Z.ai: GLM 4.6

z-ai/glm-4.6

Compared with GLM-4.5, this generation brings several key improvements: Longer context window: The context window has been expanded from 128K to 200K tokens, enabling the model to handle more complex...

Prompt $/1M

$0.500

Completion $/1M

$2.000

Context

202,752 tok

Best provider

125 tok/s · BaseTen

Specs

Model id: z-ai/glm-4.6
Display name: Z.ai: GLM 4.6
Modality: text->text
Tokenizer: Other
Instruct type: —
Context length: 202,752
Max completion: 131,072
Prompt $/1M: $0.500
Completion $/1M: $2.000
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
BaseTenfastest	125	1,040 ms	1,040 ms
Artificial Analysis	68	985 ms	—
AtlasCloudfastest	31	1,309 ms	1,474 ms
DeepInfra	26	708 ms	866 ms
Z.AI	26	3,419 ms	4,119 ms
Novita	25	1,565 ms	1,965 ms
SiliconFlow	18	2,860 ms	3,813 ms
Venice	17	1,201 ms	1,385 ms
Chutes	14	1,638 ms	1,793 ms
Io Net	4	3,431 ms	4,840 ms