Files
OmniRoute/docs/getting-started/PROVIDERS-GUIDE.md

12 KiB

title, version, lastUpdated
title version lastUpdated
Providers Guide: Connect AI Models to OmniRoute 3.8.50 2026-08-06

Providers Guide: Connect AI Models to OmniRoute

TL;DR: A provider is a connection to an AI service (like OpenAI, Anthropic, Google). You need at least one provider to use OmniRoute.


What Is a Provider?

Think of a provider like a phone carrier. Just as you need a phone carrier to make calls, you need an AI provider to use AI models. OmniRoute is like a phone that works with all carriers — you can switch between them automatically.

Types of Providers

Type What It Is Examples Cost
Free access A documented free tier or no-auth path; limits and terms still apply OpenCode Free, Pollinations, Groq $0 within the upstream allowance
API Key You need an API key OpenAI, Anthropic, Google Pay per use
OAuth Login with your account Claude Code, GitHub Copilot Subscription
Web Cookie Uses your browser session ChatGPT Web, Gemini Web $0 (uses your account)

Quick Start: Connect Your First Provider

Optional first-run free-provider setup

The first-run wizard offers an explicit Set up free providers card. It derives the current eligible list from OmniRoute's no-auth provider registry, then lets you review and deselect each provider before confirming. OmniRoute shows the provider's caution notice and a link to its site so you can review third-party terms, privacy, availability, and rate limits first.

This action is optional: finishing the wizard never creates free-provider connections silently. It creates only providers that are still missing, leaves existing customized connections untouched, and reports created, already-configured, and failed providers individually. You can safely retry only the failures after a partial result.

Option A: Free Provider (No Credit Card)

  1. Open the dashboard at http://localhost:20128
  2. Go to ProvidersAdd Provider
  3. Select a provider with a documented free-access path:
    • OpenCode Free — public no-auth endpoint; rate limits and upstream terms apply
    • Pollinations — selected keyless models; premium models require an API key
    • LongCat — one-time 10M-token signup grant; account and KYC required
    • Cloudflare Workers AI — 10K neurons/day; API token and Account ID required
    • Kiro AI — 50 credits/month through OAuth; Kiro's terms prohibit third-party proxy/harness use
  4. Click Connect
  5. Done. The connection can use the provider's current free allowance; model availability, quotas, regions, account requirements, and terms may change.

Option B: API Key Provider (Paid)

  1. Get an API key from the provider's website:
  2. Open the dashboard at http://localhost:20128
  3. Go to ProvidersAdd Provider
  4. Select your provider
  5. Paste your API key
  6. Click Connect
  7. Done! You now have access to that provider's models.

Option C: OAuth Provider (Subscription)

  1. Open the dashboard at http://localhost:20128
  2. Go to ProvidersAdd Provider
  3. Select your provider (e.g., Claude Code, GitHub Copilot)
  4. Click Connect with OAuth
  5. Login with your account
  6. Done! You now have access to your subscription models.

Best Free Providers

These providers have documented free-access paths. Authentication, account, KYC, rate, model, region, privacy, and provider-policy requirements vary.

Provider Documented free access Example models How to connect / caveat
OpenCode Free No published token cap Current *-free models from the upstream catalog No auth; rate limits and upstream terms apply
Pollinations Selected keyless models OpenAI, Qwen Coder, Mistral, DeepSeek, Grok No auth for the keyless subset; premium models need a key
LongCat 10M tokens once LongCat-2.0 API key + signup + KYC; not a recurring allowance
Cloudflare Workers AI 10K neurons/day Llama, Gemma, Qwen, GLM, Kimi API token + Account ID
Kiro AI 50 credits/month Claude Sonnet 4.5, Haiku 4.5, DeepSeek, MiniMax, GLM OAuth account; ToS prohibits third-party proxy/harness use
NVIDIA NIM Current development access; no published token cap in the catalog NVIDIA's current hosted model catalog API key; rate and model limits apply
Cerebras 1M tokens/day, 30K TPM, 5 RPM Current Cerebras-hosted models API key; current model-specific limits apply
Qwen Web No published token cap Current Qwen web models Login token; session reliability and provider terms apply
Qoder No published token cap for the documented free path Current Qoder catalog Account credentials; account, daily, and ToS limits apply

Tip: Connect multiple providers with documented free access to broaden fallback capacity; quotas, rate limits, and provider terms still apply.


Best Paid Providers

These providers offer high-quality models with API keys:

Provider Representative models Cost model Free-access note
OpenAI Current GPT and reasoning models Usage-based No general free API allowance documented in the catalog
Anthropic Current Claude models Usage-based No general free API allowance documented in the catalog
Google AI Studio Gemini models Usage-based beyond free quotas Free tier exists; current per-model quotas and regional limits apply
DeepSeek Current DeepSeek models Usage-based 5M-token one-time signup grant in the audited catalog; expiry/account terms apply
Groq Llama, GPT-OSS, and Qwen models Usage-based beyond free quotas Free tier is model-specific; RPM/RPD limits vary
xAI Grok models Usage-based No general free API allowance documented in the catalog

How to Connect a Provider (Step-by-Step)

Step 1: Open the Dashboard

Go to http://localhost:20128 in your browser.

Step 2: Go to Providers

Click Providers in the sidebar.

Step 3: Click Add Provider

Click the + Add Provider button.

Step 4: Select Your Provider

Browse the list or search for your provider. Click on it.

Step 5: Enter Credentials

  • No-auth providers: no credential is stored by OmniRoute; rate limits and upstream terms still apply
  • API key providers: Paste your API key
  • OAuth providers: Click Connect with OAuth and login

Step 6: Test the Connection

Click Test Connection to verify it works.

Step 7: Done!

Your provider is now connected. You can use it with model: "auto" or specify the provider directly.


Using Multiple Providers

OmniRoute works best with multiple providers. This gives you:

  • Automatic fallback — If one provider fails, OmniRoute tries the next
  • Cost optimization — OmniRoute picks the cheapest provider for each request
  • Speed optimization — OmniRoute picks the fastest provider for each request
  • Quality optimization — OmniRoute picks the best provider for each task

Connect at least 3 providers for the best experience:

  1. One free provider (Kiro, OpenCode Free, or Pollinations) — Always available
  2. One fast provider (Groq, Cerebras) — For quick responses
  3. One quality provider (OpenAI, Anthropic, Google) — For complex tasks

Then use model: "auto" and OmniRoute will automatically pick the best one for each request.


Provider-Specific Setup

OpenAI

  1. Get API key: https://platform.openai.com/api-keys
  2. In OmniRoute: Providers → Add Provider → OpenAI
  3. Paste API key → Connect

Anthropic

  1. Get API key: https://console.anthropic.com/
  2. In OmniRoute: Providers → Add Provider → Anthropic
  3. Paste API key → Connect

Google (Gemini)

  1. Get API key: https://aistudio.google.com/apikey
  2. In OmniRoute: Providers → Add Provider → Gemini
  3. Paste API key → Connect

DeepSeek

  1. Get API key: https://platform.deepseek.com/
  2. In OmniRoute: Providers → Add Provider → DeepSeek
  3. Paste API key → Connect

Groq

  1. Get API key: https://console.groq.com/
  2. In OmniRoute: Providers → Add Provider → Groq
  3. Paste API key → Connect

Common Questions

"Do I need to pay to use OmniRoute?"

No! OmniRoute is free and open-source. You can use free providers (Kiro, OpenCode Free, Pollinations) without paying anything. You only pay if you choose to use paid providers.

"Which provider should I start with?"

Start with Kiro AI — it's free, requires no API key, and gives you access to Claude models. Then add more providers as needed.

"Can I use multiple providers at once?"

Yes! That's the whole point of OmniRoute. Connect multiple providers and use model: "auto" to let OmniRoute pick the best one for each request.

"What if a provider goes down?"

OmniRoute automatically skips failed providers and tries the next one. You don't need to do anything.

"How do I disconnect a provider?"

Go to Providers → click on the provider → click Disconnect.

"Can I use my existing API keys?"

Yes! If you already have API keys for OpenAI, Anthropic, Google, etc., you can use them in OmniRoute. Just paste them when connecting the provider.


What's Next?