Setup a Provider

Provider Setup

Setup a Provider

Connect Hrida.ai to your model provider and start chatting in minutes.

Hrida.ai supports multiple connection protocols, including OpenAI-compatible APIs and Anthropic's native API. Any cloud API or local server that speaks one of these protocols works out of the box. Just add a URL and API key, and your models appear in the dropdown.

How It Works

┌──────────────┐         ┌──────────────────┐         ┌──────────────┐
│              │  HTTP    │                  │  Inference│             │
│  Hrida.ai  │────────▶│  Provider API    │────────▶ │    Model     │
│  (frontend)  │◀────────│  (cloud/local)   │◀──────── │  (LLM/VLM)  │
│              │  Stream  │                  │  Tokens  │             │
└──────────────┘         └──────────────────┘         └──────────────┘

1

You type a message in Hrida.ai

2

Hrida.ai sends it to your provider's API endpoint

3

The provider runs inference on the selected model

4

Tokens stream back to Hrida.ai in real time

5

You see the response in the chat interface

Adding a provider is as simple as entering a URL and API key in Admin Settings → Connections. Hrida.ai auto-detects available models from most providers.

---

Cloud Providers

Hosted APIs that require an account and API key. No hardware needed.

Hrida.aiHosted Hrida.ai model API (api.hrida.ai), OpenAI-compatible, managed by Zlabs Innovation

→

LocalAISelf-hosted, open-source OpenAI-compatible server (local)

→

OpenAI-CompatibleGoogle Gemini, DeepSeek, Mistral, Groq, OpenRouter, Amazon Bedrock, Azure, and more

→

OpenAIGPT-4o, GPT-4.1, o3, o4-mini

→

ClaudeClaude Opus, Sonnet, Haiku

→