modelrelay_
Navigate ModelRelay
Get started
Sign in
← All models

GLM 5.3 Flash

glm-5.3-flash

Open-weight sparse MoE model for efficient coding and long-horizon agentic work

Intelligence
41.8
Context
1.04M
Training cutoff
--
Added
2026-08-29
Inputs
Vision

Providers

4 routes serve GLM 5.3 Flash, in the order requests are offered to them. Every figure is measured on its own route; where one has too little traffic in the selected window, it names what it is based on rather than borrowing the model's number.

Fireworks AI primary

accounts/fireworks/models/glm-5p3-flash

Uptime 99.0%
Input / 1M
$0.15
Output / 1M
$0.50
TTFT
1.47s live traffic · 7d · n=907
Output rate
36.4 tok/s live traffic · 7d · n=907
1.04M context 131,072 max output cache $0.029 read / $0.15 write per 1M Vision ZDR Retention None Training No Provider terms, reviewed 2026-10-13warming · 30m
Prompt caching Automatic reuse Eligible Cache key Affinity hint Caller breakpoints None advertised
Together AI failover 1

zai-org/GLM-5.3-Flash

Uptime 90.2%
Input / 1M
$0.15
Output / 1M
$0.50
TTFT
1.25s live traffic · 7d · n=53
Output rate
123.3 tok/s live traffic · 7d · n=53
1.04M context 131,072 max output cache $0.03 read / $0.15 write per 1M Vision ZDR Retention None Training No Provider terms, reviewed 2026-10-13warming · 30m
Prompt caching Automatic reuse Eligible Cache key Affinity hint Caller breakpoints None advertised
NEAR AI failover 2

z-ai/glm-5.3-flash

Uptime 90.4%
Input / 1M
$0.075
Output / 1M
$0.25
TTFT
1.80s live traffic · 7d · n=48
Output rate
15.2 tok/s live traffic · 7d · n=48
1.04M context 131,072 max output cache $0.015 read / $0.075 write per 1M VisionRetention Unknown Training No Provider terms, reviewed 2026-10-13warming · 30m
Prompt caching Automatic reuse Eligible Cache key Ignored Caller breakpoints None advertised
Inco failover 3

glm-5.3-flash:fast

Uptime 74.4%
Input / 1M
$0.30
Output / 1M
$1.00
TTFT
0.49s fixed prompt · n=8
Output rate
470.3 tok/s fixed prompt · n=8
1.04M context 131,072 max output cache $0.06 read / $0.30 write per 1M VisionRetention Yes, period not published Training No Provider terms, reviewed 2026-10-15warming · 30m
Prompt caching Automatic reuse Eligible Cache key Ignored Caller breakpoints None advertised

TTFT is the median time to the first visible answer token over real ModelRelay requests, with a fixed prompt standing in for models that have no traffic yet. Speed ranks by it. Intelligence is the Artificial Analysis Intelligence Index.