Z.ai: GLM 5.3
Input per million tokens
$1.05
Unchanged since November 16, 2026
- November 16, 2026: $1.05
Output per million tokens
$3.36
Unchanged since November 16, 2026
- November 16, 2026: $3.36
Alias glm-5.3 > glm-5.3-1
GLM 5.3 is Z.ai's flagship Mixture-of-Experts model with 744B total parameters and 40B activated, using DeepSeek-style sparse attention for a 1M-token context window. It is built for agentic coding, long-horizon tool use, and complex reasoning, with post-training improvements over GLM 5.2.Reasoning is supported and enabled by default.
We are inviting early-access interest while we develop the platform.
| Model version | Status | Released | Retires | Hugging Face revision |
|---|---|---|---|---|
| glm-5.3-1CURRENT | Live |
Per million tokens
Batch is not offered for this model.
| Input | Cached input | Output | |
|---|---|---|---|
| On demand | $1.05 | Billed as input | $3.36 |
| Batch | Batch is not offered for this model. | ||
In every pool, every input token is billed at the input rate today.
Input per million tokens
$1.05
Unchanged since November 16, 2026
Output per million tokens
$3.36
Unchanged since November 16, 2026