GLM 4.5V
Z.ai · released Aug 10, 2025 · zai-org/GLM-4.5V
- Type
- Open weightsMIT License
- Params
- 108B
- Context
- 66K
active per word not recorded by us · about 49K words of context
Our take
Written Sep 1, 2026GLM 4.5V is a 108-billion-parameter vision-language model from Z.ai with a permissive MIT licence. It accepts text and images and returns text, with consistent pricing across all four tracked providers. Its measured strengths lie in coding preference rather than creative writing, with no single category win.
Pick this for open-weights vision-language work where MIT licensing matters for redistribution or commercial modification, or where predictable pricing across every provider removes cost-comparison friction. Use it when coding assistance is the priority among its measured tasks. Skip it if you need video input, measured non-English capability, or a model that tops its category on independent leaderboards.
The case for it
- Permissive MIT licence allows redistribution, modification and commercial use without restriction.
- Uniform pricing across all four providers eliminates arbitrage hunting.
- Coding preference score of 1403.7 leads its own measured tasks by a 95-point margin over creative writing.
The case against it
- No category-topping Arena performance; its overall score sits mid-pack with no field rank disclosed.
- Throughput unverified on half of offers; where measured, 47–57 tokens per second.
- Dense 107.7 billion parameters with no active-parameter efficiency claimed — no MoE savings.
How good is it?
EverydayGeneral questions and everyday reasoning
Arena Text (overall)121st of 168 · 1352
CodingWriting and fixing code on its own
Arena Coding123rd of 168 · 1402
Arena Coding is the only board that has scored it for this.
AgenticPlanning, calling tools, staying on task
Not yet scored on Arena Agent.
WritingDrafting and rewriting prose
Arena Creative Writing123rd of 168 · 1309
Arena Creative Writing is the only board that has scored it for this.
These tests check whether a model follows instructions — a precondition for all the work above, but not a measure of how well that work is done.
Every published score for this model6 scoresEvery figure we hold, from 6 boards, with who ran it and a link to the source — including the boards no rating above is built on.
Can you run it yourself?
GeForce RTX 4090 · 24 GB
Too large for this card. The weights do not fit even with part of them offloaded to system memory.
Apple M1 Pro (16-core GPU) · 32 GB
Too large for this card. The weights do not fit even with part of them offloaded to system memory.
Apple M2 Max (38-core GPU) · 96 GB
Borderline fit on an estimated size. It leaves 0.5 GB spare on a size we calculated rather than measured, and a 10% error either way would change the answer.
Memory use by level
Against a 24 GB card.
What is quantisation? →This model on every device we track71 devicesThe Q4 build most people download, on each device: what the weights come to, how much context the memory leaves, and whether it runs. Smallest device that runs it first.
Check against your own machine → · Where to rent it hosted →
Or rent it from someone else
Prices checked 4 hours ago — each listing carries its own date.
- per 1M tokens
- $0.60 in / $1.80 out
- Context served
- 66K
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouterOpenRouter's own listing | $0.60 / $1.80checked 4 hours ago | 66K | not measured | Unknown | Unknown | Unknown |
| Novita AIfp8Direct and through OpenRouter | $0.60 / $1.80checked 4 hours ago | 66K16K max reply through OpenRouter | 34 tok/sthrough OpenRouter | DirectUnknownThrough OpenRouterNo | DirectUnknownThrough OpenRouterNo | DirectUnknownThrough OpenRouterConfirmed |
| Z.AIfp8Through OpenRouter | $0.60 / $1.80checked 4 hours ago | 66K16K max reply | 47 tok/s | No | No | Confirmed |
Novita AIAcross the 3 listings we hold: 2 say they do not train on prompts (1 of them only through OpenRouter), 0 say they do and 1 does not say. 2 appear in the zero-retention registry we check (1 of them only through OpenRouter); the rest are unknown to us.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| OpenRouterOpenRouter's own listing | ✓ | ✓ | ✗ |
| Novita AIfp8Direct and through OpenRouter | ✓ | ✓ | ✗ |
| Z.AIfp8Through OpenRouter | ✓ | ✓ | ✗ |
Tool calling: 3 of 3 listings say yes. JSON output: 3 of 3 listings say yes. Strict schema: 0 of 3 listings say yes, 3 say no.
Models people weigh against GLM 4.5V
When we formed this view
Recent changes
What moved
first indexed by our pipelineEach date is the day we first saw the change, or the day the maker announced it.
What we do not know about this model yet
- We hold no measured file for it, so all 3 sizes on this page are calculated from the parameter count.
- We do not hold the active parameter count for it, so how much of it runs on any one token is unknown to us.
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 1 of 3 listings does not say whether it trains on prompts, and 1 answers only through OpenRouter, not for its own listing.
- We hold no batch or off-peak rate for any of its listings.
- We hold a decode speed for it, but no prompt-processing (prefill) figure, so how long the input side of a job takes is unknown to us.
Licence and identifiers
What the licence allowsMIT License, what it allows commercially, and the identifiers you need to pull this model — its Hugging Face repo, our slug and a machine-readable card.
Licence
MIT License
Fully permissive: do anything with attribution. No patent grant, unlike Apache-2.0.
Identifiers
- Hugging Face
- zai-org/GLM-4.5V
- Architecture
- Mixture of experts
- Takes in, gives back
- Text and images in, text out
- Catalogue slug
- z-ai-glm-4-5v