modelbenchmark.io

GLM 5.3 Flash Uncensored

Zhipu · glm-5-3-flash-uncensored

Compare

GLM 5.3 Flash Uncensored is an uncensored fine-tune of the efficient 320B mixture-of-experts reasoning model, built for unrestricted chat, creative writing, coding, agentic work, tool use, and long-context tasks.

Specification

most-agreed values

Context
1M
Max output
33K
Released
2026-07-29
Knowledge cutoff
Retires
Open weights
yes
Input
text, image
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.20
Output
$0.80
Cache read
$0.10

Available from 1 host

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
nano-gpt · z-ai$0.20$0.80$0.101M33K

Price history

append-only observations · a listing writes a row only when its price moves

DateHostField$/M
2026-09-02nano-gpt · z-aiCache read$0.175
2026-09-08nano-gpt · z-aiCache read$0.014
2026-09-09nano-gpt · z-aiCache read$0.175
2026-09-15nano-gpt · z-aiCache read$0.10
2026-09-02nano-gpt · z-aiInput$0.35
2026-09-08nano-gpt · z-aiInput$0.07
2026-09-09nano-gpt · z-aiInput$0.35
2026-09-15nano-gpt · z-aiInput$0.20
2026-09-02nano-gpt · z-aiOutput$1.40
2026-09-08nano-gpt · z-aiOutput$0.21
2026-09-09nano-gpt · z-aiOutput$1.40
2026-09-15nano-gpt · z-aiOutput$0.80

More from Zhipu

most-hosted first