Kriora

Name: Kriora
Rating: 5.0 (100 reviews)

Provides OpenAI-compatible APIs and managed GPU instances for deploying and scaling open-source AI models.

Kriora offers 11 LLM API models.

Speed benchmark average: 213 tok/s.

Avg Speed564.99 tok/s

Latency3.17 s

Total Tests100

Models11

Updated4/11/2026

Created At3/9/2026

Recent Test Records

Time	Model	Speed	Latency
Apr 2, 11:03 PM	kimi-k2.5	1231.67 tok/s	1.29s
Mar 26, 11:07 AM	kimi-k2.5	995.39 tok/s	1.17s
Mar 26, 11:06 AM	glm-5	101.67 tok/s	8.79s
Mar 22, 01:41 AM	kimi-k2.5	1275.28 tok/s	1.13s
Mar 22, 01:40 AM	glm-4.7	112.93 tok/s	8.90s
Mar 22, 01:39 AM	minimax-m2.5	103.52 tok/s	8.67s
Mar 14, 06:34 PM	kimi-k2.5	1280.08 tok/s	1.14s
Mar 14, 06:33 PM	deepseek-v3-0324	345.85 tok/s	0.81s
Mar 11, 11:04 AM	deepseek-v3-0324	345.15 tok/s	0.85s
Mar 11, 10:31 AM	kimi-k2.5	1485.27 tok/s	1.31s