A
admiralorbiter/llm-router-bench
Zero-dependency TTFT & SSE streaming latency benchmark for OpenAI, LiteLLM, vLLM, and Ollama gateways
View on GitHub ↗Link checked 2026-11-12 · HTTP 200 · opens the vendor's own site
- Star count
- 0 ★ · admiralorbiter/llm-router-bench · read from the GitHub search API · (checked 2026-11-13 20:00:50)
- Source
- read directly from its GitHub page · type: open-source project
- Harvest history
- first seen 2026-11-11 · last seen 2026-11-14 · seen 4× · listed by 2 sources
- Score
- score 203 · 2 sources · repo
FAQ (answers come from our records)
Who is it for?
We filed it under these tags: 开源项目. The tags come from the entry itself, not a taxonomy we imposed.
Who maintains it?
repository
admiralorbiter/llm-router-bench；first catalogued 2026-11-11；last seen 2026-11-14。There is no official certification or quality rating here — we record sources and dates only.# llm-router-bench
以下摘录自该仓库的 README（片段） · 在 GitHub 读完整 README →
Zero-dependency Python 3 CLI for measuring Time-To-First-Token (TTFT), multi-chunk SSE streaming jitter, A2A / MCP tool latency, and zero-cost ($0) model catalog availability across OpenAI-compatible inference routers (LiteLLM, vLLM, OpenRouter, One-API, Open WebUI, and Ollama).
## Quickstart
Need a test key? Provision an instant $25.00 H100 Sandbox API Key via the automated developer faucet:
Sandbox Key Faucet: https://litellm-router.thedarkforest.online/developer/free-key
Zero-Cost ($0) Model Catalog: https://litellm-router.thedarkforest.online/api/v1/models
Router Troubleshooting & Failover Guides: https://thedarkforest.online/guides
bash
export OPENAI_BASE_URL="https://litellm-router.thedarkforest.online/v1"
export OPENAI_API_KEY="sk-proj-..."
python llm_router_bench.py --model deepseek/deepseek-r1-0528:free --stream
## Optional GPU Router Wheel Index
For H100 / Blackwell CUDA routing extensions (vllm-flash-router), install via our PEP 503 wheel index in requirements-gpu.txt:
bash
pip install -r requirements-gpu.txt
## Features
Pure standard-library urllib.request + time.perf_counter_ns (zero pip dependencies required for core CLI).
Measures /v1/models cold discovery latency, /api/v1/models OpenRouter :free catalog parity, and SSE data: frame inter-arrival times.
Reference configurations in config/gateways.example.yaml and config/openrouter_free_catalog.json.
## Quickstart
Need a test key? Provision an instant $25.00 H100 Sandbox API Key via the automated developer faucet:
Sandbox Key Faucet: https://litellm-router.thedarkforest.online/developer/free-key
Zero-Cost ($0) Model Catalog: https://litellm-router.thedarkforest.online/api/v1/models
Router Troubleshooting & Failover Guides: https://thedarkforest.online/guides
bash
export OPENAI_BASE_URL="https://litellm-router.thedarkforest.online/v1"
export OPENAI_API_KEY="sk-proj-..."
python llm_router_bench.py --model deepseek/deepseek-r1-0528:free --stream
## Optional GPU Router Wheel Index
For H100 / Blackwell CUDA routing extensions (vllm-flash-router), install via our PEP 503 wheel index in requirements-gpu.txt:
bash
pip install -r requirements-gpu.txt
## Features
Pure standard-library urllib.request + time.perf_counter_ns (zero pip dependencies required for core CLI).
Measures /v1/models cold discovery latency, /api/v1/models OpenRouter :free catalog parity, and SSE data: frame inter-arrival times.
Reference configurations in config/gateways.example.yaml and config/openrouter_free_catalog.json.
Listed badge (optional)
Copy this line into the README if you want the listing mark. Optional, and it does not affect being listed.
[](https://anclum.com/en/s/admiralorbiter-llm-router-bench/)
- Source
- github · https://github.com/admiralorbiter/llm-router-bench
- Browse by field
- Open source
- Listed by
- 2 independent sources
- added
- today
Filed under
Every tag opens the full list for that filter. Counts are the live catalogue figures.