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

Supported Models

Model	Speed	Latency	Tests
ministral-3:3b	207.68 tok/s	2.84s	5
kimi-k2-thinking	131.31 tok/s	4.75s	5
rnj-1:8b	81.46 tok/s	2.45s	5
xbt-t	78.05 tok/s	14.65s	5
claude-sonnet-4-6	62.04 tok/s	5.36s	10
claude-opus-4-6	50.36 tok/s	4.97s	5
qwen3.6p	47.84 tok/s	26.66s	35
qwen3.6-plus	43.17 tok/s	26.98s	35
kimi-k2:1t	40.30 tok/s	2.61s	5
GLM-4-Flash-250414	39.37 tok/s	0.86s	10
xbt-c	34.33 tok/s	26.04s	5
xbt-s	32.51 tok/s	42.36s	5
zhipu/glm-4-flash	31.45 tok/s	1.81s	5
glm-5	29.62 tok/s	47.00s	5
mistral-large-3:675b	29.28 tok/s	3.00s	5