Want People to Use Cheaper AI Models? Make Expensive Models Slower
A simple way to reduce growing AI costs: add cost-proportional delay to expensive models at the AI gateway layer.
Author
Jakub A. Wąsek
Founder of enterpilot, Inc. and creator and primary maintainer of GoModel.
Articles by Jakub A. Wąsek
Your API Key Can't See Its Own Usage — So We Fixed That in GoModel
There is no standard usage API in the LLM world: OpenAI and Anthropic hide usage behind admin keys, and tools resort to scraping dashboards. Here's what our research found, and how GoModel's GET /v1/usage gives every caller their own usage, budget, and rate-limit status.
Benchmarking AI Gateways: GoModel vs LiteLLM vs Portkey vs Bifrost
A reproducible AI gateway benchmark comparing GoModel, LiteLLM, Portkey, and Bifrost on latency, throughput, memory, CPU, cold start, and image size.
GoModel, a LiteLLM alternative, is up to 14.5x faster
A March 23, 2026 localhost benchmark comparing GoModel and LiteLLM across chat completions and the Responses API.
GoModel vs LiteLLM Benchmark: Speed, Throughput, and Resource Usage
A benchmark by the GoModel team comparing latency, throughput, CPU, and memory against LiteLLM using the same workload.