GLM BigModel Relay

A third-party API relay providing access to GLM/ChatGLM models through OpenAI-compatible endpoints.

Categories

GLM BigModel Relay offers 107 LLM API models.

API pricing per token ranges from $0.0020 to $0.500/M (input).

Speed benchmark average: 41 tok/s.

Avg Speed41.22 tok/s

Latency8.21 s

Total Tests11

Models2

Updated4/16/2026

Created At12/7/2025

Model Pricing

Pricing for 107 models (group: discount, updated: 4/17/2026)

Model	Input ($/M)	Output ($/M)	Model Ratio	Completion Ratio
glm-4v-flash	$0.0020	$0.0020	0.01	1
glm-z1-flash	$0.0020	$0.0020	0.01	1
glm-4-flash	$0.0020	$0.0020	0.01	1
qwen3-32b	$0.0099	$0.033	0.0495	3.3333333
gemini-2.5-flash-lite	$0.010	$0.040	0.05	4
mimo-v2-flash	$0.010	$0.030	0.05	3
meituan/longcat-flash-lite	$0.010	$0.100	0.05	10
qwen/qwen3.5-flash	$0.010	$0.040	0.05	4
gemma-4-31b	$0.014	$0.040	0.07	2.857143
qwen3-coder-flash	$0.014	$0.057	0.072	3.9861112
meituan/longcat-flash-thinking	$0.015	$0.150	0.075	10
gemini-2.5-flash-imageFixed	$0.015	$0.015	0	0
xai/grok-4-fast	$0.020	$0.050	0.1	2.5
glm-4.5-air	$0.020	$0.110	0.1	5.5
glm-4.6v-flash	$0.020	$0.020	0.1	1
gpt-oss-20b	$0.020	$0.030	0.1	1.5
meituan/longcat-flash-chat	$0.020	$0.080	0.1	4
glm-4.5-flash	$0.020	$0.020	0.1	1
longcat-flash	$0.020	$0.080	0.1	4
jimeng-4.0Fixed	$0.020	$0.020	0	0

Showing 20 of 107 models.