Back to Blog
announcement

Welcome to SolidRusT AI

Public launch of the SolidRusT AI inference API: OpenAI-compatible chat, embeddings, and RAG on GPUs we run ourselves.

By SolidRusT Networks

SolidRusT AI is live at solidrust.ai. The API is at https://api.solidrust.ai. Keys come from console.solidrust.ai. Docs are at docs.solidrust.ai.

What you actually get

OpenAI-compatible chat and embeddings. Point the official SDK at our base URL.

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!"}],
)

vllm-primary is the chat alias (Gemma 4 12B IT QAT, 16k context). Embeddings use Qwen/Qwen3-Embedding-0.6B (1024-dim). RAG, keyword, hybrid, and graph live under /data/v1/... on the same host.

Start

  1. Create a key at console.solidrust.ai
  2. Call https://api.solidrust.ai/v1/chat/completions
  3. Read docs.solidrust.ai

Pricing is on the homepage. Limits live in the console, not in a copied table.

#launch #api #inference