Anthropic (Claude)
Run the service desk’s AI features on Claude, on your school’s own API key and your school’s own account.
| Category | AI |
| Authentication | API key |
| Reaches | api.anthropic.com |
| Needs an agent | No |
| Demo mode | No |
Capabilities
Section titled “Capabilities”ai.chat, which powers the AI features: Ask, ticket
triage, and the summary on a ticket.
When to pick this
Section titled “When to pick this”You want the best answers and you are content for ticket text to go to Anthropic under your own commercial terms.
The bundled local model is private and free, but slow. This is faster and better, and billed to you. See choosing a model for the comparison.
Getting a key
Section titled “Getting a key”- Create an account at console.anthropic.com.
- Add billing. There is no free tier for API use.
- API keys, then create one. Copy it; it starts
sk-ant-.
Create the key under a workspace for the school rather than a personal one, so it survives whoever set it up moving on, and so the spend is attributable.
Configuring it in Plugboard
Section titled “Configuring it in Plugboard”Settings, Connectors, Anthropic (Claude), Configure.
Settings
Section titled “Settings”| Field | Default | Value |
|---|---|---|
model | empty | One model id for every task. Empty uses claude-haiku-5-5 for quick tasks and claude-sonnet-5-5 for more demanding ones. claude-opus-5 gives the best answers at the highest cost |
maxTokens | 4096 | The most tokens one answer may use, thinking included |
timeoutMs | 30000 | Give up on an answer after this long |
Credentials
Section titled “Credentials”| Field | Value |
|---|---|
apiKey | Your key, starting sk-ant- |
Save and test.
Structured answers such as ticket summaries use Anthropic’s schema format. Plugboard validates the returned answer before using it.
What it costs you
Section titled “What it costs you”Billed by Anthropic per token, on your account. The work this product asks for is small: a triage or a ticket summary is a few thousand tokens in and a few hundred out.
A desk triaging around three hundred tickets a month, plus questions in Ask,
lands somewhere between five hundred and fifteen hundred calls. On
claude-haiku-5-5 that is under a US dollar a month at the per-token prices
Plugboard records for it. Per token, claude-sonnet-5-5 costs about twenty
times as much and claude-opus-5 about fifty times as much, and the answers
are better.
Start with model empty and set a single model only if the answers are not
good enough.
Where your ticket text goes
Section titled “Where your ticket text goes”To Anthropic, under your agreement with them rather than ours.
If your privacy assessment needs the data to stay on your own hardware, use the bundled local model instead. The compliance page states which one you have configured.
Troubleshooting
Section titled “Troubleshooting”| Symptom | Cause |
|---|---|
401 on test | Wrong key, or it was revoked in the console |
400 about credit | Billing is not set up on the account |
429 | Rate limited. Anthropic’s limits rise with account history |
| Answers cut off mid-sentence | maxTokens is too low for the model you picked |
| Timeouts | Raise timeoutMs, or pick a faster model |
404 on the model id | The id is wrong, or your account has no access to it |
Alternatives
Section titled “Alternatives”OpenAI-compatible endpoint for anything else, including Azure OpenAI and self-hosted GPU boxes. Ollama for the model that ships in the box.