Jan connects to Anoman as a custom model provider — a desktop chat UI backed by the full guardrail pipeline.

Prerequisites

An Anoman API key — create one in the dashboard (format anm-sk-…).
Jan installed and up to date.
A model ID from the Anoman catalog, e.g. gpt-4o, gpt-4o-mini, or claude-sonnet-4-6.

Enable streaming for long agent runs

Set stream: true on requests. Autonomous, multi-step, and long-thinking tasks can exceed the 100-second edge timeout and fail with a 524 error; streaming returns tokens as they are generated and keeps the connection alive, so the request completes. Most tools stream by default — confirm it is on for agentic use.

More detail in the streaming guide.

Add a custom provider

In Jan, go to Settings → Model Providers → Add Custom Provider, choose OpenAI-compatible, and enter Anoman's base URL (include /v1) and your key.

Format:    OpenAI-compatible
Base URL:  https://api.anoman.io/v1
API Key:   anm-sk-your-key-here

Prefer Anthropic?

Jan also offers an Anthropic-compatible format — point it at Anoman's Anthropic endpoint.

Format:    Anthropic-compatible
Base URL:  https://api.anoman.io/anthropic
API Key:   anm-sk-your-key-here

Pick a model

Add a model from the Anoman catalog and start chatting.

# Any Anoman model works, e.g.:
gpt-4o
gpt-4o-mini
claude-sonnet-4-6
claude-haiku-4-5

Verify the guardrails are active

Every Anoman response carries guardrail result headers. Inspect them in your dashboard traces to confirm the pipeline is running on Jan requests — prompt-injection detection, PII masking, and content moderation all apply automatically.

X-Anoman-Guardrail-Injection: pass score=0.03
X-Anoman-Guardrail-Pii: pass
X-Anoman-Guardrail-Content: pass
X-Anoman-Cache: none

Need help with your integration?

Join the Founding 50 for early access and direct support from the Anoman team.

Join Founding 50

Connect Jan to Anoman AI