Skip to content
ModelCap

GLM 4.5 Air

Current board #50Arena #169Open weights

Z.ai·z-ai/glm-4.5-air

GLM 4.5 Air is a language model published by Z.ai. 3 OpenRouter endpoints are published in the latest snapshot. It accepts text input and returns text. The published context limit is 131K tokens. The catalogue declares support for reasoning, tool use.

ModelCap Index · Current board
56.3#50
Measured · 83% support · score interval 56.3–62.9
Market Gravity
29.9
Secondary market signal
Input
$0.13
per 1M tokens
Output
$0.85
per 1M tokens
Context
131K
tokens
Providers
3
endpoints
Gateway spend
—
latest · Vercel share

Providers

Uptime measured over the last 30 minutes
ProviderInputOutputContextQuantUptime
Novitabf16Cheapest$0.13$0.85131Kbf1699.94%
SiliconFlowfp8$0.14$0.86131Kfp8100.0%
Z.AIfp8$0.20$1.10131Kfp899.59%

Hugging Face Inference Providers

Exact repository identity

Provider economics and telemetry published by the Hugging Face Router. These are operational signals, not benchmark results.

ProviderInputOutputContextTTFTThroughputFeatures
novita
live
$0.13$0.85131K595 ms51.2 tok/stools
zai-org
live · model author
———1840 ms64.5 tok/stools

Reported evaluation leads (3)

Excluded from score

Structured rows reported in this exact model repository at the pinned revision below. They are useful research leads, but remain quarantined until dataset revision, harness, configuration and identity pass ModelCap’s independent admission review.

Dataset / taskMetricValueRevisionProvenance
cais/hle
none
—8.12
Unpinned
not published
Reported
Quarantined
Idavidrein/gpqa
diamond
—71.7172
Unpinned
not published
Reported
Quarantined
TIGER-Lab/MMLU-Pro
mmlu_pro
—81.4
Unpinned
not published
Reported
Quarantined

ModelCap Index · Current board

Methodology
56.3
Measured · 2 public benchmark observations across 2 boards
Current board
#50
Public rank basis
Measured (measured)
Index support
83.3% · strong
Index interval
56.3–62.9
Rank posterior
Not available
Top 5 / Top 10 probability
Not available / Not available
Posterior as of
Snapshot timestamp unavailable
Identity binding
Exact catalogue product · z-ai/z-ai/glm-4.5-air · aggregates disclosed benchmark configurations · endpoint configuration not claimed · artifact metadata zai-org/GLM-4.5-Air@a24ceef6ce4f3536971efe9b778bdaa1bab18daa (not the evaluation revision)
Direct benchmark observations
2
Breadth-adjusted BES point estimate
59.6
Bayesian Evidence Score · measured evidence input only

BES normalizes admitted public benchmark evidence for measured Index rows. Its legacy score and observables prior do not define the public language rank.

Observed capability
59.6
Evidence status
confirmed · 83% mass
General preference
59.3
Coding
60.7
Agents & tools
—
Reasoning
—
Evidence breadth
92%
Evidence coverage
83%
Market and catalogue signals · secondary, never the language Index rank
Usage (OpenRouter popularity)
15.4
Liquidity (providers × uptime)
51.4
Open reach (HF downloads)
49.3
Surface (context / tools / modalities)
70.2
Freshness
23.7
  • · OpenRouter popularity #124
  • · 3 live providers
  • · HF 30d downloads 390160
  • · Catalogue: context 131072, reasoning, tools
  • · First seen 2025-07-25

These adoption and deployment observations remain context only. They do not change this model's ModelCap Index score or rank.

BES evidence selected · measured input only

The bounded 0–100 capability score blends each source’s competitive placement with its published achievement, then combines capability families. Evidence breadth adds a modest uncertainty adjustment; price and popularity are not part of benchmark-led rank.

Deployment readiness

Metadata index
83.1
strong · 94% metadata coverage
Not capability
Artifact reproducibility
85.0
Access & legal clarity
100.0
Deployability
90.2
Evaluation provenance
52.5

Missing: artifactReproducibility.base-lineage, evaluationProvenance.evaluation-dataset-revisions.

A metadata completeness and deployability index—not a safety certification, quality grade, or production-readiness claim.

Market activity

Venue coverage
Market Gravity
29.9
OpenRouter weekly popularity
#124 of 298

Market Gravity uses OpenRouter’s full-catalogue popularity order. Sparse Vercel top-ten observations appear only when published and do not affect the score.

Arena preference

Status
Ranked
Source
Arena
Official rank
#169 of 385
Rating
1372.7
95% confidence interval
1368–1377
Votes
31K
Source snapshot
6 Aug 2026, 13:00 UTC
Category
overall
Identity match confidence
100%

Market Gravity breakdown

Usage55%
15.4

OpenRouter weekly popularity across the full model catalogue.

Liquidity25%
51.4

Independent providers versus the model's open or closed cohort, weighted by uptime.

Open reach15%
49.3

Hugging Face 30-day downloads for open models; neutral for closed models.

Freshness5%
23.7

Time since first public availability, on a six-month half-life.

Specification

Context window
131K tokens
Max output
98K tokens
Inputs
Text
Outputs
Text
Tokenizer
Other
Cached input tokens
$0.025 / 1M
First seen on OpenRouter
25 Jul 2025
Knowledge cutoff
2024-12-31

Capabilities

  • Supported: Reasoning
  • Supported: Tool use
  • Not supported: Structured output
  • Not supported: Response format
  • Not supported: Moderated

Weights & access

Open weights. Downloadable weights are published under an OSI or free-culture license in the current repository metadata. This describes weight availability, not whether the full training stack qualifies as Open Source AI.

Access
Open weights
Licence
mit
Pinned revision
a24ceef6ce4f
Parameters
110.5B
Architecture
Glm4MoeForCausalLM
Model type
glm4_moe
Hugging Face downloads (30d)
390K
Downloads (all time)
4.5M
Likes
629
Repository
zai-org/GLM-4.5-Air
Repository updated
11 Aug 2025, 13:25 UTC