GLM-4.5-Air
GLM-4.5 and GLM-4.5-Air are our latest flagship models, purpose-built as foundational models for agent-oriented applications.
text → text · made by Z.ai
Sold by 16 ways
| Seller | Lane | Rate |
|---|---|---|
| Z.ai 0 ways | $0.2per Mtok in$1.1per Mtok out$0.03per Mtok cached | |
| Z.ai apinot on the seller's list today | standard | $0.2per Mtok in$1.1per Mtok out$0.03per Mtok cacheddocs.z.ai · read 2026-10-20 |
| Hugging Face Inference Providers 2 ways | $0.13per Mtok in$0.85per Mtok out | |
| Hugging Face Inference Providers aggregator | standard | $0.13per Mtok in$0.85per Mtok outmodels.dev · read 2026-11-01 |
| Hugging Face Inference Providers aggregator | novita | $0.13per Mtok in$0.85per Mtok outrouter.huggingface.co · read 2026-08-25 |
| Nous Research aggregator | standard | $0.13per Mtok in$0.85per Mtok out$0.025per Mtok cachedinference-api.nousresearch.com · read 2026-09-12 |
| Novita AI aggregator | standard | $0.13per Mtok in$0.85per Mtok out$0.025per Mtok cachedapi.novita.ai · read 2026-08-25 |
| OpenRouter 4 ways | $0.13per Mtok in$0.85per Mtok out$0.025per Mtok cached | |
| OpenRouter aggregator | standard | $0.13per Mtok in$0.85per Mtok out$0.025per Mtok cachedopenrouter.ai · read 2026-08-24 |
| OpenRouter aggregator | novita/bf16 | $0.13per Mtok in$0.85per Mtok out$0.025per Mtok cachedopenrouter.ai · read 2026-11-01 |
| OpenRouter aggregator | siliconflow/fp8 | $0.14per Mtok in$0.86per Mtok outopenrouter.ai · read 2026-08-25 |
| OpenRouter aggregator | z-ai/fp8 | $0.2per Mtok in$1.1per Mtok out$0.03per Mtok cachedopenrouter.ai · read 2026-08-25 |
| SiliconFlow aggregator | standard | $0.14per Mtok in$0.86per Mtok outmodels.dev · read 2026-11-01 |
| DeepInfra aggregator | standard | $0.2per Mtok in$1.1per Mtok outapi.deepinfra.com · read 2026-08-25 |
| ElectronHub aggregator | standard | $0.2per Mtok in$1.1per Mtok outapi.electronhub.ai · read 2026-11-01 |
| Requesty aggregator | deepinfra | $0.2per Mtok in$1.1per Mtok out$0.2per Mtok cachedrouter.requesty.ai · read 2026-08-28 |
| Vercel AI Gateway aggregator | standard | $0.2per Mtok in$1.1per Mtok out$0.03per Mtok cachedai-gateway.vercel.sh · read 2026-08-25 |
| Fireworks AI aggregator | standard | $0.22per Mtok in$0.88per Mtok outraw.githubusercontent.com · read 2026-11-01 |
| PPIO aggregator | standard | $1.2per Mtok in$2per Mtok outapi.ppinfra.com · read 2026-11-01 |
Measured 11 standings
| Place | Board | Metric | Score |
|---|---|---|---|
| 37thof 56 | Humanity's Last Exam (Epoch AI replication) | Accuracy | 8.12 |
| 39thof 42 | Gso — Epoch AI | Score OPT@1 | 0.029 |
| 65thof 92 | Forecastbench — Epoch AI | Overall score | 62 |
| 89thof 154 | Design Arena · dataviz (models) | Elo | 1186 |
| 97thof 114 | Design Arena · svg (models) | Elo | 1068 |
| 102ndof 150 | Design Arena · 3d (models) | Elo | 1120 |
| 117thof 157 | Design Arena · uicomponent (models) | Elo | 1118 |
| 121stof 169 | Design Arena · website (models) | Elo | 1145 |
| 123rdof 163 | Design Arena · codecategories (models) | Elo | 1135 |
| 127thof 162 | Design Arena · gamedev (models) | Elo | 1094 |
| 194thof 414 | LMArena · Text | Score (Elo) | 1373 |
About
GLM-4.5-Air — a text model from Z.ai, sold by 11 companies from $0.13 in and $0.85 out per million tokens, placed 194th of 414 on LMArena · Text.
It takes text and returns text, with a context window of 128,000 tokens. It was published in July 2025, trained on material up to April 2025. Its sellers say it can reason step by step and call a tool. The catalogue files it under reasoning and agents. Eleven companies sell it. The cheapest is $0.13 in and $0.85 out per million tokens at Hugging Face Inference Providers. Beside the standard rate there are separately routed and regional lanes. It has been measured on 11 boards, and stands best at 194th of 414 on LMArena · Text.
Every current figure
- Maker
- Z.ai
- Register
- model
- Takes
- text
- Returns
- text
- Context
- 128,000 tokens
- Published
- July 2025
- Knowledge to
- April 2025
- Parameters
- 110 billion
- Licence
- not read
- Sellers
- 11
- Price
- $0.13 in and $0.85 out per million tokens — Hugging Face Inference Providers
- Boards
- 11
- Best place
- 194th of 414 — LMArena · Text
Known as 4 names
zai-org/GLM-4.5-Airz-ai/glm-4.5-airdeepinfra/zai-org/GLM-4.5-Airzai/glm-4.5-air