Inference on our own iron

OpenAI-compatible chat, embeddings, and RAG — served from GPUs we actually run. Refurbished machines, assembled like we meant it.

Get an API key Read the docs

OpenAI-compatible

Drop-in base URL

Own GPUs

5 nodes in the rack

Same stack as our apps

We dogfood the API

POST /v1/chat/completions

curl https://api.solidrust.ai/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "vllm-primary",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Used in production by

MyAshes.ai AI Companion Platform Aidiant.com AI Council Platform SolidRusT.net Zone AI Companion

What we already run on it

Our own products hit the same API you get a key for.

MyAshes.ai

AI Companion Platform

Companion conversations on the vLLM chat endpoint, with the RAG pipeline for memory that is actually grounded.

Aidiant.com

AI Council Platform

Per-member tool access on the agent endpoints, one inference backend behind a council of specialists.

SolidRusT.net

Zone AI Companion

Hybrid search over the community wiki — natural-language questions, vector plus keyword answers.

What the API actually does

OpenAI-compatible where it matters. Same key for chat, embeddings, RAG, and agents.

Chat Completions

OpenAI-compatible chat. Streaming, function calling, context management.

/v1/chat/completions

Text Embeddings

1024-dimensional vectors (BAAI/bge-m3) for search, clustering, and RAG.

/v1/embeddings

RAG Pipeline

Semantic search, keyword search, and knowledge-graph queries on the same key.

/data/v1/query/*

AI Agents

Tool-enabled agents with automatic function execution.

/v1/agent/chat

Custom Endpoints

Dedicated routes, a database, and a namespace when shared iron is not enough.

/your-api/*

Usage Analytics

Token tracking and cost monitoring in the console.

Console

Call it like OpenAI

Point the official SDK at our base URL. No new client required.

APIInteractive Playground

Try it live!

API Key

Get your API key from console.solidrust.ai

Quick Examples

Prompt

View cURL equivalent

curl -X POST https://api.solidrust.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "vllm-primary",
    "messages": [{"role": "user", "content": "Say hello and introduce yourself briefly."}],
    "max_tokens": 512,
    "temperature": 0.7
  }'

Python

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!"}
    ],
    stream=True
)

for chunk in response:
    print(chunk.choices[0].delta.content, end="")

JavaScript

import OpenAI from 'openai';

const client = new OpenAI({
  baseURL: 'https://api.solidrust.ai/v1',
  apiKey: 'your-api-key',
});

const stream = await client.chat.completions.create({
  model: 'vllm-primary',
  messages: [
    { role: 'user', content: 'Hello!' }
  ],
  stream: true,
});

for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content || '');
}

Endpoints

Endpoint	Description	Model
`/v1/chat/completions`	Chat completions (OpenAI compatible)	vllm-primary
`/v1/embeddings`	Text embeddings (1024-dim)	bge-m3
`/data/v1/query/semantic`	Semantic vector search	-
`/data/v1/query/hybrid`	Hybrid search (vector + keyword + graph)	-
`/v1/agent/chat`	Tool-enabled AI agent	vllm-primary
`/v1/models`	List available models	-