Platform Tour
Explore the Skytells Console, Dashboard, and API — your command center for building AI-powered products.
What you'll be able to do after this module
By the end of this short tour you'll know exactly where to go to get an API key, test any model without code, and understand how the REST API is structured — so nothing slows you down in Module 2 (Models & Billing).
The three interfaces
Skytells gives you three entry points depending on whether you're exploring, managing, or building:
| Interface | URL | Best for |
|---|---|---|
| Console | skytells.ai/console | Test any model interactively, no code required |
| Dashboard | skytells.ai/dashboard | API keys, usage analytics, billing |
| REST API | api.skytells.ai/v1 | Everything your app needs |
| Edge API | edge.skytells.ai/v1 | Ultra-low latency (Business/Enterprise) |
The REST API exposes two separate sub-APIs under the same base URL. The Prediction API (/v1/predictions) generates images, video, and audio. The Inference API (/v1/chat/completions, /v1/responses, /v1/embeddings) runs LLM text models. You'll learn both in this path.
Step 1: Create your account and get an API key
Create your account
Go to skytells.ai and sign up. A free account gives you enough quota to work through this entire course.
Open the API Keys page
Navigate to Dashboard → API Keys.
Click "Generate New API Key" and give it a name like dev-learning.
Save your key immediately
Copy the key — it starts with sk-. You can only see it once. Paste it into a .env file or your terminal:
export SKYTELLS_API_KEY="sk-your-key-here"Never commit your API key to source control. If you accidentally expose a key, revoke it immediately from the Dashboard and generate a new one.
Step 2: Try your first model in the Console
Before writing a single line of code, spend 5 minutes in the Console to understand what models can do.
Select a model
Choose TrueFusion Pro from the model selector — this is Skytells' flagship image model.
Write a prompt and generate
Try: A photorealistic mountain lake at sunrise, golden light, reflections
Click Generate and watch the output. This same call — the exact same JSON — is what your code will send to the API.
Inspect the response
Scroll down to the Response panel. You'll see a JSON object with an id, status, and output field. This is the prediction object — the core data structure of the entire API.
The Console's "Copy as cURL" button generates a ready-to-run terminal command with your prompt pre-filled. Use this to quickly prototype before writing SDK code.
The API structure
All programmatic access uses one consistent pattern across every model:
POST https://api.skytells.ai/v1/predictions → create a prediction
GET https://api.skytells.ai/v1/predictions/:id → get status + output
GET https://api.skytells.ai/v1/models → list all models
GET https://api.skytells.ai/v1/models/:id → get model detailsThe API is OpenAI-compatible. If you already use OpenAI's API, you can often switch to Skytells by changing two things: the base URL and the API key.
Good news for OpenAI users: The same POST /v1/chat/completions endpoint works on Skytells — you don't need to rewrite any existing code to get started.
Plans at a glance
| Plan | Standard rate limit | Edge API | Who it's for |
|---|---|---|---|
| Free | 60 req/min | — | Learning, prototyping |
| Pro | 600 req/min | — | Solo developers, small products |
| Business | Custom | ✓ | Teams, higher volume |
| Enterprise | Custom | ✓ | Large-scale production |
The Edge API is only available on Business and Enterprise plans, and only for models that explicitly support Edge routing (e.g., truefusion-edge, flux-1-edge).
What you now understand
| Concept | Where |
|---|---|
| Create and manage API keys | Dashboard → API Keys |
| Test any model without code | Console |
| Production API calls | api.skytells.ai/v1 |
| Low-latency edge (Business+) | Edge API — edge.skytells.ai/v1 |
| View usage and billing | Dashboard |
| Generate images, video, audio | Prediction API — POST /v1/predictions |
| LLM text generation | Inference API — POST /v1/chat/completions |
Up next: you'll use your API key to make your first real prediction — generating an image from a terminal, in Python, and in TypeScript.
AI Foundations
Your starting point. Tour the Skytells platform, understand both APIs, make your first Prediction and Inference calls, and handle errors in production.
Models & Billing
Navigate Skytells' full model catalog — image, video, audio, and text/LLM models — and accurately estimate costs before you build.