enterpilot

Author

Jakub A. Wąsek

Founder of enterpilot, Inc. and creator and primary maintainer of GoModel.

LinkedIn profile

Articles by Jakub A. Wąsek

  • AI costs
  • Claude Code

Cutting Claude Code Token Consumption by 10-30%

I proxied Claude Code and read every request I was paying for. Four fixes - CLAUDE.md, memory, untracked files, absolute paths - cut token usage 10-30%.

1 min read

  • AI costs
  • Model routing

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.

4 min read

  • Usage
  • Budgets

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.

5 min read

  • Benchmarking
  • AI control plane

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.

10 min read

  • Benchmarking
  • LiteLLM

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.

5 min read

  • Benchmarking
  • LiteLLM

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.

2 min read