Back to models
available
GLM-5.2
z-ai/glm-5-2-fastPrices
- Input
$2.10 per 1M tokens
low- Input (cache write)
$2.10 per 1M tokens
low- Input (cached read)
$0.21 per 1M tokens
low- Output
$6.60 per 1M tokens
low
Also available on
The same model, sold by someone else. The price above is the maker's own.
| Channel | What | Price |
|---|---|---|
| Other · baseten | Input | $2.10 per 1M tokens |
| Input (cached read) | $0.21 per 1M tokens | |
| Output | $6.60 per 1M tokens | |
| Other · vercel | Input | $2.80 per 1M tokens |
| Input (cached read) | $0.56 per 1M tokens | |
| Output | $8.80 per 1M tokens |
Specifications
- Provider
- z-ai
- Context window
- 1,000,000
- Max output tokens
- 128,000
- Open weights
- yes
- Released
- 06/13/2026
- Retires
- no date announced
- First seen by this tracker
Price history
No price of this model has changed since we started tracking it.
- Input
- 2.1 per 1M tokens, unchanged since 09/14/2026
- Output
- 6.6 per 1M tokens, unchanged since 09/14/2026
- Input (cached read)
- 0.21 per 1M tokens, unchanged since 09/14/2026
- Input (cache write)
- 2.1 per 1M tokens, unchanged since 09/14/2026