By Fikra DevRel • 4 min read

Understanding Fikra API Billing: Token Credits and Payment Methods

Understanding Fikra API Billing: Token Credits and Payment Methods

Fikra API operates on a token-credit wallet system. This means you purchase credits that are deducted as you consume tokens through API requests. The platform integrates with Paystack for billing, and the public website states that M-Pesa and card payments are accepted.

How the Token-Credit Wallet Works

When you use Fikra API, your requests consume tokens. These tokens are deducted from your account's credit balance. You do not pay per request directly; instead, you top up your wallet with credits, and the system deducts the cost of each request from that balance.

Account and Top-Up Flow

  1. Access the Dashboard: Log in to the Fikra dashboard to manage your account.
  2. Top Up Credits: Use the billing section to add credits to your wallet. The platform supports M-Pesa and card payments via Paystack.
  3. Verify Balance: Ensure your wallet has sufficient credits before making API calls to avoid interruptions.

Monitoring Balance and Handling HTTP 402

Developers should monitor their token-credit balance to prevent service interruptions. If your balance is insufficient, the API will return an HTTP 402 (Payment Required) status code. Handle this by:

  • Checking your balance in the dashboard.
  • Topping up your wallet with additional credits.
  • Retrying the request once the balance is sufficient.

Security Advice

Never expose your Fikra API key in browser code or client-side applications. API keys should be stored securely on the server side and accessed via environment variables (e.g., FIKRA_API_KEY). Exposing keys in client-side code can lead to unauthorized usage and potential financial loss.

Note on Payment Methods

While M-Pesa and card payments are publicly stated as accepted methods, always confirm the latest payment options and availability with Fikra before use, as these may vary by region or change over time.


JM
// The Founder

James Miano

CTO & ML Engineer at Lacesse Ventures. James specializes in low-overhead LLM quantization processes, custom ternary weights architectures, and localized server optimization.

Stop paying for overpriced round-trip latency

Why route queries over Western servers when you can use low-overhead hardware located in Nairobi? Save 87% on your monthly inference spend. No minimum credit limits. M-Pesa ready.

usagestatusdashboard