- Type
- Open weightsMIT License
- Params
- 358B
- Context
- 131K
32B active per word · about 98K words of context
Our take
Written Sep 17, 2026GLM 4.5 is a downloadable text model with a licence that allows commercial use, changes and redistribution, and it resolves a measured share of real GitHub issues end-to-end. At 358.3 billion parameters it is data-centre scale, so hosted use is the practical route for nearly everyone.
Pick it for software engineering work where fixes have to land in an existing codebase, or for long-document work where the material need not be split up first. Three hosts serve it at the same rate, so there is no cheaper row to shop for. Skip it if you need to run the model on your own machine, or if you need measured reasoning or factual accuracy rather than coding and preference evidence.
The case for it
- 64.2% on SWE-bench Verified, which records the share of real GitHub issues resolved end-to-end rather than set-piece exercises.
- The licence allows commercial use, changes and redistribution (MIT), so the terms are not the thing to read first.
- A request capacity of 131072 tokens leaves room for a long report or a stack of documents beside the question, though reliable recall across all of it is unverified in our data.
The case against it
- 358.3 billion parameters in total, with no figure supplied for how many work on any one token, so hosted use is the practical route.
- Quality evidence is limited to coding and human preference: nothing supplied measures reasoning or factual accuracy, so those need a trial on work you can check yourself.
- The arena ratings cover coding, creative writing, hard prompts, instruction following and maths, and record which answer people preferred rather than a prose-craft rubric.
How good is it?
EverydayGeneral questions and everyday reasoning
Arena Text (overall)89th of 168 · 1411
CodingWriting and fixing code on its own
Arena Coding90th of 168 · 1455
Arena Coding is the only board that has scored it for this.
AgenticPlanning, calling tools, staying on task
Not yet scored on Arena Agent. It is on SWE-bench Verified, in 20th of 42 with 64.2.
WritingDrafting and rewriting prose
Arena Creative Writing88th of 168 · 1372
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 model7 scoresEvery figure we hold, from 7 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.
Comfortable fit
Apple M3 Ultra (80-core GPU) · 512 GB
Room to spare. 149.3 GB spare means a 10% error in the size would not 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 between 54 min and 21 days ago — each listing carries its own date.
- per 1M tokens
- $0.60 in / $2.20 out
- Context served
- 131K
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouterOpenRouter's own listing | $0.60 / $2.20checked 56 min ago | 131K | not measured | Unknown | Unknown | Unknown |
| Novita AIDirect | $0.60 / $2.20checked 21 days ago | 131K | not measured | Unknown | Unknown | Unknown |
| Z.AIfp8Through OpenRouter | $0.60 / $2.20checked 54 min ago | 131K98K max reply | 21 tok/s | No | No | Confirmed |
OpenRouterAcross the 3 listings we hold: 1 says it does not train on prompts, 0 say they do and 2 do not say. 1 appears in the zero-retention registry we check; 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 AIDirect | |||
| Z.AIfp8Through OpenRouter | ✓ | ✓ | ✗ |
Tool calling: 2 of 3 listings say yes, 1 publishes no parameter list. JSON output: 2 of 3 listings say yes, 1 publishes no parameter list. Strict schema: 0 of 3 listings say yes, 2 say no, 1 publishes no parameter list.
Models people weigh against GLM 4.5
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.
- 1 of 3 listings publishes no parameter list, so what its API accepts is unknown to us.
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 2 of 3 listings do not say whether they train on prompts.
- 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-4.5
- Architecture
- Mixture of experts
- Takes in, gives back
- Text in, text out
- Catalogue slug
- z-ai-glm-4-5