Overview
Fireworks serves open models quickly. If you use a Fire Pass plan, make a dedicated Fire Pass key.
Get a key
- 1Sign in at app.fireworks.ai.
- 2Open Settings → Users → API Keys and choose Create API Key. Name it.
- 3Copy the key. It is not shown again.
Cost. Billed by usage. Check the dashboard for any starting credit.
Add it to Loom
- 1Open Loom, then Providers in the menu, and choose Add provider.
- 2Pick Fireworks AI (the search box finds it).
- 3Fill in the fields in the table below.
- 4Choose Connect. Loom checks the key and says how many models it found. If it cannot check, it says so, and you can Save anyway and try a message.
- 5Open the model chip below the message box and pick a model.
| Field in Loom | What to put | Needed |
|---|---|---|
| API key | Paste the key you copied. Create one at app.fireworks.ai → API keys. | Yes |
| Endpoint | https://api.fireworks.ai/inference/v1 | Pre-filled |
| Name | Anything you like. It is shown in the model picker | Optional |
At a glance
| Appears in Loom as | Fireworks AI |
| Sign-in | Your key, sent as Authorization: Bearer |
| Models | Loom fetches the list from your account |
| Tools (connectors, search) | Depends on the model |
| Photos | Depends on the model |
| PDFs | No |
Good to know
Fireworks cuts replies at 2,048 tokens by default. Loom sets a larger limit for you.
If something goes wrong
| What you see | What to do |
|---|---|
| 401 | Create a new key and paste it again. |
| A model name is refused | Fireworks names look like accounts/fireworks/models/…. Use the live list. |