Quick Start

Welcome to the Arewa AI platform! Access the most advanced models in minutes.

Before you start

Prepare everything to make your first API call with these steps:

Create an inference account in the Arewa AI console.
Generate your API key from the dashboard. Keep it secret and secure.
Install the official OpenAI package for Python. We are 100% compatible.
```
pip install openai
```
Set your API key as an environment variable. It is the safest way to handle your key.
```
export AREWA_API_KEY='tu-api-key-aqui'
```

Chat Completions

Generate text responses for conversational AI. You can use any of the open-source models available on our platform, such as Kimi K2, gpt-oss, or Qwen3, by specifying the `model` parameter. Our API is 100% compatible with the OpenAI Completions API

cURL y Python

The following example shows how to perform a Chat inference:

curl https://api.arewa.ai/inference/v1/chat/completions \
  -H "Authorization: Bearer $AREWA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "Qwen/Qwen3-Next-80B-A3B-Instruct",
    "messages": [
        {
            "role": "user",
            "content": "What is the secret of life?"
        }
    ]
  }'

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.arewa.ai/inference/v1",
    api_key=os.environ.get("AREWA_API_KEY")
)

completion = client.chat.completions.create(
    model="Qwen/Qwen3-Next-80B-A3B-Instruct",
    messages=[
        {
            "role": "user",
            "content": "What is the secret of life?"
        }
    ]
)

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

Embeddings

Create vector representations for your text data. Useful for semantic search, clustering, RAG (Retrieval-Augmented Generation), and more. Our Embeddings API is 100% compatible with the OpenAI Completions API

cURL y Python

Use any of our available embedding models to generate vectors for your text.

curl https://api.arewa.ai/inference/v1/embeddings \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $AREWA_API_KEY" \
  -d '{
    "model": "text-embedding-3-small",
    "input": "What is the secret of life?"
  }'

import os
from openai import OpenAI

# Configura tu AREWA_API_KEY como variable de ambiente
# os.environ["AREWA_API_KEY"] = ""

client = OpenAI(
    base_url="https://api.arewa.ai/inference/v1",
    api_key=os.environ.get("AREWA_API_KEY")
)

response = client.embeddings.create(
    # Selecciona cualquier modelo de embeddings de Arewa AI
    model="text-embedding-3-small", 
    input="What is the secret of life?"
)

# La API retornará una lista de flotantes (embedding)
embedding_vector = response.data[0].embedding
print(f"Embedding vector (first 5 dimensions): {embedding_vector[:5]}")
print(f"Total dimensions: {len(embedding_vector)}")