APIMaster
Instantly check if your Claude, GPT, or DeepSeek API proxy is serving the real model. Free AI model authenticity detection — no API key stored, results in 60 seconds.
Source: APIMasterhttps://apimaster.ai
57
Total Detections
93.0%
Pass Rate
11.69s
Avg Latency
19.44s
P95 Latency
APIMaster independently tests whether APIMaster delivers the model you specify — checking for model substitution, pass rates, and latency. Our 30-day detection data shows real-world performance across: claude-sonnet-4-6, gpt-5.4, claude-opus-4-7, deepseek-v4-flash, deepseek-v4-pro, gpt-5.5, claude-opus-4-8, claude-haiku-4-5, gemini-3.1-pro-preview.
AI models may exhibit hallucination and drift. Detection results are not 100% accurate — please rely on multiple detection results for a reliable assessment.
Results by Model
Run Detection →| Model | Detections | Pass Rate | Avg Latency |
|---|---|---|---|
| claude-sonnet-4-6 | 28 | 96.4% | 9.55s |
| gpt-5.4 | 12 | 100.0% | 12.55s |
| claude-opus-4-7 | 8 | 75.0% | 18.19s |
| deepseek-v4-flash | 4 | 100.0% | 9.90s |
| deepseek-v4-pro | 2 | 100.0% | 23.23s |
| gpt-5.5 | 1 | 0.0% | — |
| claude-opus-4-8 | 1 | 100.0% | 10.15s |
| claude-haiku-4-5 | 1 | 100.0% | 5.93s |
| gemini-3.1-pro-preview | 0 | 0.0% | — |