ModelPriceWatch.com
Last scan 2026-09-05 Models tracked 248 Providers 32 Cheapest paid Granite 4.0 H Micro $0.017/Mtok in Every price links to its source

GLM-5.3

by Z.AI

Current new · 22d flagship open weights mid tier

Today's price · per 1M tokens

Input

$1.40

per 1M tokens

Output

$4.40

per 1M tokens

Blended

$2.15

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

Cached input

$0.260

19% of input — prompt caching

Source: official Z.AI pricing · read MODELPRICEWATCH.COM · 2026-09-05

Price receipt

We read Z.AI's own pricing page on and found GLM-5.3 listed with a price on the same row — that read is where the number above comes from. We keep the page text we read; its content hash is aac79925f8.

Available on 3 hosts

cheapest blended first · $ per 1M tokens

GLM-5.3 is sold by 3 providers. Prices are per 1M tokens (blended = (3×input + 1×output) ÷ 4). The first-party row is the model maker; “vs first-party” shows each host’s blended price relative to it.

GLM-5.3 price on every host still selling it, per 1M tokens, cheapest blended first
Host Input Output Blended vs first-party
Fireworks details → $1.40 $4.40 $2.15 0%
Together details → $1.40 $4.40 $2.15 0%
Z.AI first-party $1.40 $4.40 $2.15
Each host links to its provider page and official pricing. Prices refresh twice daily. MODELPRICEWATCH.COM · 2026-09-05

Overview

Z.AI's flagship open-weights model — a post-trained upgrade of GLM-5.2 (same MoE base) with major gains in coding and long-horizon agentic work. Text-only, 1M-token context, 128K max output; reasoning is always on with selectable effort. $1.40/$4.40 per 1M tokens; cached input $0.26. Weights are published at huggingface.co/zai-org/GLM-5.3 (with a BF16 twin), under the GLM-5.3 License.

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 1/5
Text Image Audio Video PDF
Output 1/5
Text Image Audio Video Embedding
Features 3/9
Prompt caching Reasoning Coding Fast inference Long context Open weights Multimodal Web search Realtime

Benchmark performance

accuracy % · higher is better
Percentile vs all tracked models 87.9th4 independent measurements
Percentile per $/Mtok 40.9

We hold no per-benchmark accuracy scores for this model yet, so it has no accuracy average. That is a gap in our coverage, not a sign the model is untested — independent evaluators often publish a composite index for a new model long before releasing its per-benchmark numbers. The percentile above is its standing across the independent composites below.

Independent composite scores
  • AA Intelligence Index: 48.6 (Artificial Analysis composite across reasoning, knowledge and coding evals)
  • AA Agentic Index: 53.6 (Tool use, planning, autonomy)
  • AA-Omniscience Index: 14.3 (−100–100)
  • GDPval-AA v2: 1680.9 ELO (Real-world work tasks, human baseline = 1000)
How it stacks up
  • Ranks #6 of 180 comparably-measured models by percentile score, across 4 independent measurements
  • Ranks #64 of 180 comparably-tested models by normalized performance per dollar

71.6 tokens/sec output

Source: Artificial Analysis · updated · See full rankings →

Specifications

Provider
Z.AI
Context window
1M tokens
Modality
text
Parameters
Proprietary
Open source
Yes — open weights available
Released
Status
Current
Last updated
Tags
open-weightsflagshipcaching

Availability verified: listed on Z.AI's own page