Welcome
Welcome to the Bulutistan LLMaaS documentation.
What is Bulutistan LLMaaS?
Bulutistan LLMaaS is an enterprise-grade AI platform that enables organizations to deploy, manage, and scale AI workloads using open-source models. Featuring high-performance inference powered by vLLM, with a fully OpenAI-compatible API.
Whether you're building chatbots, content generation tools, or AI-powered features, the platform handles the infrastructure complexity so you can focus on building great products.
Key Features
| Feature | Description |
|---|---|
| Multi-Tenant Architecture | Isolated environments for each organization with separate API keys and usage tracking |
| High-Performance Inference | Powered by vLLM for optimized throughput and low latency |
| Multiple Model Support | Access various open-source LLMs including Llama, Mistral, and more |
| Usage & Billing | Token-level usage tracking with detailed analytics and per-cycle reporting |
| Rate Limiting | Configurable limits per tenant to ensure fair resource allocation |
| Image Generation | Generate images via the /v1/images/generations endpoint using compatible models |
| OpenAI Compatible | Drop-in replacement for OpenAI API - use existing SDKs with minimal changes |
OpenAI SDK Compatibility
The platform is fully compatible with OpenAI's Python and Node.js SDKs. Simply change the base URL to start using it:
from openai import OpenAI
client = OpenAI(
api_key="sk-proj-your-api-key",
base_url="https://api.bulutistan.ai/v1"
)
response = client.chat.completions.create(
model="meta-llama/Llama-3.1-8B-Instruct",
messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)
All standard OpenAI endpoints are supported: /v1/chat/completions, /v1/completions, /v1/embeddings, /v1/images/generations, and /v1/models.
Documentation Sections
For Developers
| Section | Description |
|---|---|
| Getting Started | Set up your environment in 5 minutes |
| API Reference | Full API documentation |
| OpenAI Compatible | OpenAI SDK-compatible endpoints |
| Portal | Using the web dashboard |
| Integration | Language-specific integration guides |
Guides
| Guide | Description |
|---|---|
| Streaming | Handle streaming responses |
| Rate Limiting | Handle rate limits gracefully |
| Error Handling | Troubleshooting guide |