All plans are metered in ECU (Euriklis Computation Units) — a single unit that normalises compute cost across tensor ops, graph algorithms, and econometric models. The Free tier runs on the Euriklis TypeScript library stack. Pro compiles to native CPU via LLVM IR. Custom unlocks GPU execution via PTX, AMD, and SPIR-V.
Full access to the Euriklis TypeScript library stack, no credit card required.
More ECU for data scientists and researchers who need extended computation without LLVM compilation.
We are currently rolling out our API and MCP tools. Paid plans will be available very soon — register for free to get early access.
The same operations compiled to native machine code via LLVM IR for maximum CPU throughput.
We are currently rolling out our API and MCP tools. Paid plans will be available very soon — register for free to get early access.
GPU-accelerated execution for large-scale workloads — PTX, AMD, and SPIR-V targets.
An Euriklis Computation Unit (ECU) is a normalised measure of compute work. A simple vector addition costs a few ECU; a large matrix multiply or a PageRank run on a dense graph costs orders of magnitude more. ECU lets you reason about quota in one number regardless of which operation or library you call.
Free runs your operations through the Euriklis TypeScript library stack — high-performance implementations in TypeScript on CPU. Pro compiles the same operations to native machine code via LLVM IR (x86_64 and ARM64), delivering higher throughput for compute-intensive workloads. Custom adds GPU execution: NVIDIA via PTX (LLVM IR → NVVM IR → PTX), AMD via ROCm/HIP, and cross-platform GPU via SPIR-V. The API surface and result semantics are identical across all three tiers.
Yes. The Euriklis TypeScript libraries (@euriklis/mathematics, @euriklis/ds-architect, @euriklis/econometrics) are open source. Paid tiers cover the hosted execution infrastructure, LLVM compilation pipeline, GPU capacity, and workspace tooling.
Custom plans are negotiated annually and include dedicated GPU capacity, a production SLA, and volume pricing. Contact us to discuss your workload requirements.