Quick Start
Welcome to the Public AI Inference Utility developer portal.
1. Get your API key
- Sign up: Click Login in the top right and sign up
- Open Account: Go to the Account tab in the top navigation
- Create API key: Open API Keys and click Create API Key
- Generate: Enter a name, set expiration, and click Generate Key
2. Explore available models
See Available Models for the full catalog of hosted models, including Swiss AI Apertus, AISingapore SEA-LION, Allen AI Olmo, and more.
You can also list models programmatically:
Code
Or try it interactively:
3. Make your first request
Once you have an API key, you can start making requests to our AI models. Here's a simple example:
Code
Or try it interactively:
Authentication
All API requests require:
-
API Key: Include your key in the Authorization header:
Code -
User-Agent Header: Specify a User-Agent to prevent bot spamming:
Code
Model configuration
Inference parameters vary by model. See each model's Hugging Face card on the Available Models page, and use GET /v1/models for context_length and pricing.
Rate limits and billing
Rate limits depend on your plan tier. See Plans & Rate Limits for details on Free, Plus, Pro, and Enterprise tiers. Usage and wallet balance are available under Account → Billing.
Support
- API Reference: Explore the full API Reference
- Community: Join our discussions at github.com/forpublicai
- Issues: Report problems via GitHub Issues
What's next?
- Browse Available Models and pick the right model for your use case
- Review Plans & Rate Limits and Billing for usage and pricing
- Explore the complete API Reference for detailed endpoint documentation
- Support Us to upgrade to the Plus tier via OpenCollective