geekradar
Int
Explore GeekRadar

More to explore

Good gear All topics About us Say hello
GeekRadar / The comparison desk
COMPARE.
AI models
zhipuai

GLM-5.3

AI model Released

Context window
1,000,000 tokens
Maximum output
131,072 tokens
Open weights
Yes

No matched benchmark results are available for this entry yet.

Run it locally

Inference ยท memory estimate

GLM-5.3

Not enough verified architecture information for a reliable VRAM estimate.

API cost

USD / month

Standard text-token estimate. Excludes taxes, caching, batch discounts, reasoning and multimodal surcharges. Provider limits and regional availability may differ.

GLM-5.3

GLM-5.3 / Pricing tiers 6
Provider / scopeRateCurrencyAmount / unit
DeepInfrazai-org/GLM-5.3Standard Cached inputUSD0.2 / 1M tokens
InputUSD0.9 / 1M tokens
OutputUSD4 / 1M tokens
Fireworks AIGLM 5.3Priority Cached inputUSD0.325 / 1M tokens
InputUSD1.75 / 1M tokens
OutputUSD5.5 / 1M tokens
Fireworks AIGLM 5.3Standard Cached inputUSD0.26 / 1M tokens
InputUSD1.4 / 1M tokens
OutputUSD4.4 / 1M tokens
Fireworks AIGLM 5.3 FastStandard Cached inputUSD0.39 / 1M tokens
InputUSD2.1 / 1M tokens
OutputUSD6.6 / 1M tokens
SiliconFlowzai-org/GLM-5.3Standard Cached inputCNY2 / 1M tokens
InputCNY8 / 1M tokens
OutputCNY28 / 1M tokens
ZhipuGLM-5.3Standard Cached inputCNY2 / 1M tokens
InputCNY8 / 1M tokens
OutputCNY28 / 1M tokens

Capabilities

Context window
1,000,000 tokens
Maximum output
131,072 tokens
Reasoning
Yes
Tool calling
Yes
Open weights
Yes

Input modalities

  • text

Output modalities

  • text