Post-Cutoff
Search For AI agents

Zhipu AI (Z.ai)GLM-5 familyCurrentMultimodal modelReleased Aug 2026

GLM-5.3-Flash / FlashX

Cheap multimodal GLM for visual coding, agents and office documents; open weights under MIT.

Model idglm-5.3-flash

Price$0.15 in, $0.50 out per 1M tokens

Checked30 September 2026

No published training cutoff

At least1,604events since its release in August 2026

72 historic, 356 major. 74 days of news.

Zhipu AI (Z.ai) doesn’t publish a training cutoff, so we count from its release date. The real gap is larger.

Five things it has never heard of

How to call it

7 ways to use GLM-5.3-Flash / FlashX, with the model id each provider expects.

Providers, model ids, endpoints and docs for GLM-5.3-Flash / FlashX
ProviderModel idEndpointDocs
Z.ai API glm-5.3-flash https://api.z.ai/api/paas/v4 docs.z.ai
Z.ai API (fast) glm-5.3-flashx https://api.z.ai/api/paas/v4 docs.z.ai
OpenRouter z-ai/glm-5.3-flash openrouter.ai
OpenRouter (FlashX) z-ai/glm-5.3-flashx openrouter.ai
RunInfra (third-party inference, also via Vercel AI Gateway)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. x.com
runinfra.ai
Hugging Face huggingface.co
Web app chat.z.ai

Pricing

Prices for GLM-5.3-Flash / FlashX
Input$0.15 per 1M tokens
Output$0.50 per 1M tokens
Cache read$0.03 per 1M tokens

As published: “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: docs.z.ai, checked 30 September 2026.

Specs

Input
Text, images, video and PDF
Output
Text
Context window
1,000,000 tokens
Max output
128,000 tokens
Open weights
Yes
Licence
MIT
Training cutoff
Not published
Released
August 2026
Status
Current
Type
Multimodal model

What stands out

What its maker marketed at launch, and what people found later, each with its source.

  • First native multimodal GLM-5 model

    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).

    Source: docs.z.ai

  • Sparse + linear attention hybrid

    First

    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).

    Source: docs.z.ai

  • Office deliverables with visual self-check

    Produces PPTX/PDF/DOCX/XLSX and renders them to catch overflow and layout issues.

    Source: docs.z.ai

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).

curl https://api.z.ai/api/paas/v4/chat/completions \
 -H "Authorization: Bearer $ZAI_API_KEY" -H "Content-Type: application/json" \
 -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"}]}]}'

Sources: 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