Zhipu AI model product
GLM 4.5 Air
5 Air is a compact MoE language model from Zhipu AI with 106 billion total parameters and 12 billion active parameters.
Updated Oct 23, 2026. Default version: GLM-4.5-Air
LLMBoard Score39.9GLM-4.5-Air
Coverage100%14 benchmark families
Context windowN/ATokens
Official input price$0.1195Zhipu AI API
GLM 4.5 Air Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
GLM 4.5 Air Benchmark Results
Benchmark scores for GLM-4.5-Air.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkAA-Index | Score64.80% | Rank02 | Participants4 | Percentile66.67% | EvidenceC | Evaluated |
| BenchmarkBFCL-v3 | Score76.40% | Rank02 | Participants20 | Percentile94.74% | EvidenceC | Evaluated |
| BenchmarkTAU-bench Airline | Score60.80% | Rank03 | Participants23 | Percentile90.91% | EvidenceC | Evaluated |
| BenchmarkMATH-500 | Score98.10% | Rank04 | Participants33 | Percentile90.63% | EvidenceC | Evaluated |
| BenchmarkTAU-bench Retail | Score77.90% | Rank07 | Participants25 | Percentile75.00% | EvidenceC | Evaluated |
| BenchmarkAIME 2024 | Score89.40% | Rank10 | Participants54 | Percentile83.02% | EvidenceC | Evaluated |
| BenchmarkTerminal-Bench | Score30.00% | Rank20 | Participants25 | Percentile20.83% | EvidenceC | Evaluated |
| BenchmarkLiveCodeBench | Score70.70% | Rank24 | Participants76 | Percentile69.33% | EvidenceC | Evaluated |
| BenchmarkSciCode | Score37.30% | Rank25 | Participants31 | Percentile20.00% | EvidenceC | Evaluated |
| BenchmarkAA AIME 2025 | Score80.67% | Rank34 | Participants96 | Percentile65.26% | EvidenceB | EvaluatedN/A |
| BenchmarkMMLU-Pro | Score81.40% | Rank51 | Participants142 | Percentile64.54% | EvidenceC | Evaluated |
| BenchmarkBrowseComp | Score21.30% | Rank69 | Participants70 | Percentile1.45% | EvidenceC | Evaluated |
| BenchmarkSWE-Bench Verified | Score57.60% | Rank94 | Participants120 | Percentile21.85% | EvidenceC | Evaluated |
| BenchmarkHumanity's Last Exam | Score10.60% | Rank98 | Participants109 | Percentile10.19% | EvidenceC | Evaluated |
| BenchmarkLM Arena Text Factuality | Score1,394.17 rating | Rank116 | Participants131 | Percentile11.54% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text | Score1,383.75 rating | Rank123 | Participants218 | Percentile43.78% | EvidenceA | Evaluated |
| BenchmarkGPQA | Score75.00% | Rank125 | Participants256 | Percentile51.37% | EvidenceC | Evaluated |
| BenchmarkAA GPQA Diamond | Score73.33% | Rank126 | Participants199 | Percentile36.87% | EvidenceB | EvaluatedN/A |
| BenchmarkAA IFBench | Score37.55% | Rank128 | Participants168 | Percentile23.95% | EvidenceB | EvaluatedN/A |
| BenchmarkAA LCR v1.1 | Score46.67% | Rank130 | Participants193 | Percentile32.81% | EvidenceB | EvaluatedN/A |
| BenchmarkLM Arena Text Style Control | Score1,373.07 rating | Rank140 | Participants218 | Percentile35.94% | EvidenceA | Evaluated |
| BenchmarkAA HLE Text No Tools | Score7.04% | Rank141 | Participants200 | Percentile29.65% | EvidenceB | EvaluatedN/A |
| BenchmarkAA Omniscience Accuracy | Score16.25% | Rank158 | Participants201 | Percentile21.50% | EvidenceB | EvaluatedN/A |
| BenchmarkAA CritPt | Score0.00% | Rank162 | Participants200 | Percentile19.10% | EvidenceB | EvaluatedN/A |
GLM 4.5 Air Arena Results
Preference and agent-evaluation results for the default version.
Sort by
Arena | Category | Rank | Rating / score | Votes | Observations | Result date |
|---|
| Arenatext | Categoryjapanese | Rank96 | Rating / score1,347.60 | Votes845 | ObservationsN/A | Result date |
| Arenatext | Categorygerman | Rank110 | Rating / score1,377.40 | Votes744 | ObservationsN/A | Result date |
| Arenatext | Categorypolish | Rank110 | Rating / score1,367.69 | Votes1,863 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry business and management and financial operations | Rank110 | Rating / score1,390.12 | Votes741 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry writing and literature and language | Rank110 | Rating / score1,374.21 | Votes972 | ObservationsN/A | Result date |
| Arenatext style control | Categoryjapanese | Rank111 | Rating / score1,329.36 | Votes845 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry medicine and healthcare | Rank112 | Rating / score1,401.60 | Votes1,645 | ObservationsN/A | Result date |
| Arenatext factuality | Categorymulti turn | Rank112 | Rating / score1,382.31 | Votes699 | ObservationsN/A | Result date |
| Arenatext factuality | Categorycoding | Rank115 | Rating / score1,429.88 | Votes874 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryenglish | Rank115 | Rating / score1,406.32 | Votes2,520 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryhard prompts english | Rank115 | Rating / score1,421.43 | Votes983 | ObservationsN/A | Result date |
| Arenatext | Categoryfrench | Rank116 | Rating / score1,399.56 | Votes520 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryexclude ties | Rank116 | Rating / score1,379.63 | Votes4,921 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryinstruction following | Rank116 | Rating / score1,377.20 | Votes1,189 | ObservationsN/A | Result date |
| Arenatext factuality | Categorynon english | Rank116 | Rating / score1,380.22 | Votes3,596 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryoverall | Rank116 | Rating / score1,394.17 | Votes7,280 | ObservationsN/A | Result date |
| Arenatext | Categorychinese | Rank117 | Rating / score1,426.29 | Votes2,236 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry life and physical and social science | Rank117 | Rating / score1,406.67 | Votes4,923 | ObservationsN/A | Result date |
| Arenatext factuality | Categorylonger query | Rank117 | Rating / score1,384.11 | Votes1,091 | ObservationsN/A | Result date |
| Arenatext | Categoryspanish | Rank120 | Rating / score1,385.46 | Votes824 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryhard prompts | Rank120 | Rating / score1,405.08 | Votes3,560 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry software and it services | Rank120 | Rating / score1,417.24 | Votes1,516 | ObservationsN/A | Result date |
| Arenatext | Categoryenglish | Rank122 | Rating / score1,397.35 | Votes13,222 | ObservationsN/A | Result date |
| Arenatext | Categoryrussian | Rank122 | Rating / score1,372.52 | Votes2,005 | ObservationsN/A | Result date |
| Arenatext | Categoryexclude ties | Rank123 | Rating / score1,357.62 | Votes21,541 | ObservationsN/A | Result date |
| Arenatext | Categorynon english | Rank123 | Rating / score1,366.21 | Votes17,407 | ObservationsN/A | Result date |
| Arenatext | Categoryoverall | Rank123 | Rating / score1,383.75 | Votes30,671 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry business and management and financial operations | Rank124 | Rating / score1,370.59 | Votes5,505 | ObservationsN/A | Result date |
| Arenatext | Categorymath | Rank124 | Rating / score1,395.54 | Votes1,528 | ObservationsN/A | Result date |
| Arenatext | Categorycreative writing | Rank125 | Rating / score1,343.08 | Votes4,004 | ObservationsN/A | Result date |
GLM 4.5 Air Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- $0.1195 input, $0.8964 output per 1M
- Official provider
- Zhipu AI
- Lowest third-party
- From $0.10 input, $0.50 output per 1M via submodel
- Tracked offerings
- 16
Sort by
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| Providersubmodel | Provider model IDzai-org/GLM-4.5-Air | Regionglobal | Input / 1M$0.10 | Output / 1M$0.50 | Context131.1K | Updated |
| ProviderZenMux | Provider model IDz-ai/glm-4.5-air | Regionglobal | Input / 1M$0.1165 | Output / 1M$0.2911 | Context128K | Updated |
| ProviderZhipu AI | Provider model IDglm-4.5-air | Regionglobal | Input / 1M$0.1195 | Output / 1M$0.8964 | Context131.1K | Updated |
| ProviderNanoGPT | Provider model IDz-ai/GLM-4.5-Air | Regionglobal | Input / 1M$0.12 | Output / 1M$0.80 | Context128K | Updated |
| ProviderHugging Face | Provider model IDzai-org/GLM-4.5-Air | Regionglobal | Input / 1M$0.13 | Output / 1M$0.85 | Context131.1K | Updated |
| ProviderOpenRouter | Provider model IDz-ai/glm-4.5-air | Regionglobal | Input / 1M$0.13 | Output / 1M$0.85 | Context131.1K | Updated |
| ProviderNovita AI | Provider model IDzai-org/glm-4.5-air | Regionglobal | Input / 1M$0.13 | Output / 1M$0.85 | Context131.1K | Updated |
| ProviderKilo Gateway | Provider model IDz-ai/glm-4.5-air | Regionglobal | Input / 1M$0.13 | Output / 1M$0.85 | Context131.1K | Updated |
| ProviderOrcaRouter | Provider model IDz-ai/glm-4.5-air | Regionglobal | Input / 1M$0.20 | Output / 1M$1.1 | Context131.1K | Updated |
| ProviderImpossibl | Provider model IDzai/glm-4.5-air | Regionglobal | Input / 1M$0.20 | Output / 1M$1.1 | Context131.1K | Updated |
| ProviderZ.AI | Provider model IDglm-4.5-air | Regionglobal | Input / 1M$0.20 | Output / 1M$1.1 | Context131.1K | Updated |
| ProviderMerge Gateway | Provider model IDzai/glm-4.5-air | Regionglobal | Input / 1M$0.20 | Output / 1M$1.1 | Context128K | Updated |
| ProviderVercel AI Gateway | Provider model IDzai/glm-4.5-air | Regionglobal | Input / 1M$0.20 | Output / 1M$1.1 | Context128K | Updated |
| ProviderDevPass (LLM Gateway) | Provider model IDglm-4.5-air | Regionglobal | Input / 1M$0.20 | Output / 1M$1.1 | Context131K | Updated |
| ProviderTempr Gateway | Provider model IDzai/glm-4.5-air | Regionglobal | Input / 1M$0.20 | Output / 1M$1.1 | Context131.1K | Updated |
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
GLM 4.5 Air Runtime Performance
Provider-specific output speed and catalog latency for GLM-4.5-Air. Runtime does not affect the capability score.
No runtime data
No provider-specific speed or latency record is linked to the default version yet.
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
GLM 4.5 Air Specifications
Technical details for the model's default version.
- Version
- GLM-4.5-Air
- Released
- Jul 28, 2025
- Knowledge cutoff
- Unknown
- Parameters
- 106B
- Context window
- N/A
- Max output
- N/A
- Inputs
- text
- Outputs
- text
- Open weights
- Yes
- License
- MIT
GLM 4.5 Air Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
Sort by
Version | Released | LLMBoard | Parameters | Context | Max output | Open weights | License |
|---|
| VersionGLM-4.5-Air | Released | LLMBoard39.90 | Parameters106B | ContextN/A | Max outputN/A | Open weightsYes | LicenseMIT |
Models similar to GLM 4.5 Air
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
ZA
GLM 4.7 Flash
Zhipu AI
ZA
GLM 4.5
Zhipu AI
ZA
GLM 4.6
Zhipu AI
ZA
GLM 5V Turbo
Zhipu AI
ZA
GLM 4.7
Zhipu AI
ZA
GLM 5
Zhipu AI
What is GLM 4.5 Air?
Key information about GLM 4.5 Air and its available data.
5 Air is a hybrid reasoning model for Agentic, Reasoning, and Coding applications, with thinking and non-thinking modes, tool usage, and a 128K context length. 8 across 12 industry-standard benchmarks, ranking 6th overall.
Data as of 2026-10-22.
FAQ
Common questions about GLM 4.5 Air.
When was GLM 4.5 Air released?
GLM 4.5 Air's default version was released on Jul 28, 2025.
How much does GLM 4.5 Air cost?
GLM 4.5 Air's official API price is $0.1195 per million input tokens and $0.8964 per million output tokens via Zhipu AI. The lowest tracked third-party offer starts at $0.10 input and $0.50 output via submodel.
Who created GLM 4.5 Air?
GLM 4.5 Air was created by Zhipu AI.
What is the context window for GLM 4.5 Air?
A context window is not available for the default version.
Is GLM 4.5 Air open weight?
Yes. The default version is marked as open weight under MIT.
How many API providers offer GLM 4.5 Air?
16 provider offerings are linked to the default version.