{"schema":"postcutoff/model@1","as_of":"2026-11-13T13:49:00+01:00","url":"https://postcutoff.com/m/glm-5-3/","md":"https://postcutoff.com/m/glm-5-3/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","name":"GLM-5.3","org":"Zhipu AI (Z.ai)","family":"GLM-5","released":"2026-08","status":"current","type":"reasoning-llm","modality_in":["text"],"modality_out":["text"],"open_weights":true,"model_license":"glm-5.3 (custom)","context_window":1000000,"max_output":128000,"knowledge_cutoff":null,"pricing":{"input":1.4,"output":4.4,"cache_read":0.26,"unit":"per 1M tokens (USD)","source":"https://docs.z.ai/guides/overview/pricing"},"price_line":"$1.40 in, $4.40 out per 1M tokens","access":[{"provider":"Z.ai API","model_id":"glm-5.3","endpoint":"https://api.z.ai/api/paas/v4","docs":"https://docs.z.ai/guides/llm/glm-5.3"},{"provider":"Z.ai API (Anthropic format)","model_id":"glm-5.3","endpoint":"https://api.z.ai/api/anthropic","docs":"https://docs.z.ai/guides/llm/glm-5.3"},{"provider":"Alibaba Cloud Model Studio","model_id":"ZHIPU/GLM-5.3","docs":"https://www.alibabacloud.com/help/en/model-studio/models"},{"provider":"OpenRouter","model_id":"z-ai/glm-5.3","url":"https://openrouter.ai/z-ai/glm-5.3"},{"provider":"Hugging Face","url":"https://huggingface.co/zai-org/GLM-5.3"},{"provider":"Baseten (GLM-5.3 Fast, speed-optimized)","model_id":"zai-org/GLM-5.3","endpoint":"https://inference.baseten.co/v1","docs":"https://www.baseten.co/library/glm-53-fast/"},{"provider":"Vercel AI Gateway (GLM 5.3 Fast; routed to Baseten or Alibaba; $2.10 in / $6.60 out)","url":"https://vercel.com/ai-gateway/models/glm-5.3-fast"},{"provider":"AWS Bedrock (GA Oct 5, 2026; prompt caching supported)","docs":"https://aws.amazon.com/about-aws/whats-new/2026/10/amazon-bedrock-glm-5-3/"},{"provider":"Web app","url":"https://chat.z.ai"}],"capabilities":[{"name":"Post-training-only jump in coding","detail":"Same base as GLM-5.2; Z.ai reports +50% on its Code Bench and open-model SOTA on Terminal Bench 3.0 and Agents' Last Exam (CLI).","first":false,"discovered":"launch","source":"https://docs.z.ai/guides/llm/glm-5.3"},{"name":"Emergent cyber capability","detail":"Best CyberGym vulnerability-discovery score to date per Z.ai; exploitation benchmark scores more than double GLM-5.2's.","first":false,"discovered":"launch","source":"https://docs.z.ai/guides/llm/glm-5.3"},{"name":"Always-on reasoning with effort levels","detail":"thinking.type disabled no longer allowed; reasoning_effort low/high/max (default max).","first":false,"discovered":"launch","source":"https://docs.z.ai/guides/llm/glm-5.3"},{"name":"Coding Plan integration","detail":"Available in the GLM Coding Plan (points-based; off-peak/weekend calls cost 50% points) for Claude Code, Cline, OpenCode etc.","first":false,"discovered":"launch","source":"https://docs.z.ai/guides/llm/glm-5.3"}],"entry":null,"notes":"Z.ai flagship. GLM 5.3 Fast (speed-optimized GLM-5.3 at $2.10 in / $0.21 cached / $6.60 out, 1M context, 262k max output per Vercel) appeared on Baseten and Vercel AI Gateway around Oct 7, 2026 (LLM Gateway timeline); it is not on Z.ai's own pricing page as of 2026-10-09 and no Z.ai announcement was found. Text-only input. Migration: requests with thinking disabled fail - set enabled + reasoning_effort low. Coding Plan base URL is https://api.z.ai/api/coding/paas/v4. Release day not verified (OpenRouter 2026-08-18, HF 2026-08-25). GLM-5.2 (same price, MIT weights) still listed. A speed-optimized 'GLM-5.3 Fast' API appeared on Oct 7, 2026 (LLM Gateway release timeline); Baseten lists it at $2.10 input / $0.21 cached / $6.60 output per 1M tokens, 753B-A40B, custom license; no Z.ai announcement or throughput figure found (unverified). GLM-5.3-Highspeed: seen on 2026-10-13 in a gray release inside ZCode 3.15.1 for randomly selected subscribers, about 490 tokens/s in one user's test (Pandaily citing QbitAI); not announced by Zhipu, no API id or price on docs.z.ai.","verified":"2026-10-13","body_md":"Z.ai's top model for long-horizon software engineering, terminal agents and security research; 1M context, 128K output.\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\",\"thinking\":{\"type\":\"enabled\"},\"reasoning_effort\":\"max\",\"messages\":[{\"role\":\"user\",\"content\":\"Hello\"}]}'\n```\n\nSources: https://docs.z.ai/guides/llm/glm-5.3 · https://docs.z.ai/guides/overview/pricing · https://huggingface.co/zai-org/GLM-5.3","page_url":"https://postcutoff.com/m/glm-5-3/","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/","briefings":null}