GLM 5.3

Open weights by Z.ai

Z.ai's flagship. Reach for it on complex, long-horizon coding when DeepSeek V4.1 Flash falls short. It reads text only; when complex work involves images, use Kimi K3.1 Pro.

Get an API key Live status

Price per 1M tokens: $1.40 in$4.40 out; $0.26 cache read
Context: 1M; 128K max output
Parameters: 744B; 40B active
Weights: FP8; Official release

Text only
Tool calling
Reasoning always on, default max

How it ranks

Against every model we serve, best first. About the scores

Artificial Analysis Intelligence Index v5by Artificial Analysis

Kimi K3.1 Pro46
DeepSeek V4.1 Flash33
GLM 5.332

Not ranked, reported on another version: Kimi K3 (Intelligence v4.3: 44).

DeepSWEby Datacurve

DeepSeek V4.1 Flash77%
Kimi K3.1 Pro75.5%
GLM 5.369%
Kimi K368.5%

Terminal-Bench 4.0by tbench.ai

Kimi K3.1 Pro67.2%
DeepSeek V4.1 Flash42.3%
GLM 5.341.9%

Not ranked, reported on another version: Kimi K3 (Terminal-Bench 2.1: 85%).

Artificial Analysis Intelligence Index v5 for GLM 5.3: independent measurement. Source
DeepSWE for GLM 5.3: independent measurement. Source
Terminal-Bench 4.0 for GLM 5.3: independent measurement. Source

Pricing

Input: $1.40 per 1M tokens
Output: $4.40 per 1M tokens
Cache read: $0.26 per 1M tokens

See all prices

Specs

Context window: 1M tokens
Max output: 128K tokens
Parameters: 744B total, 40B active per token
Vision: No, text only
Tool calling: Yes
Reasoning: Always on (low, high, max)
Default effort: max
Weights: FP8, official release
In production since: August 29, 2026

Quickstart

Pick your tool; the command already carries this model's id. More tools (Pi, Copilot, Zed, omp) in the setup guides.

OpenCode

Built in

Launch OpenCode on this model with the umans CLI. Umans AI is also built into OpenCode: run /connect and pick it.

Terminal

curl -fsSL https://api.code.umans.ai/cli/install.sh | bash   # once
umans opencode --model umans-glm-5.3

Full setup in the docs

How it ranks

Pricing

Specs

Quickstart

Or consider