glm-5.3-flash
Description
GLM‑5.3‑Flash is built on a newly trained base model, with its architecture and training scheme redesigned around capability and efficiency. For the first time in the GLM series, it introduces a hybrid architecture combining sparse attention and linear attention, which significantly reduces long‑context inference costs while retaining precise long‑context processing capabilities. The model also adopts Manifold‑Constrained Hyper‑Connections (mHC) to further improve scaling efficiency. Combined with our latest 30T‑token multimodal pre‑training corpus, these improvements enable GLM‑5.3‑Flash to deliver stronger intelligence with less computational resources.
Specifications
- Type
- Text
- Vendor
- 智谱
- Model ID
-
glm-5.3-flash - Context size
- 1M
- Max input length
- 1M
- Max output length
- 128K
- Requests per minute
- 500
- Tokens per minute
- 1000000
Pricing
Default
Charged by input & output
- Input base price
- $0.00015714 / 1000 tokens
- Output base price
- $0.00055014 / 1000 tokens
Cache Hit
Charged by input
- Input base price
- $3.929E-5 / 1000 tokens
Explicit Cache Hit
Charged by input
- Input base price
- $3.929E-5 / 1000 tokens