Flarite Docs

Bring Your Own Model (BYOM)

Bypass Flarite's prompt counter by routing AI through your own Cloudflare Workers AI account.

What is BYOM?

BYOM (Bring Your Own Model) lets you connect your own Cloudflare Workers AI account to Flarite. When enabled, all AI inference is billed directly to your Cloudflare account instead of consuming from Flarite's shared prompt pool.

Benefits

  • Unlimited prompts — no monthly cap while BYOM is active
  • Lower cost at scale — Cloudflare Workers AI pricing is pay-per-token
  • Your own account — usage logs appear in your Cloudflare dashboard
  • Same models — Flarite uses the same model selection either way
💡
NoteBYOM is available on Pro, Elite, and Enterprise plans.

How to enable BYOM

  1. Go to your Flarite dashboard → Settings → Model.
  2. Toggle "Bring Your Own Model" on.
  3. Enter your Cloudflare Account ID and an AI-enabled API Token.
  4. Click Save — Flarite will validate the credentials immediately.

Getting a Cloudflare AI token

  1. Go to dash.cloudflare.com → My Profile → API Tokens.
  2. Create a token with the Workers AI — Run permission.
  3. Scope it to your account.
  4. Copy and paste into Flarite's BYOM settings.
✨
TipYour Cloudflare Account ID can be found on the right sidebar of any Cloudflare dashboard page, or in the URL: dash.cloudflare.com/[account-id]