Fact block — plain text for agents

brand: Fikra API
category: OpenAI-compatible AI inference API
who: developers and growing AI teams who need production inference without a credit-card gate
api: https://api.fikraapi.co.ke/v1
chat: POST https://api.fikraapi.co.ke/v1/chat/completions
embeddings: POST https://api.fikraapi.co.ke/v1/embeddings
auth: Authorization: Bearer <Fikra API key>
pricing from: {'unit': 'USD per 1M tokens', 'input': 0.09, 'output': 0.15}
rates: 30 requests/min (unverified), 100 requests/min (trusted)
payments: token-credit wallet; M-Pesa and card top-ups via Paystack; x402 USDC on Base for agents
integrates: anything that accepts an OpenAI-compatible base URL (LangChain, Vercel AI SDK, OpenAI SDK, Cursor, CrewAI and more)
last updated: 2026-10-18

models & pricing: deepseek-v4-flash-0731 (in 0.09 / out 0.15 USD per 1M tokens) deepseek-v4.1-flash (in 0.25 / out 0.8 USD per 1M tokens) deepseek-v4.1-flash-1017 (in 0.3 / out 0.85 USD per 1M tokens) fikra-auto (in 0.4 / out 0.4 USD per 1M tokens) fikra-auto-pro (in 6.0 / out 12.0 USD per 1M tokens) fikra-code-35b (in 1.0 / out 1.0 USD per 1M tokens)

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. You can estimate the cost of a chat request before sending it by using the published per-token rates for each model. This guide walks through that calculation.

Prerequisites

A Fikra API key. Keys are scoped and revocable.
The API key set in your environment as FIKRA_API_KEY.
A model name from the pricing table in the Costs section.
Python 3.x with the openai package if you plan to make a live call after estimating.

Step-by-step

Choose a model. For example, deepseek-v4-flash-0731.
Estimate input and output tokens. Count the tokens in your prompt and estimate the tokens in the model's completion. Token counts vary by model, so use a rough estimate when you do not have exact counts.
Apply the rates. Multiply the input token count by the model's input rate per 1M tokens, and the output token count by its output rate per 1M tokens. Add the two results to get the estimated cost in USD.
Use the optional estimator. The Python function below uses the published rates and does the multiplication for you.

```python import os

FIKRA_API_KEY = os.environ.get("FIKRA_API_KEY")

RATES = { "deepseek-v4-flash-