Model prices / Zhipu AI / Z.ai (GLM)
GLM-5.3-Flash API pricing
Official API pricing for GLM-5.3-Flash (Zhipu AI / Z.ai (GLM)) on Volcano Engine Ark, Zhipu BigModel Open Platform (CNY), Z.ai API Platform (USD): cache and off-peak prices, context length, open weights and regional availability, with sources and check dates.
- Context
- 1M
- Max output
- —
- Open weights
- Yes · MIT
- Current version
- —
- Hugging Face
- zai-org/GLM-5.3-Flash ↗
China vs global edition
Rate 1 USD = 6.6862 CNY (2026-10-16). Published prices on each side are authoritative.
CN · CNY Volcano Engine Ark
glm-5-3-flash-260828| Tier | Input | Cached input | Cache write | Output |
|---|---|---|---|---|
| Standard | ¥0.8≈$0.12 | ¥0.23≈$0.034 | — | ¥2.8≈$0.419 |
Same as Zhipu's standard price; Ark also bills cache storage at ¥0.017 per 1M tokens per hour
CN · CNY Zhipu BigModel Open Platform (CNY)
glm-5.3-flash| Tier | Input | Cached input | Cache write | Output |
|---|---|---|---|---|
| Standard | ¥0.8≈$0.12 | ¥0.23≈$0.034 | — | ¥2.8≈$0.419 |
Standard price shown. A limited-time 50% discount applies (input ¥0.4, cached ¥0.115, output ¥1.4); no end date is given. Fast variant glm-5.3-flashx: input ¥2, cached ¥0.57, output ¥7. Cache storage free for a limited time
GLOBAL · USD Z.ai API Platform (USD)
glm-5.3-flash| Tier | Input | Cached input | Cache write | Output |
|---|---|---|---|---|
| Standard | $0.15≈¥1.003 | $0.03≈¥0.201 | — | $0.5≈¥3.343 |
Fast variant glm-5.3-flashx: input $0.37, cached $0.075, output $1.25; cache storage free for a limited time
Source
- https://docs.bigmodel.cn/cn/guide/models/vlm/glm-5.3-flash · 2026-10-17
- https://huggingface.co/zai-org/GLM-5.3-Flash · 2026-10-17
≈ marks values converted at the ECB reference rate, for comparison only; the published currency is authoritative.