Not Diamond

Reading on routing

• The gateway is the productThe interesting engineering is not calling a model. It is deciding which model, failing over safely, and staying inside a budget while you do it.
• Build a cost model before you optimiseTeams optimise the thing they can see in the dashboard. The dashboard shows tokens. The number that matters is cost per successful outcome, and nobody is measuring it.
• Choosing a model is a routing problemThere is no best model. There is a best model for a task, at a quality bar, within a latency and cost budget — and that decision is a routing policy, not a benchmark.

• MartianModel router that optimizes for quality, cost and latency.
• RouteLLMLearned router that cuts cost by matching difficulty to model size.

Listed as an alternative to

• MartianMartianModel router that optimizes for quality, cost and latency.Use when Routing tuned on your own traffic rather than a public benchmark.Skip when You want the routing rule to be plain config you can read.proprietary · saas · usage-based
• RouteLLMRouteLLMLearned router that cuts cost by matching difficulty to model size.Use when Cutting cost by matching query difficulty to model size, with a learned router.Skip when You cannot evaluate the quality you would be trading away.Apache-2.0 · self-hosted · free

Also in routing

• LiteLLMLiteLLMOpenAI-format proxy translating across 100+ model providers.Use when The widest provider coverage, deployed the least committal way.Skip when You want routing policy to live in a SaaS console.MIT · self-hosted · free
• PortkeyPortkeyAI gateway with routing, caching and guardrails in one layer.Use when A managed gateway with guardrails and analytics already bundled.Skip when Prompts cannot leave your infrastructure.proprietary · saas · usage-based
• Cloudflare AI GatewayCloudflare AI GatewayEdge gateway adding caching, retries and rate limiting.Use when Edge caching and latency dominate, on Cloudflare already.Skip when Requests must not transit a third party's network.proprietary · saas · free-tier
• OpenRouterOpenRouterSingle API key and billing across many hosted models.Use when One key and one bill across many hosted models, while experimenting.Skip when You need self-hosting or per-provider SLAs.proprietary · saas · usage-based
• MartianMartianModel router that optimizes for quality, cost and latency.Use when Routing tuned on your own traffic rather than a public benchmark.Skip when You want the routing rule to be plain config you can read.proprietary · saas · usage-based
• Envoy AI GatewayEnvoy AI GatewayCNCF-track gateway for LLM traffic on an Envoy data plane.Use when A Kubernetes shop that already runs Envoy and needs the gateway in-cluster.Skip when You want a gateway configurable without a data plane.Apache-2.0 · self-hosted · free
• BifrostBifrostHigh-throughput LLM gateway with drop-in OpenAI compatibility.Use when A high-throughput OpenAI-compatible proxy with a small footprint.Skip when You need the breadth of a full routing stack.proprietary · self-hosted · free
• RouteLLMRouteLLMLearned router that cuts cost by matching difficulty to model size.Use when Cutting cost by matching query difficulty to model size, with a learned router.Skip when You cannot evaluate the quality you would be trading away.Apache-2.0 · self-hosted · free
• TrueFoundryTrueFoundryGateway plus observability and guardrails as one deployment.Use when Gateway, observability and guardrails as one managed deployment.Skip when You want to adopt the pieces independently.proprietary · managed · subscription