Benchmark OpenAI, Claude, Gemini and AI API relay quality
AIBench.cc uses the same probes to test API latency, TTFT, model purity, prompt cache, rate limits and token cost. English pages target LLM API benchmark, OpenAI API check, Claude API check and AI API relay test searches.
Start a Real API Check
Paste a temporary test key and run the same probes for connectivity, latency, model purity, cache, rate limits and token cost.
AI API Check Pages
Dedicated landing pages for each search intent help Google and AI answer engines understand the site.
LLM API Benchmark
An LLM API benchmark compares real API behavior across models and providers with the same probes. AIBench.cc measures P95 latency, TTFT, prompt cache, model purity, rate limits and token cost so you can decide whether an AI API channel is ready for production.
OpenAI API Check
An OpenAI API check validates connectivity, response model fields, P95 latency, TTFT, cached_tokens, rate limit behavior and token usage to determine whether an OpenAI channel is usable, stable and free of relay anomalies.
Claude API Check
A Claude API check verifies Anthropic protocol behavior and reads cache_read_input_tokens, cache_creation_input_tokens, rate limit headers, model identity and TTFT to judge whether a Claude channel is stable and truly supports prompt cache.
API Latency Test
An API latency test should not only measure average time. AIBench separates end-to-end P50/P95/P99, streaming TTFT, chunk interval and rate-limit signals to show real product responsiveness and stability.
Model Purity Check
A model purity check determines whether the model id you requested is likely backed by the intended model. AIBench compares response model fields, self-reported identity, tokenizer count deviations and protocol behavior, then marks inconsistent evidence as suspicious or downgraded.
AI API Relay Test
An AI API relay test should cover connectivity, latency, model purity, cache fields, rate limits and billing. If a relay shows abnormal model identity, missing prompt cache evidence or high P95 latency, it may create quality and cost risk in production.
LLM API Guides and Comparisons
Practical guides to model purity, prompt caching, benchmark metrics and provider selection.
How to Detect Model Switching by an API Relay
Use response model fields, self-identification, tokenizer behavior, protocol evidence and repeated sampling to detect model switching or silent downgrades by an AI API relay.
How to Check Claude API Prompt Cache
Build a stable long prefix, compare cache_creation_input_tokens with cache_read_input_tokens, and diagnose missing Claude prompt cache evidence through API relays.
Which Metrics Matter in an LLM API Benchmark?
Compare P50/P95/P99, TTFT, success rate, 429 limits, throughput, prompt cache, model purity and actual token cost in an LLM API benchmark.
OpenAI API vs Claude API: Check Differences
Compare authentication, request formats, streaming, prompt cache, usage, rate-limit headers and model-purity checks for OpenAI API and Claude API.
Official API vs API Relay: Check Differences
Compare official LLM APIs and AI API relays across authentication, model origin, protocol forwarding, latency, prompt cache, rate limits, cost and accountability.