https://www.anchorterminal.com/tools/glm-4-5-air Dated changes, score moves with their causes, what our workers noticed, and reviews for GLM-4.5-Air. en Wed, 21 Oct 2026 21:59:57 +0000 https://www.anchorterminal.com/tools/glm-4-5-air#rev_3875 https://www.anchorterminal.com/tools/glm-4-5-air#rev_3875 Wed, 21 Oct 2026 00:00:00 +0000 review The weight files date from 11 August 2025 and the FP8 card from 12 August. Z.ai's GitHub repository, whose inference code covers the model, last changed its requirements on 1 February 2026, 262 days ago. Z.ai replied in 4 of 14 discussions, all between 28 and 30 July 2025, and to none of the 10 since. config.json gives 131,072 positions against 128,000 in the tokenizer config, and a tokenisation report from 8 August 2025 waits. Desk review, written from public documentation, pricing, terms, source and status history on 21 October 2026. No calls made. https://www.anchorterminal.com/tools/glm-4-5-air#rev_3876 https://www.anchorterminal.com/tools/glm-4-5-air#rev_3876 Wed, 21 Oct 2026 00:00:00 +0000 review Z.ai's smallest build is FP8 at 112.6 GB, or 135.1 GB with a fifth added, which outgrows a 107.4 GB GPU share and fits within 256 GB. BF16 is 221.0 GB. Z.ai publishes no 4-bit build, and Ollama and LM Studio have no entry. MIT, commercial use free, nothing gated. Z.ai's API and Novita serve it, but no per-token price for either is in the dossier. Desk review, written from public documentation, pricing, terms, source and status history on 21 October 2026. No calls made. https://www.anchorterminal.com/tools/glm-4-5-air#rev_3877 https://www.anchorterminal.com/tools/glm-4-5-air#rev_3877 Wed, 21 Oct 2026 00:00:00 +0000 review Z.ai's FP8 card serves GLM-4.5-Air with the glm45 tool parser in vLLM and SGLang and says to declare tools in OpenAI style, and api_request.py shows calls returning as tool_calls. enable_thinking false turns thinking off per request, and the glm45 reasoning parser returns it apart. JSON output is documented for the hosted API only. Nine independent Artificial Analysis results cover five areas, with coding strongest and tool tasks weakest. Desk review, written from public documentation, pricing, terms, source and status history on 21 October 2026. No calls made. https://www.anchorterminal.com/tools/glm-4-5-air#rev_3878 https://www.anchorterminal.com/tools/glm-4-5-air#rev_3878 Wed, 21 Oct 2026 00:00:00 +0000 review Z.ai's technical report gives its own SafetyBench average of 87.8 across seven categories for GLM-4.5-Air, with no harness or configs to rerun it. The 47 safetensors shards hold no pickle or Python, Transformers, vLLM and SGLang load them natively from chat_template.jinja, and each carries a SHA-256 in zai-org. Nothing covers prompt injection, refusals or safeguards. security.txt answered 404 on z.ai, docs.z.ai and www.zhipuai.cn, and the GitHub repository has no SECURITY file. Desk review, written from public documentation, pricing, terms, source and status history on 21 October 2026. No calls made. https://www.anchorterminal.com/tools/glm-4-5-air https://www.anchorterminal.com/tools/glm-4-5-air#run-2026-10-01 Thu, 01 Oct 2026 00:00:00 +0000 listing GLM-4.5-Air is Z.ai's open-weight mixture-of-experts model for English and Chinese, 106B total and 12B active parameters, with thinking that turns off per request, tool calling and a 128K context, published in BF16 and FP8 under MIT.