Tag: self-hosting

A JavaScript Cost Calculator for Choosing Between $0.10/M APIs and Self-Hosted Models

pr0h0•November 13, 2026

Build a JavaScript cost calculator that models per-token API pricing against self-hosted open-weight inference, including GPU, utilization, and ops overhead, to decide when $0.10/M APIs beat owning the stack.

javascriptaillm

Reflection Beam Throughput and VRAM: What 501B MoE Inference Costs Per Token

pr0h0•October 6, 2026

A practical look at what Reflection AI's 501B-parameter Beam MoE, with only 23B active parameters per token, actually costs in VRAM, throughput, and dollars per token when self-hosted for agentic coding workloads.

mixture-of-expertsllm-inferencevram