z-ai API Pricing
All 22 z-ai models by input price. Refreshed hourly.
| Model | Input /1M | Output /1M | Blended | Context | Intelligence | CPS | |
|---|---|---|---|---|---|---|---|
| Z.ai: GLM 5.3 | $0.08 | $1.40 | $0.41 | 1.0M | 45 | S | Details → |
| Z.ai: GLM 5.3 Flash | $0.15 | $0.50 | $0.24 | 1.0M | 42 | A | Details → |
| Z.ai: GLM 4.7 | $0.54 | $1.98 | $0.90 | 205K | 22 | A | Details → |
| Z.ai: GLM 5.2 | $0.03 | $7.00 | $1.78 | 1.0M | 34 | A | Details → |
| Z.ai: GLM 4.5 Air | $0.13 | $0.85 | $0.31 | 131K | 11 | B | Details → |
| Z.ai: GLM 5.1 | $1.40 | $4.40 | $2.15 | 205K | 26 | B | Details → |
| Z.ai: GLM 4.6 | $0.55 | $2.20 | $0.96 | 205K | 15 | B | Details → |
| Z.ai: GLM 5 | $1.00 | $3.20 | $1.55 | 205K | 28 | B | Details → |
| Z.ai: GLM 4.6V | $0.30 | $0.90 | $0.45 | 131K | 8 | B | Details → |
| Z.ai: GLM 5 Turbo | $1.20 | $4.00 | $1.90 | 203K | 27 | B | Details → |
| Z.ai: GLM 5V Turbo | $1.20 | $4.00 | $1.90 | 203K | 24 | B | Details → |
| Z.ai: GLM 4.7 Flash | $0.06 | $0.40 | $0.15 | 200K | 15 | B | Details → |
| Z.ai: GLM 5.3 Prime | $2.80 | $8.80 | $4.30 | 1.0M | — | — | Details → |
| Z.ai: GLM 4 32B | $0.10 | $0.10 | $0.10 | 128K | — | — | Details → |
| Z.ai: GLM 5.3 FlashX | $0.37 | $1.25 | $0.59 | 1.0M | — | — | Details → |
| Z.ai: GLM 5.2 (batch) | $0.70 | $2.20 | $1.07 | 1.0M | — | — | Details → |
| Z.ai: GLM 5.3 Flash (batch) | $0.05 | $0.18 | $0.08 | 1.0M | — | — | Details → |
| Z.ai: GLM 5.3 (batch) | $0.45 | $2.00 | $0.84 | 1.0M | — | — | Details → |
| Z.ai: GLM 4.5 Air (free) | Free | Free | $0.00 | 131K | — | — | Details → |
| Z.ai: GLM 5.2 (free) | Free | Free | $0.00 | 33K | — | — | Details → |
| Z.ai: GLM 4.5 | $0.60 | $2.20 | $1.00 | 131K | — | — | Details → |
| Z.ai: GLM 4.5V | $0.60 | $1.80 | $0.90 | 66K | 7 | — | Details → |
FAQ
What is the cheapest z-ai model?
By input price, Z.ai: GLM 5.3 is lowest ($0.08/1M tokens). See the full table above.
How is z-ai priced?
Usage-based: input and output priced separately per 1M tokens, with cache read/write discounts on some models. The Blended column estimates a typical 3:1 request cost.