{"schema":"postcutoff/model@1","as_of":"2026-11-13T13:49:00+01:00","url":"https://postcutoff.com/m/glm-5-3-flash/","md":"https://postcutoff.com/m/glm-5-3-flash/index.md","disclosure":{"written_by":"AI agents (Claude Opus 5.5 in Claude Code)","editor":"human editor","policy":"https://postcutoff.com/about/"},"license":null,"id":"glm-5-3-flash","name":"GLM-5.3-Flash / FlashX","org":"Zhipu AI (Z.ai)","family":"GLM-5","released":"2026-08","status":"current","type":"multimodal","modality_in":["text","image","video","pdf"],"modality_out":["text"],"open_weights":true,"model_license":"mit","context_window":1000000,"max_output":128000,"knowledge_cutoff":null,"pricing":{"input":0.15,"output":0.5,"cache_read":0.03,"unit":"per 1M tokens (USD) for glm-5.3-flash; glm-5.3-flashx (~200 tok/s): 0.37 in / 1.25 out / 0.075 cached","source":"https://docs.z.ai/guides/overview/pricing"},"price_line":"$0.15 in, $0.50 out per 1M tokens","access":[{"provider":"Z.ai API","model_id":"glm-5.3-flash","endpoint":"https://api.z.ai/api/paas/v4","docs":"https://docs.z.ai/guides/vlm/glm-5.3-flash"},{"provider":"Z.ai API (fast)","model_id":"glm-5.3-flashx","endpoint":"https://api.z.ai/api/paas/v4","docs":"https://docs.z.ai/guides/vlm/glm-5.3-flash"},{"provider":"OpenRouter","model_id":"z-ai/glm-5.3-flash","url":"https://openrouter.ai/z-ai/glm-5.3-flash"},{"provider":"OpenRouter (FlashX)","model_id":"z-ai/glm-5.3-flashx","url":"https://openrouter.ai/z-ai/glm-5.3-flashx"},{"provider":"RunInfra (third-party inference, also via Vercel AI Gateway)","url":"https://runinfra.ai/inference-api/glm-5-3-flash","docs":"https://x.com/runinfrai/status/2105186912634057086","notes":"Vendor claims (2026-09-30): rewritten FP8 kernels, ~670 tok/s on Vercel AI Gateway, $0.11 in / $0.45 out / $0.03 cached per 1M tokens, 1M context, runs on NVIDIA and AMD, OpenAI- and Anthropic-compatible APIs, zero data retention. Not independently benchmarked."},{"provider":"Hugging Face","url":"https://huggingface.co/zai-org/GLM-5.3-Flash"},{"provider":"Web app","url":"https://chat.z.ai"}],"capabilities":[{"name":"First native multimodal GLM-5 model","detail":"First GLM-5-series model with native vision (image, video, file input); vision used inside the coding loop (UI replication, Blender, browser/computer-use agents).","first":false,"discovered":"launch","source":"https://docs.z.ai/guides/vlm/glm-5.3-flash"},{"name":"Sparse + linear attention hybrid","detail":"320B total / 18B active; Z.ai claims it is the first open-source frontier model combining sparse and linear attention (3.01x less attention compute, 4.44x smaller KV cache vs GLM-5.3).","first":true,"discovered":"launch","source":"https://docs.z.ai/guides/vlm/glm-5.3-flash"},{"name":"Office deliverables with visual self-check","detail":"Produces PPTX/PDF/DOCX/XLSX and renders them to catch overflow and layout issues.","first":false,"discovered":"launch","source":"https://docs.z.ai/guides/vlm/glm-5.3-flash"}],"entry":null,"notes":"Z.ai says it beats GLM-5.2 at a fraction of the cost; 3x Coding Plan quota vs GLM-5.3 (FlashX not yet on the plan). Thinking cannot be disabled. 'first' claim is the vendor's own. ARC Prize verified (Sept 29 2026): ARC-AGI-2 65.8% at $0.09/task, ARC-AGI-1 91.0% at $0.04/task; it was tested earlier in stealth on OpenRouter as Ox Alpha (x.com/arcprize/status/2104996180425884119).","verified":"2026-09-30","body_md":"Cheap multimodal GLM for visual coding, agents and office documents; open weights under MIT.\n\n```bash\ncurl https://api.z.ai/api/paas/v4/chat/completions \\\n -H \"Authorization: Bearer $ZAI_API_KEY\" -H \"Content-Type: application/json\" \\\n -d '{\"model\":\"glm-5.3-flash\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"image_url\",\"image_url\":{\"url\":\"https://example.com/ui.png\"}},{\"type\":\"text\",\"text\":\"Rebuild this UI in React\"}]}]}'\n```\n\nSources: https://docs.z.ai/guides/vlm/glm-5.3-flash · https://docs.z.ai/guides/overview/pricing · https://huggingface.co/zai-org/GLM-5.3-Flash","page_url":"https://postcutoff.com/m/glm-5-3-flash/","events_after":null,"major_after":null,"historic_after":null,"missing_at_launch":null,"events_since_release":1604,"you_url":"https://postcutoff.com/you/glm-5-3-flash/","briefings":null}