素墨API

A non-profit AI infrastructure offering free access to integrated large language models with privacy-focused, no-logging policies.

素墨API offers 788 LLM API models.

API pricing per token ranges from $0.010 to $0.100/M (input).

Speed benchmark average: 358 tok/s.

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

Avg Speed357.92 tok/s

Latency6.95 s

Total Tests196

Models31

Updated4/17/2026

Created At2/8/2026

Recent Test Records

Time	Model	Speed	Latency
Apr 9, 06:56 AM	cb/glm-5.1	41.30 tok/s	7.76s
Apr 5, 05:53 AM	cb/auto	46.59 tok/s	23.98s
Apr 5, 05:52 AM	[按量]anti/claude-opus-4-6	46.66 tok/s	2.34s
Apr 5, 05:47 AM	[按量]anti/claude-sonnet-4-6	49.13 tok/s	8.19s
Mar 22, 07:51 AM	openai/gpt-oss-20b	277.46 tok/s	1.11s
Mar 22, 07:36 AM	openai/gpt-oss-20b	257.86 tok/s	0.96s
Mar 22, 06:48 AM	abacusai/dracarys-llama-3.1-70b-instruct	16.23 tok/s	0.78s
Mar 22, 06:30 AM	deepseek-v3.2	15.61 tok/s	7.14s
Feb 28, 04:36 AM	echo	1008.34 tok/s	0.67s
Feb 28, 04:35 AM	echo	646.25 tok/s	0.77s