Providers / Z.ai

Z.ai API Pricing

Z.ai models and prices

USD per 1M tokens, official API list prices.

ModelInputOutputCachedBatchVerified
GLM-5.3$1.4$4.4$0.26—2026-11-03
GLM-5.3-Flash$0.15$0.5$0.03—2026-11-03
GLM-5.3-FlashX$0.37$1.25$0.075—2026-11-03

Z.ai (Zhipu) prices its international GLM API in USD on a flat pay-as-you-go schedule. GLM-5.3 is the current flagship at $1.40 per million input tokens and $4.40 per million output tokens, with cached input at $0.26. GLM-5.3-Flash is the volume multimodal tier at $0.15 / $0.50 (cached input $0.03), and GLM-5.3-FlashX is the faster Flash serving tier at $0.37 / $1.25 (cached input $0.075). All three share a 1M-token context window and a 128K max output.

Two billing details matter for budgets. Cached Input Storage is listed as Limited-time Free on the official pricing page, so the calculator only bills cache hits at the cached-input rate. No Batch column appears on the Latest Models table, so the calculator uses Standard rates only. GLM-5.3 is text-only with always-on reasoning; Flash and FlashX accept image, video, and file inputs.

Figures below are official USD rates from docs.z.ai pricing (Latest Models), each stamped with a verification date (full breakdown: GLM-5.3 API pricing). The GLM Coding Plan is a separate points-based subscription and is never mixed into this table. Older GLM-5.2 / GLM-4.x rows remain on the official page but are omitted here until we track them separately.

Further reading

Frequently asked questions

What is the cheapest Z.ai API model?

GLM-5.3-Flash, at $0.15 per 1M input tokens and $0.5 per 1M output tokens (verified 2026-11-03). Its cost calculator shows worked examples at realistic volumes.

Are these Z.ai's official prices?

Yes — this page tracks official API list prices only, each cross-checked and stamped with a verification date. Gateway resellers and consumer subscriptions use different schedules and are not mixed in.

How do I estimate my Z.ai bill?

Open any model above and use its calculator: enter your input, output and cached token counts plus your call volume, and it computes the per-call and monthly cost from the same verified prices. The homepage calculator also compares models across providers side by side.