# llmping
> OpenAI, Claude, Gemini, and OpenRouter API error diagnosis for developers.

Website: https://llmping.app

## Core Diagnosis Pages
- https://llmping.app/ - interactive diagnosis and cURL generator
- https://llmping.app/errors/openai/429/ - OpenAI API error 429 rate limit
- https://llmping.app/errors/anthropic/529/ - Anthropic API 529 overloaded
- https://llmping.app/errors/openai/401/ - OpenAI API 401 invalid key
- https://llmping.app/errors/openai/403/ - OpenAI API 403 forbidden
- https://llmping.app/errors/gemini/fetch-failed/ - Gemini API fetch failed
- https://llmping.app/errors/claude/econnreset/ - Claude API ECONNRESET
- https://llmping.app/errors/openrouter/402/ - OpenRouter insufficient credits

## Provider Status Symptom Pages
- https://llmping.app/status/openai/ - Is OpenAI API down
- https://llmping.app/status/anthropic/ - Is Claude API down
- https://llmping.app/status/gemini/ - Is Gemini API down

## Badge
- https://llmping.app/badge/ - embeddable README badges
- https://llmping.app/badge/ok.svg - static OK badge
- https://llmping.app/badge/degraded.svg - static degraded badge

## Latency Benchmark Archive
Dataset: LLM API Latency Benchmark - May 2026
Temporal coverage: 2026-05-01/2026-05-12
- https://llmping.app/leaderboard/ - SSR HTML latency table
- https://llmping.app/leaderboard.md - Markdown latency table
- https://llmping.app/data/latency-benchmark.json - JSON benchmark download
- https://llmping.app/llms-full.txt - Full site markdown corpus

## Region Pages
- https://llmping.app/regions/us-east/ - US East LLM API latency
- https://llmping.app/regions/us-west/ - US West LLM API latency
- https://llmping.app/regions/europe/ - Europe LLM API latency
- https://llmping.app/regions/asia-pacific/ - Asia Pacific LLM API latency
- https://llmping.app/regions/singapore/ - Singapore LLM API latency
- https://llmping.app/regions/japan/ - Japan LLM API latency

## Technical Guides
- https://llmping.app/blog/what-is-time-to-first-token/ - What Is Time to First Token?
- https://llmping.app/blog/p50-vs-p95-vs-p99-latency/ - P50 vs P95 vs P99 Latency for LLM APIs
- https://llmping.app/blog/why-llm-latency-varies-by-region/ - Why LLM API Latency Varies by Region
- https://llmping.app/blog/streaming-vs-batch-llm-api/ - Streaming vs Batch LLM API Latency
- https://llmping.app/blog/measuring-llm-latency-correctly/ - How to Measure LLM Latency Correctly
- https://llmping.app/blog/openai-vs-anthropic-vs-google-latency-comparison/ - OpenAI vs Anthropic vs Google LLM Latency Comparison