Skip to content

GLM-5.3 Flash

The cheap multimodal GLM

Open weightsReleased: August 26, 2026Self-hostingHigh volumeVerified: October 24, 2026

What it is

Z.ai’s cheap multimodal coding model: 320B total parameters with 18B active, a 1M context, native image input, and $0.15/$0.50 per 1M tokens. Same post-training family as GLM-5.3, built to be the everyday tier.

NLT take

If you want image input and open weights without paying GLM-5.3 prices, this is the lane. It is also the cheapest way here to give an agent eyes on a UI.

Before you switch

The Ollama tag is the GLM-5.3 family page, not a Flash-only build. Check the tag before you pull it.

Cost for a real task

The same task on every model: 50,000 input tokens and 10,000 output tokens, at the base tier.

Task cost

$0.013

50K input + 10K output tokens

Input, per 1M
$0.15
Output, per 1M
$0.50
Cached input, per 1M
$0.030

Pricing source: Z.ai pricing

Specs

Maker
Z.ai
Licence
Open weights
Released
August 26, 2026
Context window
1,000,000 tokens
Parameters
320B total / 18B active
Max output
128,000 tokens
Input / output
Text · Image → Text

Also known as: glm-5.3-flash · glm-5.3-flash:cloud

Watch it in action

Hands-on videos from creators we trust. They open on YouTube; we do not host or re-upload them.

From our coverage

Articles about this model or its family. A “Background” tag means we have not covered this exact release yet.

Sources & model links

Every number on this card traces back to one of these links. The maker page proves the positioning, the pricing page proves the rates, the Hugging Face repo proves the weights exist, and the Ollama page proves a local tag.

Official

Open weights

Run locally