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 inference service hosted in Kenya. It lets developers run chat (and embeddings) behind the same OpenAI‑style endpoints without a credit‑card gate.

Prerequisites

Python 3.8+
openai package (pip install openai)
Environment variable FIKRA_API_KEY containing your Fikra API key
Internet access to https://api.fikraapi.co.ke/v1

Step‑by‑step

import os
import openai

openai.api_key = os.getenv("FIKRA_API_KEY")
openai.base_url = "https://api.fikraapi.co.ke/v1"

response = openai.ChatCompletion.create(
    model="deepseek-v4-flash-0731",
    messages=[{"role": "user", "content": "Hello, world!"}],
    stream=False
)
print(response.choices[0].message.content)

Verify it works

Run the script; you should receive a JSON response with the assistant’s reply. If the call succeeds, the endpoint replacement is complete.

Costs

Default pricing is $0.09 USD per 1M input tokens and $0.15 USD per 1M output tokens. Model‑specific rates (e.g., deepseek-v4-flash-0731) follow the same tier; see the pricing page for other models.

Common errors

401 Unauthorized – API key missing, malformed, or inactive.
400 Bad Request – Model name not supported or request format invalid.
429 Too Many Requests – Exceeded rate limit (30 req/min unverified, 100 req/min trusted).
503 Service Unavailable – Upstream busy; retry with exponential backoff.