AIHubMix

A unified API gateway providing access to multiple large language models and AI services through a single interface.

Categories

AIHubMix offers 232 LLM API models.

Speed benchmark average: 66 tok/s.

AIHubMix is an API aggregator, offering models from multiple vendors.

Avg Speed66.47 tok/s

Latency13.29 s

Total Tests75

Models14

Updated4/18/2026

Created At12/7/2025

Versionv1.0.0

Online SinceApr 17, 2026, 05:44 PM

GitHub

Recent Test Records

Time	Model	Speed	Latency
Apr 10, 08:22 AM	coding-glm-5.1	32.33 tok/s	41.57s
Apr 3, 07:30 AM	coding-glm-4.7-free	27.71 tok/s	50.72s
Mar 31, 11:33 AM	deepseek-v3.2	27.93 tok/s	1.52s
Feb 21, 02:31 PM	gemini-3.1-pro-preview	69.84 tok/s	25.06s
Feb 1, 09:47 AM	alicloud-qwen3-max-2026-01-23	40.59 tok/s	1.26s
Feb 1, 09:41 AM	zai-glm-4.7	47.80 tok/s	41.22s
Feb 1, 09:40 AM	sophnet-mimo-v2-flash	104.20 tok/s	1.22s
Feb 1, 09:36 AM	doubao-seed-1-8-251228	46.32 tok/s	23.71s
Jan 30, 04:31 AM	grok-4-1-fast-non-reasoning	108.12 tok/s	1.01s
Jan 30, 04:28 AM	gemini-3-flash-preview	155.47 tok/s	7.06s