ModelPriceWatch.com
Last scan 2026-09-11 Models tracked 258 Providers 32 Cheapest paid Granite 4.0 H Micro $0.017/Mtok in Every price links to its source

GLM-4.5V

by Z.AI · 106B (A12B) parameters

Current mid tier open weights cheap tier
Email me when GLM-4.5V gets cheaper

Today's price · per 1M tokens

Input

$0.600

per 1M tokens

Output

$1.80

per 1M tokens

Blended

$0.900

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

Cached input

$0.110

18% of input — prompt caching

Source: official Z.AI pricing · read MODELPRICEWATCH.COM · 2026-09-11

Price receipt

We read Z.AI's own pricing page on and found GLM-4.5V 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 7596a14ff6.

Overview

Z.AI's 100B-scale open-source vision reasoning model — 106B total / 12B activated, covering image, video, document understanding, visual grounding and GUI-agent tasks. $0.60/$1.80 per 1M; cached input $0.11. Context window is deliberately unpublished here: Z.AI's own GLM-4.5V page prints a Maximum Output of 16K but no context length, and the third-party catalogues disagree (OpenRouter and Novita both serve 65,536 while LiteLLM's first-party zai/ entry says 128,000), so we omit the field rather than publish a contested number.

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.

RunPod →
Rent GPUs by the second and serve any open-weight model yourself.
Novita AI →
Serverless open-model inference billed per token — no GPU ops.
Vast.ai →
GPU marketplace — rent spot/on-demand GPUs cheaply and serve any open-weight model.

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 3/5
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 12.8th1 independent measurement
Percentile per $/Mtok 14.2

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
  • LMSYS Chatbot Arena: 1352.5 ELO (Human preference)
How it stacks up
  • Ranks #156 of 181 comparably-measured models by percentile score, across 1 independent measurement
  • Ranks #141 of 181 comparably-tested models by normalized performance per dollar

Source: LMSYS Chatbot Arena (UC Berkeley) · updated · See full rankings →

Specifications

Provider
Z.AI
Context window
— tokens
Modality
text, image, video
Parameters
106B (A12B)
Open source
Yes — open weights available
Released
Status
Current
Last updated
Tags
open-weightsmid-tiermultimodalcaching

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

Try on Z.AI Official pricing page