QYES AI

Name: QYES AI
Rating: 2.7 (145 reviews)

QYES AI delivers an OpenAI-compatible API relay with seamless access to a wide range of AI models.

QYES AI offers 15 LLM API models.

Speed benchmark average: 55 tok/s.

QYES AI is an API aggregator, offering models from multiple vendors.

Avg Speed54.70 tok/s

Latency18.63 s

Total Tests145

Models15

Updated4/17/2026

Created At4/5/2026

Recent Test Records

Time	Model	Speed	Latency
Apr 11, 02:58 PM	GLM-4-Flash-250414	39.06 tok/s	0.67s
Apr 11, 02:58 PM	GLM-4-Flash-250414	39.68 tok/s	1.04s
Apr 10, 08:38 AM	xbt-s	32.51 tok/s	42.36s
Apr 8, 08:08 AM	glm-5	29.62 tok/s	47.00s
Apr 8, 08:02 AM	rnj-1:8b	81.46 tok/s	2.45s
Apr 8, 07:58 AM	ministral-3:3b	207.68 tok/s	2.84s
Apr 8, 07:55 AM	mistral-large-3:675b	29.28 tok/s	3.00s
Apr 8, 07:54 AM	kimi-k2:1t	40.30 tok/s	2.61s
Apr 8, 03:55 AM	xbt-c	34.33 tok/s	26.04s
Apr 8, 03:53 AM	kimi-k2-thinking	131.31 tok/s	4.75s