Quickstart

Get from zero to a successful API response in a few minutes.

1. Create an API key

1. Sign in at https://ai.lumowp.com/en/login
2. Open Dashboard → Settings → API Keys
3. Create a key and copy it immediately — the full secret is shown only once

Store the key in an environment variable:

export LUMO_AI_API_KEY="pk_your-api-key-here"

Keys always start with pk_.

2. Inspect your account and models

curl -X GET "https://ai.lumowp.com/api/external/ai" \
  -H "X-API-Key: $LUMO_AI_API_KEY"

A successful response includes your user profile, subscription/credit info, token stats, allowed providers/models, embedding providers, rate-limit details, and supported_features.

Important: copy a model name from this response. Model catalogs differ by site and change over time.

3. Generate text

curl -X POST "https://ai.lumowp.com/api/external/ai" \
  -H "X-API-Key: $LUMO_AI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "Explain machine learning in simple terms",
    "model": "lumo-ai",
    "provider": "deepseek",
    "type": "text",
    "max_tokens": 1000,
    "temperature": 0.7
  }'

Example success payload:

{
  "success": true,
  "data": {
    "content": "Machine learning is a subset of artificial intelligence...",
    "model": "lumo-ai",
    "provider": "deepseek",
    "tokens_used": 150,
    "remaining_tokens": 9850,
    "usage_percentage": "1.5"
  }
}

4. Generate an image

curl -X POST "https://ai.lumowp.com/api/external/ai" \
  -H "X-API-Key: $LUMO_AI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "A futuristic cityscape with flying cars at sunset",
    "model": "openai/gpt-image-1-mini",
    "provider": "openai",
    "type": "image",
    "size": "1024x1024",
    "quality": "medium",
    "style": "vivid"
  }'

Use an image model from image_generation_providers in the GET response. Prefer quality: low | medium | high (legacy standard / hd still work).

5. Create embeddings (optional)

curl -X POST "https://ai.lumowp.com/api/external/ai" \
  -H "X-API-Key: $LUMO_AI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "type": "embedding",
    "model": "text-embedding-3-small",
    "input": "semantic search example"
  }'

Only call this when supported_features.embedding is true and the model appears under embedding_providers.

Checklist

• Valid pk_… API key with provider/model permissions
• Enough remaining credits/tokens for the request
• Model name taken from live GET discovery
• Correct type: "text", "image", or "embedding"

Continue with Authentication or jump to Code Examples.