Z.ai: GLM 4.7 Flash

z-ai/glm-4.7-flash

GLM 4.7 Flash (Z.ai) is a low-cost open-weight model priced near the bottom of the board, at $0.06/$0.4 per million input/output tokens, served by 5 independent hosts. For the money it delivers #132 of 235 on the TryAii Score. Its best showing is #2 on Tau2-bench. It's reasonably quick at roughly 30-56 tokens/sec.

Prompt $/1M

$0.060

Completion $/1M

$0.400

Context

202,752 tok

Best provider

63 tok/s · DeepInfra

Specs

Model id: z-ai/glm-4.7-flash
Display name: Z.ai: GLM 4.7 Flash
Modality: text->text
Tokenizer: Other
Instruct type: —
Context length: 202,752
Max completion: 16,384
Prompt $/1M: $0.060
Completion $/1M: $0.400
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
DeepInfrafastest	63	386 ms	522 ms
Venice	60	655 ms	1,077 ms
Phala	43	814 ms	1,014 ms
Z.AI	30	6,177 ms	8,076 ms
Novita	30	2,138 ms	6,819 ms
Cloudflare	26	335 ms	433 ms
z-aifastest	—	—	—
Artificial Analysis	0	0 ms	—