One prompt.
The best model for the job.
Aridel classifies every prompt and sends it to the right frontier model — Claude, GPT, Gemini, Kimi, DeepSeek, and more. Pay pennies for the easy stuff. Reach for the smartest model only when you actually need it.
Smart routing
An embedding-based classifier reads each prompt and picks the model with the best price/quality fit. Easy questions go to cheap, fast models. Hard ones get the heavyweights.
40+ frontier models
GPT-5 family, Claude 4.x (Sonnet, Opus, Haiku), Gemini 2.5 & 3, Kimi K2, DeepSeek, Qwen, Amazon Nova — all behind a single streaming chat UI.
Stop overpaying
Most prompts don't need a top-tier model. Routing trims the bill on the long tail of easy queries — without you having to think about which model to pick.
How it works
Three steps, no model picking, no per-provider accounts.
You write a prompt
Same flow as ChatGPT or Claude — one box, one stream. Attach files, toggle web search, keep your conversation history.
Route AI classifies it
A lightweight classifier embeds the prompt, estimates difficulty and domain, then selects the model that gives you the best answer per dollar.
Streamed answer, every time
The chosen model streams back token-by-token. We log which model was picked and why, so you can audit the routing decision later in Insights.
Pricing
Start free. Bring your own keys if you want, subscribe if open-source is mostly enough for your use case.
Free
$0 / month
Pay-as-you-go wallet. Top up only what you use.
- Access to all proprietary + OSS models
- Smart routing across every model
- Bring-your-own-key (BYOK) supported
- Insights dashboard
OSS Unlimited
$10 / month
Unlimited-ish open-source models with a fair-use cap.
- Open-source models routed without metering
- Proprietary models still billed via wallet
- Cancel anytime via customer portal
- Best value if your work is > 70% OSS-friendly