modelbenchmark.io

GLM-5.2 Turbo (SCX.ai)

Zhipu · glm-5-2-fast

Compare

Open flagship GLM for long-horizon coding agents and million-token context work

Specification

most-agreed values

Context
1M
Max output
131K
Released
2026-06-13
Knowledge cutoff
Retires
Open weights
yes
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
$2.20
Output
$6.50
Cache read
$0.45
Cache write
$2.10

Available from 10 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
neuralwatt$1.45$4.50$0.1451M1M
baseten · zai-org$2.10$6.60$0.211M262K
fireworks_ai$2.10$6.60$0.211M131K
fireworks-ai · accounts$2.10$6.60$0.211M131K
pioneer · zai-org$2.10$6.60$0.21$2.101M128K
requesty$2.10$6.60$0.211M131K
vercel · zai$2.10$6.60$0.211M128K
llmgateway$2.20$6.50$0.451M131K
llmgateway-providers · scx-ai-gp$2.20$6.50$0.451M131K
above$2.31$7.26$0.2311M131K

Price history

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

DateHostField$/M
2026-09-02llmgatewayCache read$0.40
2026-09-10llmgatewayCache read$0.45
2026-09-02llmgateway-providers · scx-ai-gpCache read$0.40
2026-09-10llmgateway-providers · scx-ai-gpCache read$0.45
2026-09-02llmgatewayInput$1.99
2026-09-10llmgatewayInput$2.20
2026-09-02llmgateway-providers · scx-ai-gpInput$1.99
2026-09-10llmgateway-providers · scx-ai-gpInput$2.20
2026-09-02llmgatewayOutput$6.16
2026-09-10llmgatewayOutput$6.50
2026-09-02llmgateway-providers · scx-ai-gpOutput$6.16
2026-09-10llmgateway-providers · scx-ai-gpOutput$6.50

More from Zhipu

most-hosted first