ModelPriceWatch.com
Last scan 2026-08-28 Models tracked 237 Providers 31 Cheapest paid Granite 4.0 H Micro $0.017/Mtok in Every price links to its source

GLM-5.3-Flash

by Z.AI · 320B (A18B) parameters

Current new · 3d Intro price budget open weights cheap tier

Today's price · per 1M tokens

Input

$0.075

per 1M tokens

Output

$0.250

per 1M tokens

Blended

$0.119

blended $/1M — 3:1 weighted input:output

Cached input

$0.015

20% of input — prompt caching

How this price is scoped: Launch/intro pricing, per 1M tokens. Z.AI's own rate card (docs.z.ai/guides/overview/pricing) prints both prices for this model, with the list price struck through: "GLM-5.3-Flash is available at a 50% discount (strikethrough prices are list prices). The promotion ends at 24:00 on September 9, 2026 (UTC+8, Singapore time)." That is input $0.15 -> $0.075, cached input $0.03 -> $0.015, output $0.50 -> $0.25. The figures shown here are the current effective discounted rates — what you would pay today. On 2026-09-10 they revert to the $0.15 / $0.015 cached / $0.50 list price, and we track that reversion as a price increase with its own reversion date so this row cannot quietly go stale. Cached-input STORAGE is separately labelled "Limited-time Free" with no end date, and is not a rate we publish. Checked live on the vendor's page twice, 2026-08-26 and 2026-08-27, identical both times; Z.AI has not extended the promotion.

Source: official Z.AI pricing · read Aug 27, 2026 MODELPRICEWATCH.COM · 2026-08-28

Price receipt

We read Z.AI's own pricing page on Aug 27, 2026 and found GLM-5.3-Flash listed with a price on the same row — that read is where the number above comes from, recorded as a new model. We keep the page text we read; its content hash is e52135daf4.

Overview

Z.AI's first natively multimodal GLM-5 model and a separate SKU from GLM-5.3, not a cheaper serving of it — 320B total / 18B activated, image input via image_url content blocks, 1M-token context. Currently $0.075/$0.25 per 1M tokens under a 50% launch discount that ends 2026-09-09; it reverts to the $0.15/$0.50 list price on 2026-09-10, with cached input going $0.015 -> $0.03. Weights are published under MIT at huggingface.co/zai-org/GLM-5.3-Flash.

Run it yourself

Deploy this open model on rented GPUs

Open weights mean you can self-host instead of paying per-token API prices. These platforms let you serve it on demand — often cheaper at scale.

Partner links — we may earn a commission if you sign up, at no cost to you. We only list platforms we'd recommend regardless.

Capabilities

struck through = not supported
Input 2/5
Text ✓ Image ✓ Audio Video PDF
Output 1/5
Text ✓ Image Audio Video Embedding
Features 4/9
Prompt caching ✓ Reasoning Coding Fast inference Long context ✓ Open weights ✓ Multimodal ✓ Web search Realtime

Benchmark performance

accuracy % · higher is better
Avg benchmark score69.8%
Perf per $/Mtok587.8
Terminal-Bench 2.1
84.3%
Humanity's Last Exam
55.3%
AutoBench *
48.8%
Independent composite scores
  • AA Intelligence Index: 57.5 (Artificial Analysis composite across reasoning, knowledge and coding evals)
  • AA Agentic Index: 58.2 (Tool use, planning, autonomy)
  • AA-Omniscience Index: 7.5 (−100–100)
  • GDPval-AA v2: 1763.8 ELO (Real-world work tasks, human baseline = 1000)
  • LMSYS Chatbot Arena: 1469.4 ELO (Human preference)
How it stacks up
  • Ranks #36 of 73 benchmarked models by average score
  • Ranks #8 of 170 comparably-measured models by percentile score, across 7 independent measurements
  • Ranks #2 of 170 comparably-tested models by normalized performance per dollar top value
  • Strongest at AutoBench — 48.8%, #1 of 9

Source: Vellum LLM Leaderboard · updated Aug 28, 2026 · See full rankings →

Specifications

Provider
Z.AI
Context window
1M tokens
Modality
text, image
Parameters
320B (A18B)
Open source
Yes — open weights available
Released
Aug 25, 2026
Status
Current
Last updated
Aug 27, 2026
Tags
open-weightsbudgetmultimodalcachinglong-context

Availability verified: Aug 27, 2026 — listed on Z.AI's own page