Home › Compare › APIcuts vs Not Diamond
CompareAPIcuts vs Not Diamond
Not Diamond is a model router: it predicts which model to use for each prompt, aiming for accuracy at the lowest cost. It isn't a gateway; it works alongside your existing gateway, and its pay-as-you-go plan costs $0.05 per million tokens routed. apicuts includes model routing, plus caching, batching, prompt work and output limits, with at least 20% guaranteed after our fee.
Choose Not Diamond if per-prompt model choice is the lever you want to tune yourself. Choose apicuts for a guaranteed saving across every lever, done for you.
At a glance
| apicuts | Not Diamond | |
|---|---|---|
| What it is | Done-for-you LLM API gateway with cost optimization | Model router that picks a model for each prompt |
| Price | 10% of verified savings. No retainer | $0.05 per million tokens routed on pay-as-you-go, through a waitlist; enterprise volume discounts |
| Savings guarantee | At least 20% lower all-in cost after our fee, or you pay nothing | None listed on its pricing page |
| Levers | Caching, batching, routing, model routing, and prompt and output work | Model selection |
| Where it runs | As your gateway | Alongside your existing gateway |
| Best for | Teams that want a lower bill without doing the work | Teams running coding agents that want per-prompt model choice |
When Not Diamond is the better fit
- Model choice is the one lever you want to optimize.
- You already run a gateway you're happy with.
- Your workload is mostly coding agents.
When apicuts is the better fit
- You want every lever used, not just model choice.
- You want the work done for you, with your quality checks.
- You want a written guarantee, measured after fees.
Can you use both?
They work at different layers: Not Diamond picks the model, and a gateway carries the request. If you already use it, tell us on your teardown call.
Frequently asked questions
How is Not Diamond priced?
According to its pricing page, pay-as-you-go costs $0.05 per million tokens routed, through a waitlist, with volume discounts for enterprise.
Is apicuts a Not Diamond alternative?
Yes, if you want more than model routing. apicuts uses model routing alongside caching, batching and prompt work, and guarantees at least 20% lower all-in cost after our fee.
Does apicuts switch models automatically?
Only with your approval. Lower-cost models are used only for requests where they pass your evaluations, after a small canary rollout.
Not Diamond details checked on October 30, 2026 from its own website. Prices change, so check their site for current terms.
Want us to find your 20%?
Book a free 15-minute API cost teardown. Bring last month's provider usage and we'll show you your biggest waste and the first fix we'd ship.
Get a Free 15-Minute API Cost Teardown