Z.ai: GLM 5.2

relace/glm-5.2

Tools
JSON mode
Vision
Streaming

Released Jun 13, 2026

Context: 1.0M
Max out: 131K
From / 1M: $0.034

Providers

Relace
relace/glm-5.2
Input / 1M$0.034
Output / 1M$7.00
Cache read / 1MN/A
Speed131.2 t/s
First token553 ms
Baseten
baseten/GLM-5.2
Input / 1M$0.75
Output / 1M$2.40
Cache read / 1MN/A
Speed158.9 t/s
First token973 ms
DeepInfra
baseten/GLM-5.2
Input / 1M$0.75
Output / 1M$2.40
Cache read / 1MN/A
Speed158.9 t/s
First token973 ms
CoreWeave / W&B Inference
baseten/GLM-5.2
Input / 1M$0.75
Output / 1M$2.40
Cache read / 1MN/A
Speed158.9 t/s
First token973 ms
DeepInfra
deepinfra/GLM-5.2
Input / 1M$0.75
Output / 1M$2.40
Cache read / 1MN/A
Speed158.9 t/s
First token973 ms
Baseten
deepinfra/GLM-5.2
Input / 1M$0.75
Output / 1M$2.40
Cache read / 1MN/A
Speed158.9 t/s
First token973 ms
CoreWeave / W&B Inference
deepinfra/GLM-5.2
Input / 1M$0.75
Output / 1M$2.40
Cache read / 1MN/A
Speed158.9 t/s
First token973 ms
CoreWeave / W&B Inference
wandb/GLM-5.2
Input / 1M$0.75
Output / 1M$2.40
Cache read / 1MN/A
Speed158.9 t/s
First token973 ms
Baseten
wandb/GLM-5.2
Input / 1M$0.75
Output / 1M$2.40
Cache read / 1MN/A
Speed158.9 t/s
First token973 ms
DeepInfra
wandb/GLM-5.2
Input / 1M$0.75
Output / 1M$2.40
Cache read / 1MN/A
Speed158.9 t/s
First token973 ms
Wafer
wafer/GLM-5.2
Input / 1M$1.20
Output / 1M$4.10
Cache read / 1M$0.26
Speed158.3 t/s
First token236 ms
Arcee AI
arcee/glm-5.2
Input / 1M$1.40
Output / 1M$4.40
Cache read / 1MN/A
Speed101.0 t/s
First token1,471 ms
Atlas Cloud
arcee/glm-5.2
Input / 1M$1.40
Output / 1M$4.40
Cache read / 1MN/A
Speed101.0 t/s
First token1,471 ms
Novita AI
arcee/glm-5.2
Input / 1M$1.40
Output / 1M$4.40
Cache read / 1MN/A
Speed101.0 t/s
First token1,471 ms
Atlas Cloud
atlas-cloud/glm-5.2
Input / 1M$1.40
Output / 1M$4.40
Cache read / 1MN/A
Speed101.0 t/s
First token1,471 ms
Arcee AI
atlas-cloud/glm-5.2
Input / 1M$1.40
Output / 1M$4.40
Cache read / 1MN/A
Speed101.0 t/s
First token1,471 ms
Novita AI
atlas-cloud/glm-5.2
Input / 1M$1.40
Output / 1M$4.40
Cache read / 1MN/A
Speed101.0 t/s
First token1,471 ms
Novita AI
novita-ai/glm-5.2
Input / 1M$1.40
Output / 1M$4.40
Cache read / 1MN/A
Speed101.0 t/s
First token1,471 ms
Arcee AI
novita-ai/glm-5.2
Input / 1M$1.40
Output / 1M$4.40
Cache read / 1MN/A
Speed101.0 t/s
First token1,471 ms
Atlas Cloud
novita-ai/glm-5.2
Input / 1M$1.40
Output / 1M$4.40
Cache read / 1MN/A
Speed101.0 t/s
First token1,471 ms
Novita AI
novita/glm-5.2
Input / 1M$1.40
Output / 1M$4.40
Cache read / 1M$0.26
Speed101.0 t/s
First token1,471 ms
Arcee AI
novita/glm-5.2
Input / 1M$1.40
Output / 1M$4.40
Cache read / 1M$0.26
Speed101.0 t/s
First token1,471 ms
Atlas Cloud
novita/glm-5.2
Input / 1M$1.40
Output / 1M$4.40
Cache read / 1M$0.26
Speed101.0 t/s
First token1,471 ms