GLM-5.3-Flash
AvailableA Z.ai model with a 1M-token context window, image input and tool calling. On the Z.ai Open Platform API since August 26, 2026.
Access details: Z.ai Open Platform API
An alias. The provider can point it at a newer version.
glm-5.3-flashOpen weights on Hugging Face: zai-org/GLM-5.3-Flash
Updated Oct 1, 2026
Capabilities & limits
- Context window
- 1M
- Maximum output
- 128K
- Image input
- Supported
- Tool calling
- Supported
- Structured output
- Supported
Pricing
USD / 1M tokens- Input
- $0.15
- Output
- $0.50
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
$0.15 per 1M tokensCached input
$0.03 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
$0.50 per 1M tokensPrice history
Oct 1, 2026
Input $0.15 per million tokens
Oct 1, 2026
Output $0.50 per million tokens
Technical details
- Parameters
- 320B
- Active parameters
- 18B
- Architecture
- Hybrid sparse and linear attention
- Training / knowledge cutoff
- Not published
- Input modalities
- Text, image, video, file
- Output modalities
- Text
From Z.ai
Official announcement ↗How they describe it
the first native multimodal model in the GLM-5 series
What they say is new
it outperforms GLM-5.2 across benchmarks and real-world workloads at one-tenth the price
Release & lifecycle
- First available
- Aug 26, 2026
- available
- As of Oct 1, 2026