LLM Chat
Conversational AI for any task
- Mistral 7B, Llama 2/3, and more
- Real-time streaming responses
- Multi-turn conversations
- ~0.0001 credits/token
For AI Users
AI inference, closer to you
Access powerful language models and image generators running on community hardware. Fast responses, fair pricing, no cloud provider markup.
Capabilities
What you can do
Image Generation
Create images from text prompts
- Stable Diffusion XL, FLUX
- Multiple resolutions up to 1024px
- Batch generation support
- ~0.01 credits/image
Getting Started
How it works
-
Create account
Sign up with email or GitHub in seconds.
-
Add credits
Purchase credit packages starting at $10.
-
Submit request
Use the web UI or call our API.
-
Get results
Responses stream from the nearest host.
For Developers
Simple REST API
Integrate Archipelag.io into your applications with our OpenAI-compatible API. Python and JavaScript SDKs available.
- OpenAI-compatible endpoints
- Streaming support
- Python & JavaScript SDKs
- Webhook callbacks
# Python SDK
from archipelag import Client
client = Client(api_key="your-key")
response = client.chat.create(
model="mistral-7b",
messages=[
{"role": "user", "content": "Hello!"}
]
)
print(response.content)// JavaScript SDK
import { Archipelag } from 'archipelag';
const client = new Archipelag('your-key');
const response = await client.chat.create({
model: 'mistral-7b',
messages: [
{ role: 'user', content: 'Hello!' }
]
});
console.log(response.content);Pricing
Pay only for what you use
No subscriptions or commitments. Credits never expire.
| Workload | Rate | Example |
|---|---|---|
| LLM Chat (7B models) | ~0.0001 credits/token | 1M tokens = 100 credits |
| Image Generation | ~0.01 credits/image | 1,000 images = 10 credits |