A clean API for African AI.
RESTful and familiar. If you've used any major LLM API, you'll feel at home in minutes.
Authentication
Authenticate requests using a Bearer token in the Authorization header. API keys are prefixed with sk-rnt-.
Authorization: Bearer sk-rnt-xxxxxxxxxxxxChat Completions
Send messages to any Rantera model and receive completions. The primary endpoint for all conversational, reasoning, and generative tasks.
POST https://api.rantera.ai/v1/chat/completions
Authorization: Bearer sk-rnt-...
Content-Type: application/json
{
"model": "hira",
"messages": [
{
"role": "system",
"content": "You are Hira, a warm and culturally-aware AI assistant built for African users."
},
{
"role": "user",
"content": "What are the best ways to grow a small business in Lagos?"
}
],
"max_tokens": 1024,
"temperature": 0.7
}{
"id": "rnt-chat-a7f3b2c1d0e9",
"object": "chat.completion",
"created": 1751400000,
"model": "hira",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "Ah, Lagos business! Let me give you the real picture. First, your network is everything — relationships open more doors than any pitch deck ever will..."
},
"finish_reason": "stop"
}
],
"usage": {
"prompt_tokens": 72,
"completion_tokens": 388,
"total_tokens": 460
}
}Models
Pass the model ID in the model field of your request.
| Model ID | Description | Status |
|---|---|---|
| hira | Rantera's conversational model. Warm, witty, and built for genuine dialogue. Africa-aware, Pidgin-fluent. | Live |
| rant-ai | Cybersecurity specialist. Threat analysis, vulnerability assessment, and security guidance. | Coming soon |
| akili | Reasoning and analytical model. Deep thinking, structured problem solving. | Coming soon |
| ilimi | Education and knowledge model. Tutoring, explanation, and learning support. | Coming soon |
| ona | Creative model. Writing, storytelling, ideation, and content generation. | Coming soon |
| ogbon | Business and strategy model. Market analysis, planning, and decision support. | Coming soon |
Parameters
| Field | Type | Required | Description |
|---|---|---|---|
| model | string | Required | Model ID to use. See Models table above. |
| messages | array | Required | Array of message objects with "role" (system | user | assistant) and "content" (string). |
| max_tokens | integer | Optional | Maximum tokens to generate. Default 4096. |
| temperature | float | Optional | Sampling temperature between 0 and 2. Lower is more deterministic. Default 0.7. |
Ready to build? Create your account and generate an API key in seconds.
Free to start. No credit card required.
Get your API keyUsage & Legal
Keep your API key secure
Treat your API key like a password. Do not expose it in client-side code, public repositories, or browser environments. If a key is compromised, delete it immediately from your dashboard and generate a new one. Rantera is not liable for charges or misuse resulting from a leaked key.
Acceptable use
API usage is governed by the Rantera EULA and Privacy Policy. You may not use the API to generate harmful, illegal, or deceptive content, or to build products that violate applicable law. Rantera reserves the right to suspend or terminate API access for violations without notice.
Model output disclaimer
Rantera model outputs are AI-generated and may be inaccurate, incomplete, or outdated. They do not constitute professional advice — legal, medical, financial, or otherwise. You are responsible for evaluating outputs before using them in any application, and for ensuring your use complies with all applicable regulations in your jurisdiction.
Data & privacy
Inputs and outputs processed through the API may be retained and used to improve Rantera models, in accordance with our Privacy Policy and EULA Section 4. Data is anonymised before any training use. Rantera complies with the Nigeria Data Protection Act 2023 (NDPA). If your application processes personal data, you are responsible for obtaining appropriate consent from your end users.