WITAN

Agent API observatory

by WITAN · platform-standard · created 2026-09-29
latencyobservatoryagentsfreshness
Get the data
Records
1,242
Latest version
v27
Fields
7
Access
free · public
Updated
updated 5h ago

AI summary — as of v27

This dataset contains 1,242 latency measurements from a single AWS vantage point in Seoul, tracking real-world HTTPS response times to 10 model APIs (Anthropic, OpenAI, Google, Mistral, Groq, and others), infrastructure registries (GitHub, Hugging Face, npm, PyPI, Docker Hub), blockchain RPCs, and status pages. Measurements are taken twice every 6 hours with a 15-second timeout, recording latency in milliseconds, HTTP status codes, and reachability—with the most recent data being most relevant since latency patterns shift over time. The dataset is deliberately small-response and production-oriented, measuring what's actually reachable rather than synthetic performance, though absolute latency values reflect Seoul as the measurement origin.

README

Continuously measured, real-world latency of the endpoints AI agents actually depend on, from a stated vantage point. Targets: model APIs (Anthropic, OpenAI, Google Gemini, Mistral, Groq, Together, Cohere, xAI, DeepSeek, OpenRouter), the registries and hubs agents install from (GitHub API, Hugging Face, npm, PyPI, the MCP registry, Docker Hub), the chains and the payment facilitator they pay through (Base Sepolia and …

Show more

Base mainnet RPC, the x402 facilitator), the OpenAI and Anthropic status pages, and two baselines (Google generate_204, Cloudflare trace) that show how the vantage itself is doing. Each record is one real HTTPS round-trip: latency in milliseconds, HTTP status, ok (any answer below 500 — an unauthenticated model API answering 401 or 403 is reachable, which is what is measured), the time and the vantage. Never synthetic, never estimated. Two rounds per run every 6 hours. Freshness is the product: latency data decays, so recent windows matter most. Method: fetch with a 15 s timeout, TLS included, the response read to the end, small responses chosen on purpose. Vantage: one shared AWS EC2 host in Seoul (ap-northeast-2) (each row names it in vantage), so absolute values carry that bias; deltas, the gap to the baselines and availability flips are the durable signal.

Report this dataset

We read every report (terms, section 3); your address is used to answer it and for nothing else (privacy).