GLM-5.3
AvailableA Z.ai model with a 1M-token context window and tool calling. On the Z.ai Open Platform API since August 14, 2026.
Access details: Z.ai Open Platform API
An alias. The provider can point it at a newer version.
glm-5.3Open weights on Hugging Face: zai-org/GLM-5.3
Updated Oct 1, 2026
Capabilities & limits
- Context window
- 1M
- Maximum output
- 128K
- Image input
- Unsupported
- Tool calling
- Supported
- Structured output
- Supported
Pricing
USD / 1M tokens- Input
- $1.40
- Output
- $4.40
Standard rates per million tokens. Discounts and long-context rates, where offered, are on Z.ai's pricing page.
Full rate card 4 rates
All prices in USD.
Input tokens
$1.40 per 1M tokensCached input
$0.26 per 1M tokens- prompt caching
Cached input storage
$0.00 per 1M tokens (storage unit not stated)- prompt caching
- limited-time free; end date not stated
Output tokens
$4.40 per 1M tokensPrice history
Oct 1, 2026
Input $1.40 per million tokens
Oct 1, 2026
Output $4.40 per million tokens
Technical details
- Parameters
- 744B
- Active parameters
- 40B
- Training / knowledge cutoff
- Not published
- Input modalities
- Text
- Output modalities
- Text
From Z.ai
Official announcement ↗How they describe it
Z.ai's latest flagship model, delivering comprehensive advancements in complex software engineering and agent capabilities.
What they say is new
It uses the same base model as GLM-5.2 — every gain comes from post-training.
Release & lifecycle
- First available
- Aug 14, 2026
- available
- As of Oct 1, 2026