Z.ai API pricing
Z.ai currently lists 13 models in our data. The lowest input price is GLM-5.3 Flash at $0.15 per 1M tokens and the lowest output price is GLM-5.3 Flash at $0.50; the newest model is GLM-5.3 Flash (2026-08-26). 8 of the 13 have a cached-input price and 0 a batch price. Tick models to compare them, or put your traffic into the calculator. Official price page: docs.z.ai ↗.
Billing rules for caching, Batch and long prompts: Z.ai API cost guide.
Default order: premium models (output $6.00+/1M) first, newest release first. Tick models to compare them side by side.
| Compare | Model | Provider | Released | Input /1M | Output /1M | Cached input /1M | Max input |
|---|---|---|---|---|---|---|---|
| GLM-4.5 X | Z.ai | 2025-07-28 | $2.20 | $8.90 | — | 128K | |
| GLM-5.3 Flash | Z.ai | 2026-08-26 | $0.15 | $0.50 | $0.03 | 1048K | |
| GLM-5.3 | Z.ai | 2026-08-14 | $1.40 | $4.40 | $0.26 | 1000K | |
| GLM-5.2 | Z.ai | 2026-06-13 | $1.40 | $4.40 | $0.26 | 1000K | |
| GLM-5.1 | Z.ai | 2026-04-07 | $1.40 | $4.40 | $0.26 | 200K | |
| GLM-5 | Z.ai | 2026-02-12 | $1.00 | $3.20 | $0.20 | 200K | |
| GLM-4.7 | Z.ai | 2025-12-22 | $0.60 | $2.20 | $0.11 | 200K | |
| GLM-4.6 | Z.ai | 2025-09-30 | $0.60 | $2.20 | $0.11 | 200K | |
| GLM-4.5v | Z.ai | 2025-08-11 | $0.60 | $1.80 | — | 128K | |
| GLM-4.5 | Z.ai | 2025-07-28 | $0.60 | $2.20 | — | 128K | |
| GLM-4.5 Air | Z.ai | 2025-07-28 | $0.20 | $1.10 | — | 128K | |
| GLM-4.5 AirX | Z.ai | 2025-07-28 | $1.10 | $4.50 | — | 128K | |
| GLM-5 Code | Z.ai | — | $1.20 | $5.00 | $0.30 | 200K |
Recent price changes
No price changes recorded since tracking began on 2026-10-08.
Estimates from published per-token rates; check official pricing before budgeting. Data synced from the LiteLLM price list 2026-10-13 08:00 UTC.
FAQ
Where do these prices come from?
From the open-source LiteLLM price list, refreshed every 4 hours and, for providers with an automatic check, compared field by field with the provider's official pricing page. Each model page shows what was verified.
Why is a model missing?
We list first-party chat and reasoning models with published per-token prices. Audio, image, realtime, fine-tuned and third-party-hosted models are out of scope; deprecated models move to the retired list. Missing or wrong entries can be reported on the feedback board.