GLM 5.2

$1.4
Input / MTok
$4.4
Output / MTok
$0.14
Cache read / MTok

Hosted third-party inference; price is Fireworks' Standard serverless rate, not Zhipu's own API. Fireworks also sells Fast and US-region deployments of this model at higher per-token rates, and an optional Priority tier at 1.25x.

API identifier accounts/fireworks/models/glm-5p2 · vendor pricing page

Full price sheet

MetricUSD / million tokens
Input$1.4
Output$4.4
Cache read$0.14

Price history

ObservedMetric Price
2026-08-08 07:26:49 Input $1.4
2026-08-08 07:26:49 Output $4.4
2026-08-08 07:26:49 Cache read $0.14

Current prices are free and always will be. The full series — every observation since we started watching, which nobody can reconstruct after the fact — is the part Pro pays for.

Changes affecting this model

coverage
GLM 5.2 added to coverage
2026-08-08

Compare with

Models at a similar price point.

ModelInputOutput
GLM-5.2 $1.4$4.4 compare →
GLM 5.1 $1.4$4.4 compare →
Kimi K2.6 $1.2$4.5 compare →
o3-mini $1.1$4.4 compare →
o4-mini $1.1$4.4 compare →
GPT-5.4 mini $0.75$4.5 compare →