# LLM Latency Tracker

> LLM Latency Tracker, an MCP server by llmlatency.dev, listed from the official MCP registry. Indexed, not reviewed: facts and our own checks, no score or ranking. Measured latency, time to first token and uptime for ~45 AI inference APIs, by region.

- Canonical: https://www.anchorterminal.com/tools/llmlatency-llm-latency-tracker
- Markdown: https://www.anchorterminal.com/tools/llmlatency-llm-latency-tracker.md (~650 tokens)
- Slim: https://www.anchorterminal.com/tools/llmlatency-llm-latency-tracker.min.md (~580 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/tools/llmlatency-llm-latency-tracker.json (this page as data, same URL with Accept: application/json)
- Site index for agents: https://www.anchorterminal.com/llms.txt (full text: https://www.anchorterminal.com/llms-full.txt)
- API: https://www.anchorterminal.com/api/v1/index.json
- Updated: 2026-10-05

# LLM Latency Tracker

> Indexed, not reviewed: facts from the official MCP registry and our own checks. No score, grade or rank, and not in the rankings until the panel reviews it. How the index works: https://www.anchorterminal.com/indexed/

- Kind: MCP server, by llmlatency.dev (https://llmlatency.dev)
- Category: Observability & incidents (https://www.anchorterminal.com/categories/observability.md)
- Listed because: It's published in the registry under llmlatency.dev, a namespace the registry only gives to whoever proves they control that domain.
- What the official MCP registry says: Measured latency, time to first token and uptime for ~45 AI inference APIs, by region.

## Facts

- MCP registry: `dev.llmlatency/llm-latency-tracker` 1.1.0
- Endpoint: https://llmlatency.dev/mcp (streamable HTTP)
- Source: https://github.com/mazamaka/llm-latency-tracker
- Website: https://llmlatency.dev
- GitHub stars: 2
- Registry entry updated: 2026-08-16

## Tools

- Tools it lists (2, about 188 tokens of context, `tools/list` without credentials, checked 2026-10-04 22:24 UTC):
  - `get_ai_api_latency`: Measured latency (TTFB p50/p95) and uptime rankings of AI inference API providers by region, from llmlatency.dev.
  - `get_model_deprecations`: AI model deprecation calendar: announced and shutdown dates, replacement models, and how many days of migration notice each provider actually gives…
- How its tools read to an agent (0 errors, 2 warnings, 1 note, about 188 tokens; rules at https://www.anchorterminal.com/check.md; not part of the score):
  - warn TC16 get_ai_api_latency: no readOnlyHint or destructiveHint
  - warn TC16 get_model_deprecations: no readOnlyHint or destructiveHint
  - note TC24 server: 2 of 2 tools have no outputSchema

- JSON: https://www.anchorterminal.com/api/v1/tools/llmlatency-llm-latency-tracker.json
- Being indexed says nothing about quality, and nobody can pay for it. Ask for a review: https://www.anchorterminal.com/builders/#claiming