glm-5.3-flash

mit320B / 18B

Z.ai's first natively multimodal model, approaching Claude Opus 4.8 on coding and agentic benchmarks with just 18B active parameters.

Context
1M
Max output
128K
Input price
$0.15/1M tokens
Output price
$0.5/1M tokens

Capabilities

Reasoning & Interaction
Reasoning
Tool Calling
Output Control
Structured Output
JSON Mode
Infrastructure
Streaming
Prompt Caching
Fine-tuning

Details

Provider Ollama
Creator Z.AI (Zhipu)
Familyglm-5.3
Licensemit
Status—
Typechat
Input modalitiestext, image
Output modalitiestext
Open weightYes
Parameters320B / 18B
Architecture—
Context window1M tokens
Max input—
Max output128K tokens
Reasoning tokensYes
Knowledge cutoff—
Release date
Sourceofficial

Tools

Function Callingfunction_calling
Call external functions and APIs

Pricing

Input
$0.15
Output
$0.5
Cache write
—
Cache read
$0.03
Batch in
—
Batch out
—

Family Comparison: glm-5.3

ModelContextMax out
glm-5.3-flash1M128K
glm-5.31M128K

API

GET/v1/models/ollama/glm-5.3-flash