LiteLLM vs Not Diamond
Both are llm gateways tools. Here is how they actually differ on price, billing model and deployment.
LiteLLM
The most widely adopted open-source LLM gateway, MIT licensed with 100+ provider integrations and zero markup on your tokens. The catch is that you operate it, and published enterprise pricing is wildly inconsistent.
Not Diamond
A model router that recommends rather than proxies - it tells your gateway which model to call and gets out of the way. That architecture means no request-path dependency, which nothing else in this category offers.
| LiteLLM | Not Diamond | |
|---|---|---|
| Category | LLM Gateways | LLM Gateways |
| Our rating | 5/5 | 4/5 |
| Starting price | $0 self-hosted | Conflicting reports |
| Billing meter | No usage metering | No usage metering |
| Free plan | Yes | Yes |
| Free self-hosting | Yes, free | No or paid tier only |
| Best for | Teams with engineering capacity that want provider-agnostic routing with no per-token markup, particularly at volumes where a percentage fee on a managed gateway becomes significant. | Teams already running a gateway who want smarter per-request model selection without putting another vendor in the request path, particularly for coding agents where model spend is high and uncontrolled. |
Our verdict on LiteLLM
LiteLLM is the default open-source LLM gateway and deserves to be. It is MIT licensed, fronts 100+ providers behind an OpenAI-compatible endpoint, and takes no markup on your tokens - which is the decisive difference at any real volume, because managed alternatives charge a percentage of everything you spend forever. Adopting it is largely a base URL change, and so is leaving, which is an unusually honest position for infrastructure to be in. The cost is operational rather than financial. You run the proxy, the database, the monitoring and the upgrades, which realistically means a few hundred dollars a month of infrastructure and a person who owns it. Releases are frequent enough that pinning to stable versions is advisable. The one genuinely unsatisfying part is enterprise pricing, where third-party sources disagree so wildly - from $250 a month to around $30,000 a year - that none of them can be trusted, and enterprise SSO being free only up to five users means identity management turns into a commercial conversation sooner than you might expect.
Full LiteLLM review →Our verdict on Not Diamond
Not Diamond is architecturally the most interesting thing in this category because it declines to be a gateway. Integrations are stack-agnostic through its API, and recommendations are executed in your own model gateway and harness - so it tells you which model to call and gets out of the way. Every other router in this category is a proxy, which means adopting it creates a request-path dependency and a new availability risk. Not Diamond has neither. It composes with LiteLLM, Vercel, Cloudflare or your own proxy rather than replacing any of them, which makes it unusually low-commitment to try. The product is a pre-trained Chat router, a Code router aimed at coding-agent cost currently in early access, and custom routers trained on your own data. That last one matters most, because the weakness of generic routing is that your workload is not the benchmark it was tuned on. The unsatisfying part is pricing, where sources directly contradict each other, and the fact that the most differentiated capability is still early access.
Full Not Diamond review →Frequently Asked Questions
What is the main difference between LiteLLM and Not Diamond?
LiteLLM: Teams with engineering capacity that want provider-agnostic routing with no per-token markup, particularly at volumes where a percentage fee on a managed gateway becomes significant. Not Diamond: Teams already running a gateway who want smarter per-request model selection without putting another vendor in the request path, particularly for coding agents where model spend is high and uncontrolled. Both sit in LLM Gateways, so the decision usually comes down to billing model and deployment rather than raw capability.
Which is cheaper, LiteLLM or Not Diamond?
It depends entirely on your workload shape, because they meter differently - LiteLLM bills on no usage metering and Not Diamond bills on no usage metering. Published starting prices are $0 self-hosted and Conflicting reports respectively, but those numbers are not comparable until you apply them to the same traffic. Use our cost calculator to model both against your own request volume and span count.
Can I self-host LiteLLM or Not Diamond?
LiteLLM: Yes, free. Not Diamond: No or paid tier only. Free self-hosting means no licence fee, not no cost - you still own the infrastructure, upgrades and on-call.