All AI models · LLM benchmarks · Methodology

Z.AI

GLM-5.1 FP8

Flagship GLM model for hybrid reasoning, coding, and agentic engineering

Model facts

Context window
203K tokens
Maximum output
131K tokens
Cheapest paid input
$0.85 per 1M tokens
Cheapest paid output
$3.3 per 1M tokens
Open weights
yes
Providers
1

Capabilities and modalities

reasoning, tool calling, structured output, temperature control, open weights, text.

Local hardware estimate

At 4K context: Q4_K_M 462.4 GiB, Q8_0 813.5 GiB, F16 1471.7 GiB working memory.

Parameters
753.9 billion
Architecture
glmmoedsa
Model license
mit

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

Observed price history

  • 2026-08-24: $0.85 input / $3.3 output per 1M tokens

API providers

  • NEAR AI Cloud — model id zai-org/GLM-5.1-FP8; $0.85 input / $3.3 output per 1M tokens; provider documentation