GitHub · Python
Moloch-AI/llm-api-benchmark
Open-source LLM API benchmark for measuring inference latency, TTFT, tokens/sec, throughput, reliability and cost across OpenAI-compatible endpoints.
- Stars
- 17
- Forks
- 0
- Stars gained in 24 hours
- 0
- Forks gained in 24 hours
- 0
Topics: benchmarking, developer-tools, inference, latency, llm, llm-api, llm-benchmark, molochai, openai-compatible, performance-testing
Latest data point: Nov 21, 2026 · 17 stars · 0 forks