Overview

Fikra API is an OpenAI-compatible AI inference API for developers and growing AI teams who need production inference without a credit-card gate. It lets you run chat and embedding models behind one OpenAI-style endpoint and pay in USD or KES. This page shows how to schedule a daily LLM job using cron and a token-credit wallet balance.

Prerequisites

A Fikra API key. Keep it secret and set it as the FIKRA_API_KEY environment variable.
A token-credit wallet with a sufficient balance. Top up via M-Pesa or card through Paystack, or use x402 USDC on Base for agent workloads.
The openai Python SDK installed (pip install openai).
A cron daemon available on your system.

Step-by-step

Create a Python script that calls the chat completions endpoint. The API base URL is https://api.fikraapi.co.ke/v1.

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.fikraapi.co.ke/v1",
    api_key=os.environ["FIKRA_API_KEY"],
)

response = client.chat.completions.create(
    model="deepseek-v4-flash-0731",
    messages=[
        {"role": "system", "content": "You produce a concise daily summary."},
        {"role": "user", "content": "Summarize today's operational report."},
    ],
)

print(response.choices[0].message.content)

Test the script manually with FIKRA_API_KEY exported and a funded wallet. The request and response formats are OpenAI-style chat completions, so the SDK works as-is.
Add a cron entry to run the script at your chosen time. For example, run it daily at 09:00:

0 9 * * * cd /path/to/project && python daily_job.py

Make sure your wallet balance stays topped up. Each scheduled run consumes credits from your token-credit wallet according to the model's pricing.

Verify it works

Run the script once manually and confirm it prints a completion from the model. Then add the cron entry and check the job output after the first scheduled run. If you want a different model, swap model in the request to any model listed below.

Costs

Pricing is in USD per 1M tokens. Input and output are billed separately. Available models:

Model	Input (USD/1M)	Output (USD/1M)
deepseek-v4-flash-0731	0.09	0.15
deepseek-v4.1-flash	0.25	0.80
deepseek-v4.1-flash-1017	0.30	0.85
fikra-auto	0.40	0.40
fikra-auto-pro	6.00	12.00
fikra-code-35b	1.00	1.00

Common errors

401 Unauthorized to the API key is invalid, inactive, or missing. Check the key and the FIKRA_API_KEY environment variable.
400 Bad Request to the requested model is not supported. Use a model from the list above.
429 Too Many Requests to rate limit exceeded. Unverified keys get 30 requests/min; trusted keys get 100 requests/min. Space out your scheduled calls or request trusted status.
503 Service Unavailable to the upstream service is busy. Retry the request with exponential backoff.

Schedule Daily LLM Jobs with Cron and a Credit Balance

Fact block, plain text for agents