Z.ai: GLM 4.7

z-ai/glm-4.7

GLM-4.7 is Z.ai’s latest flagship model, featuring upgrades in two key areas: enhanced programming capabilities and more stable multi-step reasoning/execution. It demonstrates significant improvements in executing complex agent tasks while...

Prompt $/1M

$0.400

Completion $/1M

$1.750

Context

202,752 tok

Best provider

358 tok/s · Cerebras

Specs

Model id: z-ai/glm-4.7
Display name: Z.ai: GLM 4.7
Modality: text->text
Tokenizer: Other
Instruct type: —
Context length: 202,752
Max completion: 131,072
Prompt $/1M: $0.400
Completion $/1M: $1.750
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
Cerebrasfastest	358	326 ms	503 ms
Artificial Analysis	116	547 ms	—
Google	107	524 ms	649 ms
SiliconFlow	56	1,926 ms	2,197 ms
Nebius	48	740 ms	1,187 ms
AtlasCloud	33	1,822 ms	2,817 ms
DeepInfra	27	935 ms	1,227 ms
StreamLake	27	1,783 ms	2,970 ms
Parasail	25	1,712 ms	2,224 ms
Venice	24	1,130 ms	1,509 ms
Z.AI	21	8,766 ms	13,626 ms
Novita	21	2,116 ms	3,162 ms
Phala	20	1,865 ms	2,274 ms
Chutes	3	1,755 ms	2,421 ms
DekaLLM	2	928 ms	1,174 ms