B
Brioworkx
AI Platform
Checking status…

Build AI products,
not infrastructure.

One OpenAI-compatible API covering chat, vision, search, and speech — running entirely on your own GPUs, with nothing routed through a third party.

Get started → Manage API keys
Base URL https://ai-platform.fincover.com
brioworkx-chat brioworkx-vision brioworkx-embed brioworkx-rerank brioworkx-stt tts ocr
7
services, one base URL
2 GPU
self-hosted, no external inference
600+
TTS languages, zero-shot cloning
100%
yours — no data leaves your infrastructure
Why Brioworkx

Infrastructure you already trust

The same OpenAI SDK you already use, pointed at hardware you control.

Drop-in compatible
OpenAI Chat Completions, Embeddings, Audio, and Cohere-style Rerank shapes — swap the base URL and key, ship the same code.
Self-hosted, private by default
Every request stays on your own GPUs. No prompts, documents, or audio ever leave your infrastructure.
One key, full observability
Per-key spend, rate limits, and live logs from the Console — scope a key to exactly the models a project needs.
Quickstart

Point your SDK, nothing else changes

Set the base URL and your key — the rest of your OpenAI SDK code works unmodified.

shell
curl https://ai-platform.fincover.com/v1/chat/completions \
  -H "Authorization: Bearer $BRIOWORKX_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"brioworkx-chat","messages":[{"role":"user","content":"Hello!"}]}'
python
from openai import OpenAI

client = OpenAI(
    base_url="https://ai-platform.fincover.com/v1",
    api_key="sk-your-key"
)

response = client.chat.completions.create(
    model="brioworkx-chat",
    messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)
typescript / node.js
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://ai-platform.fincover.com/v1",
  apiKey: process.env.BRIOWORKX_KEY,
});

const response = await client.chat.completions.create({
  model: "brioworkx-chat",
  messages: [{ role: "user", content: "Hello!" }],
});
console.log(response.choices[0].message.content);
Platform

Every service, one base URL

All 7 services share the same base URL and API key — scope a key down to just the ones a project needs.

Chat
Gemma-4-31B-IT-NVFP4 · brioworkx-chat

Full conversational intelligence with streaming, tool use, and long context. OpenAI Chat Completions shape.

POST /v1/chat/completions
Vision
Gemma-4-31B-IT-NVFP4 · brioworkx-vision

Analyze images, charts, and scanned documents. Same natively multimodal backend as chat — pass image URLs or base64 via the messages array.

POST /v1/chat/completions
Embeddings
BGE-M3 · brioworkx-embed

1024-dim multilingual vectors for semantic search and RAG. Same response shape as OpenAI embeddings.

POST /v1/embeddings
Rerank
BGE-Reranker-v2-M3 · brioworkx-rerank

Cohere-style relevance scoring. Pass a query and documents; receive results sorted by score.

POST /v1/rerank
Speech-to-Text
Whisper large-v3 · brioworkx-stt

Multilingual transcription with auto language detection. Force a language with language=ta.

POST /v1/audio/transcriptions
Text-to-Speech
OmniVoice · 600+ languages

Zero-shot voice cloning across 600+ languages. The same cloned persona speaks any of them. Returns WAV.

POST /v1/tts
OCR
RapidOCR

Extract text from images and documents. Returns text plus per-line score for confidence filtering.

POST /v1/ocr/file

Get your API key

  1. 1Open the Console and sign in with your admin credentials.
  2. 2Go to Gateway → Virtual Keys → Create New Key, scope it to the models you need (brioworkx-chat, brioworkx-embed, etc).
  3. 3Copy the sk-… key — shown once. Set it as $BRIOWORKX_KEY and you're ready.
Open Console → Manage keys