The missing middle
Daneel gives you two ends of the AI spectrum. On one side: local models — WebGPU, Ollama, Gemini Nano — that never leave your machine but are constrained by your hardware. On the other: Claude, a frontier model that can reason through anything but sends your data to a third-party cloud.
What if you could have both? Frontier capability with data that stays under your control?
That's what Azure brings to Daneel. Deploy models on your own Azure subscription, governed by your organization's policies, and use them with every Daneel feature.
Your prompts reach a GPU in your cloud tenant, not someone else's API.
Two endpoint styles, one integration
Daneel supports both Azure OpenAI Service (classic) and the newer Azure AI Foundry:
- Classic Azure OpenAI — the established path. Specify your resource endpoint, deployment name, and API version. Daneel builds the request URL automatically.
- Azure AI Foundry — Microsoft's newer model-as-a-service platform. Paste your project target URI and model name. Daneel auto-detects the Foundry format and adapts — no API version needed.
You don't need to tell Daneel which style you're using. Paste the URL and it figures it out.
Authentication your IT team will approve
Two authentication methods, because enterprise environments have different requirements:
API Key — paste your Azure API key, and Daneel encrypts it with AES-256-GCM before storing it in Chrome's local storage. The key never leaves your device except in the request header to your own Azure endpoint. Simple, fast, works for personal deployments and development.
Entra ID (SSO) — for organizations with centralized identity. Enter your tenant ID and client ID from your App Registration, click "Sign in with Azure," and authenticate through your organization's SSO flow. Full OAuth2 + PKCE, token refresh handled automatically. No shared secrets, no API keys to rotate — just your corporate identity.
Both methods encrypt credentials at rest. The settings panel confirms the encryption status visually so you know your keys are protected.
Five models, from flagship to frugal
The Azure registry ships with five models spanning every budget and capability tier:
- GPT-4.1 — the flagship. 1M token context window, vision, native tool calling. 8 per million tokens.
- GPT-4o — the proven workhorse. 128K context, vision, tools. 10 per million tokens.
- GPT-4.1 Mini — flagship intelligence at lower cost. 1M context, vision, tools. 1.60 per million tokens.
- GPT-4o Mini — fast and affordable for lighter tasks. 128K context, tools. 0.60 per million tokens.
- Phi-4 — Microsoft's own 14B parameter model. 16K context, tools, no vision. 0.14 per million tokens — nearly free at scale.
Every model supports native tool calling through the OpenAI function calling format, meaning MCP servers work out of the box.
The privacy sweet spot
This is why Azure matters for Daneel. Every Azure model gets "Your cloud" residency — the middle tier in Daneel's privacy model:
- On-device (WebGPU, Gemini Nano) — nothing leaves your browser
- Local network (Ollama) — stays on your machine
- Your cloud (Azure) — leaves your machine, stays in your subscription
- Third-party cloud (Claude) — reaches an external provider
With Azure, your data crosses the network but lands in infrastructure you control. Your organization's data governance policies apply. Azure RBAC controls access. The only data observer is your cloud tenant admin — not an external API provider.
For regulated industries — healthcare, finance, legal, government — this is often the only acceptable path to frontier model capability. You get GPT-4.1's reasoning power without sending patient records, financial data, or privileged communications to a third party.
The settings panel makes this explicit with a banner at the top: "Data stays within your Azure subscription, governed by your organization's policies."
Full tool calling support
Azure models use native OpenAI-style function calling. Connect any MCP server — Stripe, Supabase, Vercel, Salesforce — and Azure models will call tools with the same reliability as any OpenAI endpoint.
The multi-turn tool loop handles complex chains: the model calls a tool, reads the result, decides if it needs more information, calls another tool, and continues until it has a complete answer. Tool results are streamed back incrementally, so you see progress in real time.
Combined with agents, this means you can build specialized AI workflows backed by enterprise-grade infrastructure. A compliance agent with Salesforce access. A DevOps agent with Vercel and Cloudflare. All running through your Azure tenant.
Getting started
- Deploy a model in the Azure portal (Azure OpenAI or AI Foundry)
- Open Daneel Settings, then Azure OpenAI
- Choose your auth method (API Key or Entra ID)
- Paste your endpoint URL and deployment/model name
- Click "Test connection" to verify
- Click "Use Azure OpenAI" to activate
The test query box lets you run a quick inference before committing — tokens stream back in real time so you can confirm the connection works and gauge latency.
What's next
We're tracking Azure's expanding model catalog closely. As new models land in Foundry — including open-weight models from Mistral, Meta, and others — Daneel's registry will grow to match. The integration is endpoint-agnostic: any model Azure serves through the OpenAI-compatible API works today.
Frontier AI doesn't have to mean giving up control. With Azure on Daneel, it doesn't.