All AI models · LLM benchmarks · Methodology

Z.AI

GLM-5.3-Flash

Native multimodal GLM model for efficient coding and long-horizon agent tasks

Model facts

Context window
1M tokens
Maximum output
131K tokens
Cheapest paid input
$0.015 per 1M tokens
Cheapest paid output
$0.05 per 1M tokens
Open weights
yes
Providers
48

Capabilities and modalities

reasoning, tool calling, structured output, attachments, temperature control, open weights, text, image, video, pdf.

Local hardware estimate

At 4K context: Q4_K_M 197.6 GiB, Q8_0 347.3 GiB, F16 627.8 GiB working memory.

Parameters
321.3 billion
Architecture
glm5next
Model license
mit

Planning estimate adapted from the MIT-licensed whichllm estimator using metadata from Hugging Face; not a vendor minimum requirement.

Artificial Analysis benchmarks

Compare this model on the full LLM benchmark leaderboard.

ConfigurationAAICodingMathOutput tokens/s
default57.571.5not measured43.8

Observed price history

  • 2026-08-26: $0.075 input / $0.25 output per 1M tokens
  • 2026-08-27: $0.015 input / $0.05 output per 1M tokens

API providers