SQLite for compliance and debugging.

Built-in rule engine covers the common MITM patterns with zero code. Drop down to custom hoody-exec scripts when a rule doesn't fit.

home / platform / ai-gateway / byop
No lock-in

Bring your own provider. Opt out of keyless.

Keyless auth is the default and the safe path. But you are never locked in: route straight to any OpenAI-compatible endpoint — local Ollama, Azure OpenAI, Hugging Face inference, an enterprise proxy, or direct provider keys — by setting env vars inside the container. This is the explicit opt-out of keyless, not a parallel mode.

Container environment — opt out of keyless

# direct provider keys

ANTHROPIC_API_KEY=sk-ant-...

OPENAI_API_KEY=sk-...

 

# point at local Ollama

OPENAI_BASE_URL=http://localhost:11434/v1

 

# or Azure / enterprise proxy

OPENAI_BASE_URL=https://your-proxy.internal/v1

Direct provider keys (bypass gateway)Local Ollama (OPENAI_BASE_URL)Azure OpenAIEnterprise OpenAI-compatible proxy
home / platform / ai-gateway / vs
vs commercial AI gateways

What you otherwise stitch together

LiteLLM, Portkey, OpenRouter, and direct provider accounts each solve part of what the gateway solves in one surface running on your own hardware.

ConcernHoody AI GatewayCommercial gateway / DIY
Where it runssupported nativelyYour bare metalVendor cloud (LiteLLM SaaS, Portkey)
Container-scoped authsupported nativelycontainer-NAME tokensShared API keys + RBAC
Bring your own providersupported nativelyAny OpenAI-compatible endpointMostly yes, varies by vendor
MITM rules + scriptssupported nativelyBuilt-in rule engine + hoody-exec scriptsPaid tier or external proxy
OpenAI-compatiblesupported nativelyYesYes (most alternatives)
Pricingsupported natively5% markup over provider costPer-call fees + per-seat SaaS
Integrated with infra + walletsupported nativelySingle wallet, single API surfaceSeparate billing and ops

When your stack is already on LiteLLM or OpenRouter and you do not want to run a gateway, those stay better. The Hoody AI Gateway earns its place when you want container-scoped auth, native MITM, and the two-balance wallet model — General Balance funds the server (Stripe/crypto/bank), AI Balance funds the gateway, with one-way General → AI transfers and one invoice covering both.

home / platform / ai-gateway / start
Start

Claude in one base_url change.

Create a container, set base URL to https://ai.hoody.com/api/v1, use container-NAME as the bearer. Every OpenAI-compatible library already knows what to do.

Model catalog

See also — /platform/control-plane for token issuance and wallet, /platform/proxy for the URL layer underneath.