About LLM Latency Tracker
LLM Latency Tracker measures latency and uptime for AI inference APIs across regions, for developers comparing provider responsiveness. It publishes open data and historical statistics, while separating network time to first byte from inference time to first token.
Key features
- 01Regional latency and uptime measurements
- 02TTFB and TTFT probes
- 03Daily rankings and historical snapshots
- 04Regional p50 and p95 statistics
- 05Model deprecation calendar
Use cases
- 01Compare API response speeds by region
- 02Review historical provider latency
- 03Monitor API availability
- 04Check model shutdown schedules
MCP support
It provides an MCP endpoint and a local stdio MCP server backed by the public API. Read-only tools query provider rankings, latency across regions, model deprecations, and coding agent health.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://llmlatency.dev/mcpclaude mcp add --transport http dev-llmlatency-llm-latency-tracker https://llmlatency.dev/mcp{"mcpServers":{"dev-llmlatency-llm-latency-tracker":{"type":"http","url":"https://llmlatency.dev/mcp"}}}Open in Cursor{"servers":{"dev-llmlatency-llm-latency-tracker":{"type":"http","url":"https://llmlatency.dev/mcp"}}}Open in VS Code{"mcpServers":{"dev-llmlatency-llm-latency-tracker":{"type":"http","url":"https://llmlatency.dev/mcp"}}}{"mcpServers":{"dev-llmlatency-llm-latency-tracker":{"serverUrl":"https://llmlatency.dev/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
2| Parameter | Type | Required | Description |
|---|---|---|---|
| region | string | No | eu-hetzner, us-central, ap-tokyo or sa-east; omit for all |
Details
From the project README📊 LLM Latency Tracker
Measure AI API latency and uptime across regions, and publish the results as open data.
🌐 Live rankings · JSON API · MCP endpoint
⚡ What it does
- 🌍 Regional measurements — compare provider response times and availability from distributed probe nodes.
- ⏱️ Two probe types — network time to first byte (TTFB) and optional inference time to first token (TTFT).
- 📈 Open dataset — daily rankings, historical snapshots and regional p50 / p95 statistics.
- 🤖 Agent access — JSON API, MCP, Markdown pages and an
llms.txtindex. - 🗓️ Model lifecycle — a deprecation calendar with links to provider announcements.
🔧 Built for measurement
- Python standard-library core for edge probes; provider keys are needed for inference probes.
- SQLite storage and regional aggregation, with remote nodes shipping measurements to a central node.
- Static publishing for the website and JSON datasets.
- CI checks for tests and linting; published snapshots include their measurement date.
Reading the results: edge TTFB measures network/API responsiveness, not model generation speed. Compare it separately from inference TTFT; results depend on region, probe type and time window.
🚀 Quick start
Use the public data without installing anything:
curl https://llmlatency.dev/api/rankings.json
Or run edge probes locally with Python 3.12+:
git clone https://github.com/mazamaka/llm-latency-tracker.git
cd llm-latency-tracker
REGION=local python3 run.py
python3 aggregate.py --region local
For a local stdio MCP server over the published API (stdlib only, no keys):
python3 mcp_server.py
Tools: get_ai_api_latency (provider leaderboard per region), get_provider_latency (one provider across regions), get_model_deprecations (model shutdown calendar), get_coding_agent_health (Claude Code / Codex speed and accuracy drift). All read-only.
Inference probes, API access & site generation → · Deployment →
🧪 Contributing
Add a provider, bring a new probe region, or improve the measurement code. See CONTRIBUTING.md for setup and checks.
Python · SQLite · JSON API · MCP · Cloudflare Pages
Code: MIT · Data: CC-BY-4.0, with attribution to llmlatency.dev.
📈 Latest daily snapshot
Daily snapshot — 2026-10-27
Measured latency across 46 AI inference providers in 4 regions. Method: distributed edge (DNS→TCP→TLS→TTFB) + inference (TTFT) probes, last 24h. License: CC-BY-4.0.
| Region | Fastest provider (p50) | p50 | p95 | Uptime |
|---|---|---|---|---|
| Asia (Tokyo) | fireworks | 23 ms | 73 ms | 100% |
| Europe (Germany) | fireworks | 98 ms | 201 ms | 100% |
| South America (São Paulo) | openrouter | 61 ms | 92 ms | 100% |
| US (Central) | fireworks | 32 ms | 83 ms | 100% |
- Full dataset:
data/rankings/2026-10-27.json(latest) - Citable archive (DOI):
10.5281/zenodo.23388429— daily aggregates, CC-BY-4.0 - Hugging Face dataset: https://huggingface.co/datasets/llmlatency/llm-latency-tracker
- Kaggle dataset: https://www.kaggle.com/datasets/llmlatency/llm-latency-tracker
- Archived in Software Heritage:
swh:1:snp:2778cbabd72a70a629ee35fbd5ac536d1ccb7a9a - Python client: https://pypi.org/project/llmlatency/
- Live rankings and methodology: https://llmlatency.dev
- Machine-readable API: https://llmlatency.dev/api/rankings.json
- Model deprecation calendar: https://llmlatency.dev/deprecations
Snapshot generated 2026-10-27T07:24:20Z — this table is regenerated daily.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.