Welcome to SolidRusT AI

We’re excited to announce the public launch of SolidRusT AI - an enterprise-grade AI inference API platform designed for developers who need reliable, fast, and cost-effective AI capabilities.

What We Offer

OpenAI-Compatible API

Our API is fully compatible with OpenAI’s client libraries. Just point your existing code to our endpoint and you’re ready to go:

from openai import OpenAI

client = OpenAI(
    base_url="https://api.solidrust.ai/v1",
    api_key="your-api-key"
)

response = client.chat.completions.create(
    model="vllm-primary",
    messages=[{"role": "user", "content": "Hello!"}]
)

Key Features

• Chat Completions: High-performance LLM inference with sub-50ms latency
• Embeddings: Text embeddings using BGE-M3 model
• RAG Pipeline: Built-in retrieval-augmented generation
• AI Agents: Tool-enabled agents for complex tasks

Getting Started

1. Visit console.solidrust.ai to create your account
2. Generate an API key from the dashboard
3. Start making requests to api.solidrust.ai

Pricing

We offer a generous free tier to get started, with transparent usage-based pricing for production workloads. Check our pricing page for details.

We’re committed to building the best AI inference platform for developers. If you have questions or feedback, reach out at support@solidrust.net.