Connect your agent.Buy every AI model.
set up https://opencheap.si/SKILL.mdand let it take it from there.
Anthropic$10.00Routed to Provider C
- Your cost
- $2.00
- Price
- $4.00
Example prices per 1M output tokens.
880+ models from every major lab. One API key.
- Anthropic
OpenAI
Google
Meta
DeepSeek
Mistral
Qwen
xAI
Moonshot
Up to 99% below list on popular models.
Liveupdated 2026-10-17 17:00 UTC
| Model | List price | Our price | Below list |
|---|---|---|---|
| claude-sonnet-5 | $10.00 | $0.550 | −94% |
| claude-opus-5.5 | $20.00 | $9.30 | −53% |
| gpt-5.5 | $30.00 | $3.40 | −88% |
| gemini-3.5-flash | $9.00 | $0.140 | −98% |
| kimi-k3 | $11.94 | $1.20 | −89% |
| gpt-oss-120b | $0.600 | $0.004 | −99% |
| glm-5.3-flash | $0.500 | $0.130 | −74% |
| llama-3.3-70b | $0.320 | $0.049 | −84% |
| grok-4.7 | $6.00 | $3.50 | −41% |
| glm-4.7-flash | $0.400 | $0.003 | −99% |
Our price per 1M output tokens, next to OpenRouter's list price. See all 885 prices
Monitor, control and save.
Monitor
The dashboard and the logs: every request with its model, how long it took and its status. Filter them and export them.
Control
Gateway rules and key limits: fall back to another model, retry on errors, allow only the models you name, cap what a key spends in a month.
Save
Each request goes to the cheapest healthy source for its model, and you pay our price for it, shown next to the public list price.
Guardrails (prompt injection, personal data, allowed topics): starting soon.
FAQ
Questions, answered.
How are your prices set?
Every request is routed to the cheapest healthy source for that model, across several providers. Popular models usually cost less than OpenRouter's list price; the ones that cost more are marked "above list" on the Models page. Prices can change at any time, and the Models page shows OpenRouter's list price next to ours, so you can compare.
Is it really the same model?
Yes. A model id always means that model and version, never a renamed substitute. Like any API, answers can vary from one run to the next, even at temperature 0.
Who sees my prompts?
The provider that serves the request processes it under its own terms, and so does any provider it passes the request on to; we store metadata only (model, tokens, latency, cost), never prompt or completion bodies.
Any fees?
No monthly fee and no plan: pay as you go from one balance, by card or in USDC. Credits never expire and cannot be withdrawn. Reselling is free: you pay wholesale, nothing else.
Can I pay with crypto?
Yes: USDC on Base, from any wallet or straight from an agent. Cards work too, through Stripe.
Buy at our price. Sell at yours.
The same models on your own domain, at the prices you set, under your brand. Your clients never see us.