Auxot
Tutorials Docs Pricing Login

Connect a cloud AI model

Plug a cloud AI provider — OpenAI, Anthropic, or both — into your Auxot account so your agents have an AI model to actually generate responses.

Plus: three prompts to paste into Admin Agent chat — pinning sensible models per agent, sketching fallback when a provider has a bad day, and triaging unreliable connections against System Health without opening three tabs.

Audience Admins
Time ~5 min
Prerequisites An Auxot account where you're an org admin. An API key from OpenAI or Anthropic (instructions for getting one are in the Walkthrough). A payment method on file with that provider — both OpenAI and Anthropic charge by usage.
You'll end up with One cloud AI model connected to your Auxot account, your agents using it, and a clear sense of how to add another or switch between them.

When a tutorial shows italic text in quotation marks, it usually mirrors a label or helper string inside Auxot. Product copy changes between releases — if something reads differently in your workspace, trust what you see on screen.

Callouts with a Worth knowing gold accent are meant as must-read context before you move on. Blockquotes that open with Tip are lighter, optional depth.

Why this matters

Agents read context files. Tools let them act on the world. But the part that actually thinks (that strings together a sentence, weighs the options, and drafts the email) is the AI model.

Auxot doesn’t ship with one. It connects to whatever AI model you bring: an OpenAI account, an Anthropic account, your own GPU running locally, or a CLI tool already on your laptop. You decide which provider does your thinking, and Auxot routes work to it.

Cloud providers are the easiest place to start. Sign up with OpenAI or Anthropic, get an API key, paste it into Auxot, done. Open Chat, pick an agent and a model: you should see a real reply inside about thirty seconds.

(If you’d rather run AI on your own hardware so no data leaves your building, that’s Connect a GPU worker. The two paths aren’t mutually exclusive: many teams connect both, with cloud as the fast default and local GPU as the privacy-protecting fallback.)

Today, connect one cloud provider. Every chat you send has a sharper engine behind it once you pick that model: nothing runs on its own until workflows or integrations start the thread (Run a workflow, Create a shared Team API Key) later.

You connect a cloud AI provider (OpenAI, Anthropic, or both) by giving Auxot the API key from your account with that provider. After that, Auxot can route prompts you (or automation you configure) send to whichever model you surfaced. You still decide what appears in the picker and what each agent prefers by default.

Quick start

  1. Get an API key from your provider. OpenAI: log into platform.openai.com → API Keys → Create new secret key. Anthropic: log into console.anthropic.com → API Keys → Create Key. Copy the key value (you’ll only see it once).
  2. Sign in to Auxot in your browser.
  3. Open Providers: click Settings in the left menu, then Providers.
  4. Add the provider: click + Add Provider, pick OpenAI or Anthropic, give it a clear name (something like “OpenAI production”), paste your API key, and create.
  5. Pick which models to surface: Auxot fetches the available models from your provider. On the provider’s detail page, check the boxes for the models you want available in the agent picker (start with the latest one).

Done? Open chat with any agent, pick the new model from the model selector, send a message. You’re now running on cloud AI.

The agent can do that?

Providers page is fiddly. Use the same approach as Take Auxot’s pulse in 10 seconds: paste a sharp ask into Admin Agent chat first, skim the draft plan, tweak in Settings after. Below: three pasted prompts.

1. Recommend a sane default model per custom agent

Chat → Admin Agent, new message:

Look at all the custom agents in my account. For each one, recommend which AI model from my connected providers it should use as its preferred model — and tell me why. Match the model to the agent's job: a customer-support drafting agent doesn't need the most expensive model; a contract-review agent probably does.

Why it’s non-obvious: One expensive default everywhere quietly inflates your bill. Paste the gray box once: after you send it, Admin Agent lays job text next to whichever models you’ve already surfaced so you stop paying flagship prices for FAQs. Still your sliders to flip afterward; he’s sketching options, not changing billing on its own.

2. Sketch fallback routing between providers

Same thread. Another message:

I want my agents to keep working if any one provider has a bad day. Look at what I've connected, recommend which provider should fall back to which (and under what conditions — offline, over quota, or queue too deep), and walk me through setting it up.

Why it’s non-obvious: Queues absorb outages gracefully: graceful still means waiting until failover picks up. Fallback rules (you flip them after his outline) shorten that wait: the next prompt can ride a healthy provider sooner. Paste the gray box before the outage page is the only thing anybody reads.

3. Triage an unreliable provider without tab-hopping

When latency smells wrong, still start in Admin Agent chat:

My [provider name] keeps showing as having issues — slow responses, occasional errors, or it just feels off. Walk me through what to check, in order, and tell me which is most likely the cause based on what you can see in System Health.

Why it’s non-obvious: Slow could be the provider, your network, or your prompt. Figuring out which one usually takes a few minutes of checking in order. Paste the symptom after you’ve glanced at System Health; Admin Agent aligns provider cards, quotas, queues, whatever your account exposes because you asked. Fifteen-second ordered checklist beats ping-ponging tabs while leadership hovers behind your chair.

Go deeper

Spending controls and surprise prevention

A few habits that prevent any single agent from running up an unexpected bill:

  • Set a hard spending limit at the provider. Both OpenAI and Anthropic have monthly spend caps in their billing settings. Set one. “Pause API access if monthly usage exceeds $X” is much better than discovering a runaway loop after the fact.

  • Use cheaper models for simple work. Surface both a flagship and a budget model on each provider, then assign the budget one as the default for agents whose work is straightforward. (See power move 1 in The agent can do that? above.)

  • Watch the System Health page. The Model Providers card shows the current provider load (Take Auxot’s pulse in 10 seconds). If the bar is constantly maxed, something (usually human-started chats or workflows you wired) is spending more tokens than surprises feel worth.

  • Set spending alerts in your provider account. Both providers can email you when usage crosses a threshold. Set the alert at half your limit so you have time to investigate before hitting the cap.

The most common surprise bill is from a poorly-instructed agent making the same call in a loop. Give your agent its job description covers writing tight job descriptions; tight descriptions are also cheap descriptions.

Multiple providers: when and why

Connect more than one provider when:

  • You want fallback. Cloud providers occasionally have outages. Two providers means your agents keep working even when one is down.
  • You’re cost-optimizing. Some models are cheaper on one provider; some on another. Multiple connections let you route different agents to different providers based on cost-per-call.
  • You want different capabilities for different work. Long-context document review on one provider’s flagship; quick FAQ replies on another’s lightweight model.
  • You’re testing. Connect both, run the same agent against each, compare quality.

Multiple providers stay simple until you configure them: until you set fallback rules or per-agent preferences, Auxot just uses whichever one Auto routing picks first.

Troubleshooting
  • The provider shows “Offline” or “Error” right after I add it. Usually one of: API key was pasted wrong (extra space, missing character), the provider account doesn’t have API access enabled, or the provider account doesn’t have a payment method on file. Open the provider’s detail page; the error message there is more specific than the dashboard’s red dot.
  • The model list is empty after I add the provider. Click Refresh from provider on the detail page. If it stays empty, the API key is valid but the provider account doesn’t have access to any models (usually because billing isn’t set up). Add a payment method on the provider’s side.
  • The provider works but my agents aren’t using it. Check two things: which provider is set as the Auto routing default (Step 6), and whether the agent has a specific model pinned in its settings that doesn’t exist on this provider.
  • I’m seeing “Over quota” errors. Your provider account hit its rate limit or its monthly cap. Three options: wait it out, top up the provider account, or fall back to another connected provider (wire that before trouble: power move 2 above sketches the planner prompt).
  • The API key isn’t recognized when I paste it. Common causes: copied with extra whitespace, the key was created for an organization you don’t have access to, or you accidentally copied the display name of the key instead of the secret value. Generate a fresh one and paste carefully.
Variations & edge cases
  • Free tier: You can connect one provider of each type (one OpenAI, one Anthropic, one GPU, and one CLI). For a single user, that’s plenty. To connect a second provider of the same type, upgrade.
  • Team, Business, Enterprise: No hard limits on provider count.
  • Team scoping: On Business and Enterprise, providers can be assigned to specific teams (e.g., “Engineering team uses Anthropic; Sales team uses OpenAI”). Configure on the provider’s detail page.
  • Rotating API keys. Use the Update API key field on the provider’s detail page. Old keys can be revoked from the provider’s side; new key takes effect immediately in Auxot.
  • Deleting a provider. Use Delete provider on the detail page (Danger Zone section). Agents that had the deleted provider pinned will fail to route until reassigned.
  • CLI providers. If you have Claude Code, Cursor, or Codex CLI installed on a machine, you can connect that as a provider too: Auxot routes work to your local CLI tool when you pick that route. Different setup flow than cloud providers; see Connect a CLI provider (Claude Code, Cursor, Codex).

Walkthrough

Step 1: Get an API key from your provider

If you’ve never used OpenAI or Anthropic’s API directly, this is the part that takes the longest. It’s still under five minutes.

a. OpenAI

  1. Go to platform.openai.com and log in (or create an account).
  2. Add a payment method under Billing → Payment methods. OpenAI doesn’t allow API key creation without one. Most teams pre-load $10–$25 to start.
  3. Click API Keys in the left menu (or visit platform.openai.com/api-keys).
  4. Click Create new secret key. Give it a name like “Auxot — production” so you’ll know what it’s for later. Copy the key value (it starts with sk-...). You won’t see it again. Paste it somewhere safe immediately.

b. Anthropic

  1. Go to console.anthropic.com and log in (or create an account).
  2. Add a payment method under Plans & Billing. Anthropic also charges per usage (typical starting balance is $5–$25).
  3. Click API Keys in the left menu.
  4. Click Create Key. Name it “Auxot — production” (or whatever helps you recognize it later). Copy the key value. Same rule: you won’t see it again.

Tip: Both providers charge per call, not per month. Costs scale with how much your agents do. A small team running a handful of agents typically spends $5–$50/month. Heavy automation can run higher. Both providers let you set spending limits in their billing settings: do this so a runaway loop doesn’t surprise you.

Step 2: Sign in to Auxot

Open Auxot in your browser and log in. You’ll need to be an org admin for the next steps; non-admin users can see providers but can’t add or edit them.

Step 3: Open Providers

Click Settings in the left menu, then Providers. The page lists every AI provider currently connected to your account.

The page’s empty-state copy says it well: “No providers yet. Add one to connect your agents to an AI backend like Claude, GPT, or your own hardware.”

If you already see providers in the list (someone connected one during account setup), you can still add another. Auxot supports multiple providers running side by side: useful for fallback routing, which Step 5 covers.

Step 4: Add the provider

Click + Add Provider. A modal opens with the title “Add Provider” and the description “Choose a provider type and give it a name. You’ll configure the details on the next screen.”

Three things to fill in:

  • Provider type. Pick OpenAI or Anthropic. (You’ll also see GPU and CLI: local routes; GPU is Connect a GPU worker, CLI is Connect a CLI provider (Claude Code, Cursor, Codex).)
  • Name. What you’ll recognize this provider by. Something like “OpenAI production” or “Anthropic — Claude account.” Naming matters when you have several connected; “My OpenAI” is fine for one, but if you connect two OpenAI accounts later (production and a separate dev one, say), descriptive names save confusion.
  • API key. Paste the key you copied in Step 1. Auxot encrypts it before storing: even Auxot itself only ever sees a hint (first/last few characters) after this point.

Click Create.

Step 5: Pick which models to surface

Auxot drops you on the new provider’s detail page. Behind the scenes, it’s already calling OpenAI or Anthropic to ask “what models does this account have access to?” The list populates within a few seconds.

You’ll see a section titled something like “Available models” with the helper text “Refresh the list from your provider, then choose which models appear in the chat selector.”

Two things to do here:

a. Check the boxes for the models you want available

Don’t surface every model the provider offers. Most providers list 30+ variants: some old, some specialized, and some experimental. Pick two or three that cover your needs:

  • One latest-generation model (gpt-4o, claude-3-5-sonnet, or whatever’s current): your default for most work.
  • One smaller/cheaper model (gpt-4o-mini, claude-3-haiku): good for simple tasks where you’d rather save cost.
  • (Optional) one specialized model if you have a specific need (e.g., a long-context model for document review).

Checked models appear in the model picker for chats and agents. Unchecked models don’t, even though your account has access to them.

b. Set a default model

Pick which model is the default when this provider is selected. Most teams set this to their main latest-generation model. The default is what an agent uses if it doesn’t have a more specific preference set.

There’s no Save button: auto-save is on. Your changes apply immediately.

Tip: You can come back to this page anytime to add or remove models as the provider releases new ones. Click Refresh from provider to re-fetch the available list.

Step 6 (optional): Set up “Auto” routing

Above the providers list, you’ll see an Auto routing section. Helper: “When a chat thread or agent uses Auto for the model, Auxot starts from the provider (and optional model) you set here, then applies that provider’s fallback rules if needed.”

Plain English: when a user (or agent) picks “Auto” from the model selector, Auxot uses the provider you set here as its first try. If you don’t set anything, Auxot uses a built-in priority order (GPU → CLI → OpenAI → Anthropic: whichever is connected first).

For a brand-new account with one cloud provider, you can leave Auto routing alone. Come back to it once you have multiple providers and want a preference.

Tip: Even with one provider connected, “Auto” still works: it just always picks that provider. The Auto setting becomes more useful when you have a primary and a fallback (e.g., “prefer Anthropic, fall back to OpenAI if Anthropic is down or over quota”). You configure those fallback rules on each provider’s detail page.

What’s next

Reference

Browse all tutorials