Z.ai: GLM 5.3 Flash

z-ai/glm-5.3-flash

GLM 5.3 Flash (Z.ai) is a low-cost open-weight model priced near the bottom of the board, at $0.15/$0.5 per million input/output tokens, served by 24 independent hosts. For the money it delivers #35 of 256 on the TryAii Score. Its best result is head-to-head chat (#9 on Chatbot Arena Elo (Code)). It's reasonably quick at roughly 44-125 tokens/sec.

Prompt $/1M

$0.150

Completion $/1M

$0.500

Context

1,048,576 tok

Best provider

269 tok/s · CoreWeave

Specs

Model id: z-ai/glm-5.3-flash
Display name: Z.ai: GLM 5.3 Flash
Modality: text+image+video->text
Tokenizer: Other
Instruct type: —
Context length: 1,048,576
Max completion: 943,717
Prompt $/1M: $0.150
Completion $/1M: $0.500
Free tier: no

Capabilities

Function callingno
JSON modeno
System promptno
Visionyes
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
CoreWeavefastest	269	625 ms	743 ms
Modal	177	251 ms	286 ms
Parasail	163	1,205 ms	1,713 ms
BaseTen	146	594 ms	850 ms
Together	140	385 ms	493 ms
Reka	136	1,219 ms	1,540 ms
Sail Research	133	1,108 ms	1,516 ms
DekaLLM	125	1,087 ms	1,434 ms
Friendli	125	1,226 ms	2,079 ms
Venice	112	840 ms	1,192 ms
Inceptron	109	514 ms	633 ms
InferenceNet	107	930 ms	1,200 ms
Fireworks	102	641 ms	669 ms
DeepInfra	90	1,055 ms	1,434 ms
Morph	83	1,335 ms	2,244 ms
Crusoe	78	943 ms	1,089 ms
Decart	62	1,261 ms	1,458 ms
Relace	57	1,038 ms	1,374 ms
Artificial Analysis	55	2,556 ms	—
Z.AI	51	2,544 ms	3,067 ms
DigitalOcean	47	630 ms	818 ms
SiliconFlow	46	1,790 ms	2,840 ms
Novita	43	1,521 ms	2,151 ms
AtlasCloud	42	2,384 ms	3,415 ms
StreamLake	39	1,217 ms	1,567 ms
GMICloud	36	2,018 ms	2,669 ms
Phala	26	4,079 ms	4,601 ms
OpenInference	21	3,662 ms	6,215 ms
Near AI	20	1,223 ms	1,360 ms
Wafer	15	1,037 ms	1,522 ms