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
| Metric | USD / million tokens |
|---|---|
| Input | $1.4 |
| Output | $4.4 |
| Cache read | $0.14 |
Price history
| Observed | Metric | 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
—
2026-08-08Compare with
Models at a similar price point.
| Model | Input | Output | |
|---|---|---|---|
| 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 → |