Skip to content
AI Atlas
ModelDeprecated

GLM 4.5

Z.ai (Zhipu AI)huggingface.co/zai-org/GLM-4.5

GLM-4.5 is our latest flagship foundation model, purpose-built for agent-based applications. It leverages a Mixture-of-Experts (MoE) architecture and supports a context length of up to 128k tokens. GLM-4.5 delivers significantly...

Open in Graph
quality68

Updated 3 h ago · first seen 11 Sept 2026

model_01M294WWDZ0204TZY1EFTAP042

Overview

Identity

Identity block not returned by the API for this entity.

Openness

Openness not classified yet — no sourced evidence to place this model in the ontology.

Key facts

Release date

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 4 h agomedium

Status

Source:Artificial AnalysisT2observed 8 h agomedium

Knowledge cutoff

Source:OpenRouter public model & pricing listingT2observed 10 h agomedium

Model card
huggingface.co/zai-org/GLM-4.5

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 10 h agomedium

Openrouter id

Source:OpenRouter public model & pricing listingT2observed 10 h agomedium

Architecture

Architecture

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 9 h agomedium

Model type

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 9 h agomedium

Parameters

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 10 h agomedium

Weights dtype

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 9 h agomedium

File size

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 9 h agomedium

Library name

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 9 h agomedium

Pipeline tag

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 10 h agomedium

Hugging Face repo

Source:OpenRouter public model & pricing listingT2observed 10 h agomedium

Capabilities

Modalities

Modalities
text
Input
text
Output
text

Capabilities

  • Tool calling

    Yes

    OpenRouter public model & pricing listing · T2

  • Structured output

    Yes

    OpenRouter public model & pricing listing · T2

  • Reasoning

    Yes

    OpenRouter public model & pricing listing · T2

  • Vision

    Unavailable

  • Audio

    Unavailable

  • Fine-tuning available

    Unavailable

Context window

Source:OpenRouter public model & pricing listingT2observed 7 h agomedium

Max output

Source:OpenRouter public model & pricing listingT2observed 10 h agomedium

Knowledge cutoff

Source:OpenRouter public model & pricing listingT2observed 10 h agomedium

Languages

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 9 h agomedium

Benchmarks8

Compare with another model →

Comparable same task and conditions · Partially comparable same task, conditions differ (effort, temperature, judge) · Not comparable different variant or metric

No benchmark results recorded

Results appear when a tier 1–3 source publishes them; we never copy scores without a source.

Providers & Pricing1

All offers in the price terminal →
Current prices per 1M tokens
ProviderInput / 1MOutput / 1MCached inBatch in / outContextObservedSource
Z.ai APIz-ai/glm-4.5$0.60$2.2$0.11—131.1K2 h agoopenrouter.aiT2

USD per 1M tokens as published by each provider (USD). Rows are append-only: every change is kept in the history below.

Price history

Step lines per provider; amber markers are recorded changes. Click a marker or a row for the evidence behind that price.

Output price · USD / 1M tokens 1 provider

Output price history of GLM 4.5$0$1$2$3Sept 26Sept 26Sept 26Sept 26Sept 26Sept 26Sept 26Sept 26Z.ai API: first observed → $2.2 · 11 Sept 2026
  • Z.ai API
  • Z.ai APIfirst observed $2.211 Sept 2026

Input price · USD / 1M tokens 1 provider

Input price history of GLM 4.5$0$0.20$0.40$0.60$0.80Sept 26Sept 26Sept 26Sept 26Sept 26Sept 26Sept 26Sept 26Z.ai API: first observed → $0.60 · 11 Sept 2026
  • Z.ai API
  • Z.ai APIfirst observed $0.6011 Sept 2026

Hardware fit37

Estimated

4 of 37 device × quantization combinations fit.

Run locally: your machine →
Estimated hardware fit
HardwareQuantizationDevice memoryEst. memoryFits
Apple M3 Ultra4bit—206.5 GB est.Yes
Mac Studio (Apple M5 Ultra)4bit—206.5 GB est.Yes
AMD Instinct MI325X4bit256 GB206.5 GB est.Yes
NVIDIA DGX B2004bit1,440 GB206.5 GB est.Yes
Apple M2 Ultra4bit—206.5 GB est.No
Apple M1 Ultra4bit—206.5 GB est.No
Apple M3 Max4bit—206.5 GB est.No
Apple M4 Max4bit—206.5 GB est.No
Mac Studio (Apple M5 Max)4bit—206.5 GB est.No
MacBook Pro (Apple M5 Max)4bit—206.5 GB est.No
Apple M2 Max4bit—206.5 GB est.No
Apple M1 Max4bit—206.5 GB est.No
Apple M4 Pro4bit—206.5 GB est.No
Mac mini (Apple M5 Pro)4bit—206.5 GB est.No
MacBook Pro (Apple M5 Pro)4bit—206.5 GB est.No
Apple M3 Pro4bit—206.5 GB est.No
Apple M1 Pro4bit—206.5 GB est.No
Apple M2 Pro4bit—206.5 GB est.No
Apple M44bit—206.5 GB est.No
iMac (Apple M4)4bit—206.5 GB est.No
Mac mini (Apple M6)4bit—206.5 GB est.No
MacBook Air (Apple M5)4bit—206.5 GB est.No
MacBook Pro (Apple M5)4bit—206.5 GB est.No
Apple M24bit—206.5 GB est.No
Apple M34bit—206.5 GB est.No
Apple M14bit—206.5 GB est.No
NVIDIA GeForce RTX 30904bit24 GB206.5 GB est.No
NVIDIA GeForce RTX 40904bit24 GB206.5 GB est.No
NVIDIA GeForce RTX 50904bit32 GB206.5 GB est.No
NVIDIA A100 80GB4bit80 GB206.5 GB est.No
NVIDIA H100 SXM4bit80 GB206.5 GB est.No
NVIDIA H100 NVL4bit94 GB206.5 GB est.No
NVIDIA DGX Spark4bit128 GB206.5 GB est.No
NVIDIA H2004bit141 GB206.5 GB est.No
NVIDIA H200 NVL4bit141 GB206.5 GB est.No
NVIDIA B2004bit180 GB206.5 GB est.No
AMD Instinct MI300X4bit192 GB206.5 GB est.No
Assumptions (6)
  • Estimated, not measured: weights = parameters × bytes/param × 1.15 runtime overhead.
  • bytes/param: 4bit = 0.5, 8bit = 1.0, fp16 = 2.0 (uniform quantization, no per-layer exceptions).
  • KV cache approximated at 0.5 GB per 8 192 tokens of context, independent of architecture (GQA/MLA models need less).
  • A model 'fits' when the estimate is at most the device memory minus 2 GB reserved for the OS and framework.
  • Mixture-of-experts models are estimated on total parameters (all experts must be resident); active parameters are ignored.
  • Device memory uses the largest configuration when several are listed (e.g. Apple silicon tiers).

Papers1

Timeline14

Full timeline →
  • Context window changedModelGLM 4.5Z.ai (Zhipu AI)

    GLM 4.5: context length changed from 128000 to 131072

    Context window128K tokens→131.1K tokensopenrouter
    openrouter.ai
  • Benchmark resultModelGLM 4.5Z.ai (Zhipu AI)

    GLM 4.5 scores 54.2% on SWE-bench Verified

    swebench_leaderboard
    swebench.com
  • Benchmark resultModelGLM 4.5Z.ai (Zhipu AI)

    GLM 4.5 scores 64.2% on SWE-bench Verified

    swebench_leaderboard
    swebench.com
  • Benchmark resultModelGLM 4.5Z.ai (Zhipu AI)

    GLM 4.5 scores 21.97% on Terminal-Bench

    artificial_analysis
    artificialanalysis.ai
  • Benchmark resultModelGLM 4.5Z.ai (Zhipu AI)

    GLM 4.5 scores 42.98% on τ²-bench

    artificial_analysis
    artificialanalysis.ai
  • Benchmark resultModelGLM 4.5Z.ai (Zhipu AI)

    GLM 4.5 scores 44.08% on IFBench

    artificial_analysis
    artificialanalysis.ai
  • Benchmark resultModelGLM 4.5Z.ai (Zhipu AI)

    GLM 4.5 scores 12.97% on Humanity's Last Exam

    artificial_analysis
    artificialanalysis.ai
  • Benchmark resultModelGLM 4.5Z.ai (Zhipu AI)

    GLM 4.5 scores 78.18% on GPQA

    artificial_analysis
    artificialanalysis.ai
  • Benchmark resultModelGLM 4.5Z.ai (Zhipu AI)

    GLM 4.5 scores 12.77 on Artificial Analysis Intelligence Index

    artificial_analysis
    artificialanalysis.ai
  • Context window changedModelGLM 4.5Z.ai (Zhipu AI)

    GLM 4.5: context length changed from 131072 to 128000

    Context window131.1K tokens→128K tokensartificial_analysis
    artificialanalysis.ai
  • Release date changedModelGLM 4.5Z.ai (Zhipu AI)

    GLM 4.5: release date changed from 2025-07-20 to 2025-07-25

    Release date20 Jul 2025→25 Jul 2025openrouter
    openrouter.ai
  • Release date changedModelGLM 4.5Z.ai (Zhipu AI)

    GLM 4.5: release date changed from 2025-07-25 to 2025-07-20

    Release date25 Jul 2025→20 Jul 2025huggingface
    huggingface.co
  • New modelModelGLM 4.5Z.ai (Zhipu AI)

    New model: GLM 4.5 (Z.ai (Zhipu AI))

    openrouter
    openrouter.ai
  • Listed by providerModelGLM 4.5Z.ai (Zhipu AI)

    Z.ai API lists GLM 4.5 at $0.6 in / $2.2 out per 1M tokens

    openrouter
    openrouter.ai

Change history

Temporal, append-only claims: a new observation closes the previous claim instead of overwriting it. Rewind the record with the as-of picker.
1 claims · 1 propertiesShow all properties

Languageslanguages1

Claim history for Languages
ValueValid from → toStatusSourceConfidenceExtractor
en, zh → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Claims are temporal and append-only: a new observation closes the previous claim (valid_to) instead of overwriting it. Conflicting claims from different sources are kept side by side and flagged — never averaged. Methodology →

Provenance

Attributed facts

35

Source tiers

T235

Freshest observation

3 h ago

Conflicts

None

Source documents 6

Source documents
SourceDocumentTypeTierLast observedSnapshots
OpenRouter public model & pricing listingopenrouter.ai/api/v1/models catalogueT2· Quality secondary2 h ago6
Hugging Face Hub (public pages, model cards, papers)huggingface.co/zai-org/GLM-4.5/raw/main/README.md model_cardT2· Quality secondary3 h ago1
Hugging Face Hub (public pages, model cards, papers)huggingface.co/zai-org/GLM-4.5 model_pageT2· Quality secondary3 h ago5
Hugging Face Hub (public pages, model cards, papers)huggingface.co/models?author=zai-org&p=0&sort=downloads listingT2· Quality secondary4 h ago6
SWE-bench leaderboardsswebench.com/ leaderboardT2· Quality secondary8 h ago1
Artificial Analysisartificialanalysis.ai/leaderboards/models leaderboardT2· Quality secondary8 h ago1

Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.

Data quality (68/100) measures how well AI Atlas knows this entity — completeness, primary-source ratio, freshness, conflicts — never how good the model is. Methodology →