Available Models

The Public AI Gateway provides a unified, OpenAI-compatible API for open-source models from multiple inference partners. Model IDs use the format provider/model-name.

List Models

Fetch the current catalog programmatically:

Code
 
curl -X GET https://api.publicai.co/v1/models \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "User-Agent: MyApp/1.0"

Each model entry includes id, owned_by, and — when available — pricing (per million tokens) and context_length. See the Billing page for the latest per-model pricing.

Inference parameters (temperature, top_p, max_tokens, etc.) vary by model. Check each model's Hugging Face card in the catalog below for provider recommendations, and use GET /v1/models for context_length and pricing.

Model Catalog

Example Requests

Swiss AI Apertus:

Code
 
curl -X POST https://api.publicai.co/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "User-Agent: MyApp/1.0" \
  -d '{
    "model": "swiss-ai/apertus-v1.5-8b",
    "messages": [
      { "role": "user", "content": "Explain open-source AI in one paragraph." }
    ]
  }'

Allen AI Olmo:

Code
 
curl -X POST https://api.publicai.co/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "User-Agent: MyApp/1.0" \
  -d '{
    "model": "allenai/Olmo-3-7B-Instruct",
    "messages": [
      { "role": "user", "content": "What is machine learning?" }
    ]
  }'

AISingapore SEA-LION:

Code
 
curl -X POST https://api.publicai.co/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "User-Agent: MyApp/1.0" \
  -d '{
    "model": "aisingapore/Gemma-SEA-LION-v4-27B-IT",
    "messages": [
      { "role": "user", "content": "Hello!" }
    ]
  }'