Jan

Jan is a desktop chat app that runs local models and remote ones side by side. Adding Hyphen is a form in the settings, not a config file.

Setup guide: this config comes from Jan's official documentation and has not been run end to end against the gateway. Corrections to support@hyphen-solution.com.

1. Get a key

app.hyphen-solution.com → sign in → pick a plan or credit pack → Dashboard → API Keys. Copy the sk-... key.

2. Add the provider

Settings (⚙️) → Model Providers → Add Provider (+)

Fill in the dialog:

• API format: OpenAI-compatible
• Provider name: Hyphen
• Base URL: https://api.hyphen-solution.com/v1
• API key: sk-YOUR_KEY

Save.

3. Add the models

Jan does not auto-populate the model list for custom providers. Open the Hyphen provider you just created, find its Models section, and use the + button to add each ID you want:

Code
minimax-m3
minimax-m2.7
minimax-m2.5
minimax-text-01

Type the IDs exactly. They are real MiniMax model names and anything else returns an error. The full list is on the Models page.

4. Verify

Start a new thread, pick Hyphen → minimax-m3 in the model selector, and send:

Code
Reply with the single word: connected

Troubleshooting

• Provider saves but no models appear. You skipped step 3. Custom providers start with an empty model list.
• 401. Wrong key. Re-copy it from the console.
• 404. The Base URL is missing the /v1 suffix.
• Empty replies. Reasoning models need output headroom. See Choosing a model.
• 429. Monthly budget spent. See Rate limits & caps.
• UI moved? Jan's settings layout changes between releases. Check Jan's custom endpoint docs.

Related

• Models: the full catalog.
• Choosing a model: which model for which job.