← the radar · ✳ model tracker
GLM-5.3 Flash
● liveLive - $0.075/$0.25 per 1M; 1.31M ctx; open weights on HF Aug 25; shipped first as the stealth id ox-alpha, which our sweep read FREE at ~1.05M ctx across three gateways Aug 20-21; that Z.ai confirmed the stealth run was this model on Aug 26 is search-grade, not our own reading. On the board as live since 2026-08-26 — the watchers keep tracking it: lineup changes, pricing moves and deprecations all alert.
Answering in 0.6s· checked Live model status →
Watch for Zhipu AI’s next model, free →Launch report (PDF)
Timeline
On the bench index
Coding leaderboard
#14 of 35 on the coding index, at 55.9 · combines LMArena · Coding, LiveBench · Coding, Vals Vibe Code Bench
Open weights
#1 of 8 open-weights models on the Bench Index · zai-org/GLM-5.3-Flash on Hugging Face · 321B parameters · license MIT
Where to use GLM-5.3 Flash
72 providers list GLM-5.3 Flash in the models.dev catalog (as of 2026-10-11), under the model ids shown below.
glm-5.3-flash · glm-5.3-flashxglm-5.3-flash · glm-5.3-flashxz-ai/glm-5.3-flash · z-ai/glm-5.3-flashxzai/glm-5.3-flash · zai/glm-5.3-flashxglm-5.3-flashglm-5.3-flashzai-org/glm-5.3-flashcoding-glm-5.3-flash-free · glm-5.3-flashzai-org/GLM-5.3-Flashzai-org/GLM-5.3-Flashglm-5.3-flashglm-5.3-flashAlso listed by ClinePass, Cloudflare Workers AI, CoreWeave, Cortecs, CrofAI, CrossModel, Deep Infra, DevPass (LLM Gateway), DigitalOcean, Eden AI, EmpirioLabs AI, engy, Fireworks AI, Friendli, GreenPT, Hugging Face, Inco, IteraCompute, Kenari, Kilo Gateway, LLM Gateway, Melious, Merge Gateway, Modal, NaN, NanoGPT, NEAR AI Cloud, Nebius Token Factory, Neon, Neuralwatt, Novita AI, Nvidia, Ofox, Ollama Cloud, OpenCode Go, OpenCode Zen, Opper, OrcaRouter, Pareto Inference, Privatemode AI, Requesty, RunInfra, SCNet Token Plan, SiliconFlow, Synthetic, Tempr Gateway, TensorX, Together AI, TokenGo, Umans AI, Umans AI Coding Plan, Vancine, Venice AI, Vivgrid, Volcengine Ark, Volcengine Ark Coding Plan, Vultr, Z.AI Coding Plan, ZenMux, Zhipu AI Coding Plan.
Listings cover the model family, so a provider may list a sibling tier under the same name. Check the id before you build on it.
GLM-5.3 Flash: quick answers
Is GLM-5.3 Flash out?
Yes. GLM-5.3 Flash is live and has been since August 26, 2026.
When was GLM-5.3 Flash released?
August 26, 2026.
Is GLM-5.3 Flash good for coding?
On the ArtificialWatch coding index it scores 55.9, #14 of 35 ranked models. The index combines LMArena · Coding, LiveBench · Coding and Vals Vibe Code Bench, taking the median of each model's percentile across them.
Is GLM-5.3 Flash open source?
It has open weights: the trained model is public on Hugging Face as zai-org/GLM-5.3-Flash, 321B parameters as Hugging Face counts them, license MIT. Among the 8 open-weights models the ArtificialWatch Bench Index ranks, it is #1.
Who makes GLM-5.3 Flash?
Zhipu AI. ArtificialWatch also tracks GLM-5.3, GLM-5.2, GLM-5.5 and GLM-6 from Zhipu AI.
Where can I use GLM-5.3 Flash?
72 providers list it in the models.dev catalog, including Z.AI, Zhipu AI, OpenRouter, Vercel AI Gateway and 302.AI. The exact model ids each one lists are on this page.
How much does GLM-5.3 Flash cost?
Z.AI's own API lists GLM-5.3 Flash (glm-5.3-flash) at $0.15 per million input tokens and $0.50 per million output tokens, and $0.03 per million cached input tokens. Prices as published in the models.dev catalog, as of 2026-10-11.
What is GLM-5.3 Flash's context window?
1M tokens, with up to 131K output tokens per response, as Z.AI lists GLM-5.3 Flash (glm-5.3-flash).
Is GLM-5.3 Flash open weights?
Yes. GLM-5.3 Flash is released with open weights.
Head to head
More from Zhipu AI
Know the minute Zhipu AI's next model drops. Free.
A free Chrome push the second it's confirmed on a public API, email about 15 minutes later. Texts or a phone call on paid plans.
- Free forever
- No card
- Unsubscribe in one click
Also: the wire · the bench index · our track record