zai-org / text-generation Open weights Also via API updated 1 year ago

GLM-4.5-Air

Name: GLM-4.5-Air
Price: 0.13 USD
Author: zai-org

👋 Join our Discord community. 📖 Check out the GLM-4.5 technical blog, technical report, and Zhipu AI technical documentation. 📍 Use GLM-4.5 API services on Z.ai API Platform (Global) or Zhipu AI Open Platform (Mainland China). 👉 One click to GLM-4.5.

Params

110.5 B

Context

131,072

Downloads 30d

818 K

Likes

646

Commercial use: allowed mit Not gated SAFETENSORS 2 languages View on Hugging Face ↗

Download history

daily snapshots · 88 days

▲ 634 K in the last 30 days (344.6%)

818 K184 K

Jul 28Aug 26Sep 24Oct 23

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

File	Quant	Size	Est. VRAM	Verdict on RTX 4090 · 24 GB
model.safetensors	bf16	220.9 GB	260.1 GB	❌ Won’t fit
model.safetensors (bf16, full)	bf16 + 128K ctx	220.9 GB	508.7 GB	❌ Won’t fit

Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Run it

copy-paste, exact tags checked against the Hub

~ · curl · api/v1

$ curl -s https://aimodelscomparison.com/api/v1/models/glm-4-5-air
{
  "hf_id": "zai-org/GLM-4.5-Air",
  "params_b": 110.47,
  "context_length": 131072,
  "license": { "id": "mit", "commercial": "yes" },
  "downloads_30d": 817559,
  "vram_estimates": [
    { "quant": "bf16", "gb": 260.1 }
  ],
  "updated_at": "2026-07-28T18:05:17Z"
}

est. VRAM —on RTX 4090 · 24 GBJSON API →

Use via API

via OpenRouter · USD per 1M tokens · synced 2026-10-23

$0.13

input / 1M

$0.85

output / 1M

$0.025

cached input / 1M

$0.98

1M in + 1M out

Context window: 131,072 tokens
Max output: 98,304 tokens
Providers: 3
Cheapest provider: Novita · $0.13 / $0.85
Best throughput: —
AA Intelligence / Coding / Agentic: 11.1 / — / —

✓ Tool calling ✓ Reasoning ✗ Structured outputs ✗ Image input ✗ File input ✗ Audio input ✓ Prompt caching

Specifications

Architecture: Glm4MoeForCausalLM
Parameters: 110.5 B
Tensor type: BF16
Context length: 131,072
Vocabulary: 151,552
Layers / heads: 46 / 96
Licence: mit
First seen on the Hub: 2025-07-20
Training datasets: undisclosed
Added to our catalog: 2026-07-28

Family

Base model and the most-downloaded derivatives in the catalog.

Derivative GLM-4.5-Air unsloth 189 K

Compare with any text-generation model

Popular comparisons

dolphin-2.9.1-yi-1.5-34b 4.6 M DeepSeek-V4-Flash-0731 4.3 M gpt-oss-120b 3.0 M Qwen3-32B 2.8 M Qwen3-Coder-Next-FP8 990 K NVIDIA-Nemotron-3-Super-120B-A12B-BF16 974 K

Appears in

Trending text-generation