Z.ai: GLM 5.2

z-ai/glm-5.2

GLM 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for long-horizon agent workflows, project-level software engineering,...

Prompt $/1M

$0.818

Completion $/1M

$2.570

Context

1,048,576 tok

Best provider

198 tok/s · Artificial Analysis

Specs

Model id: z-ai/glm-5.2
Display name: Z.ai: GLM 5.2
Modality: text->text
Tokenizer: Other
Instruct type: —
Context length: 1,048,576
Max completion: 131,072
Prompt $/1M: $0.818
Completion $/1M: $2.570
Free tier: no

Capabilities

Function callingno
JSON modeno
System promptno
Visionno
Moderatedno

Benchmark scores

Each axis is one benchmark, normalized to the best model in the field.

No benchmark data for this model.

Speed by provider

Provider	tok/s	TTFT	Total latency
Artificial Analysis	198	846 ms	—
Friendlifastest	116	620 ms	951 ms
Parasail	103	679 ms	947 ms
Wafer	98	2,036 ms	2,995 ms
Fireworks	95	1,030 ms	1,427 ms
WandB	81	581 ms	711 ms
Decart	76	783 ms	1,105 ms
Cloudflare	75	1,109 ms	1,510 ms
BaseTen	66	1,193 ms	1,500 ms
Ionstream	65	727 ms	1,088 ms
Io Net	55	1,621 ms	1,780 ms
Venice	54	1,375 ms	1,650 ms
GMICloud	53	1,452 ms	1,877 ms
Baidu	50	1,228 ms	1,707 ms
AtlasCloud	44	1,085 ms	1,356 ms
Morph	43	1,379 ms	1,825 ms
DekaLLM	41	1,158 ms	1,737 ms
Ambient	40	1,010 ms	1,618 ms
AkashML	38	958 ms	1,186 ms
Alibaba	32	1,534 ms	2,011 ms
StreamLake	29	3,425 ms	4,979 ms
Z.AI	28	4,751 ms	5,820 ms
DeepInfra	25	1,983 ms	3,403 ms
SiliconFlow	24	4,029 ms	5,052 ms
Phala	20	2,203 ms	2,896 ms
Novita	20	4,476 ms	5,858 ms
DigitalOcean	16	2,600 ms	4,317 ms
Together	15	3,041 ms	3,789 ms
Chutes	14	2,224 ms	2,916 ms
Inceptron	4	3,286 ms	5,268 ms