- Type
- Open weightsMIT License
- Params
- 111B
- Context
- 131K
about 98K words of context
Our take
Written Aug 3, 2026GLM 4.5 Air is a large downloadable text model from Z.AI with a permissive MIT licence and a 131,072-token request limit. Its measured coding score is the strongest of its covered categories, though creative writing lags nearly a hundred points behind.
Pick this when a permissive open licence matters more than frontier performance, or for coding-heavy workloads where its Arena score is the standout category. It is also a budget-conscious choice among the five tracked providers. Skip it if you need image, audio or video input, if creative writing quality is critical, or if you require standard academic reasoning benchmarks.
The case for it
- Permissive MIT licence allows commercial use, modification and redistribution with no restrictions.
- Strongest measured performance in coding among covered categories, nearly a hundred points above its creative writing score.
- Lowest-cost access comes from providers with the widest offer counts in this model's market.
The case against it
- No disclosed active parameter count, so efficiency comparisons are impossible.
- Creative writing lags coding by a wide margin on the Arena leaderboard.
- No standard academic or reasoning benchmarks in the catalogue; only Arena Elo scores are present.
How good is it?
IntelligencePuzzles, maths, exam questions
Arena Text (overall)90th of 143 · 1372.7
CodingWriting and fixing code on its own
Arena Coding89th of 143 · 1426.2
Arena Coding is the only board that has scored it for this.
AgenticPlanning, calling tools, staying on task
Nobody we watch has scored GLM 4.5 Air for this. We would take the rating from Arena Agent (IPS).
WritingWe do not rate this
Two boards come close and neither tests writing: Arena Creative Writing asks people which of two replies they prefer, and LiveBench Language tests whether a model understood a passage. So we show where GLM 4.5 Air placed and give it no mark out of five.
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, which is why they get no rating.
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?
- Fits in memory
- weights load entirely on the card
- Spills to system RAM
- some weights offload; much slower
- Too large
- will not load even with offload
- est
- size is calculated; the verdict could change by 10%
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 M1 Ultra (64-core GPU) · 128 GB
Room to spare. 22.7 GB spare means a 10% error in the size would not change the answer.
Memory use by level
Against a 24 GB card.
All 3 sizes here are calculated, not measured. We hold no measured file for this model, so each size comes from the parameter count and every verdict above inherits that uncertainty.
Check against your own machine → · All 71 devices, with every size →
Or rent it from someone else
Cheapest of 5 live listings. Picked at the widest standard context we hold, within one quantisation slice, so the numbers beside it are a price one host actually charges.
- per 1M tokens
- $0.13 in / $0.85 out
- Context served
- 131K
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouter | $0.13 / $0.85 | 131K | not measured | Unknown | Unknown | Unknown |
| Novita AI | $0.13 / $0.85 | 131K | not measured | Unknown | Unknown | Unknown |
| Novita AIbf16 | $0.13 / $0.85 | 131K | 21 tok/s | No | No | Confirmed |
| SiliconFlowfp8 | $0.14 / $0.86 | 131K | 19 tok/s | No | No | Confirmed |
| Z.AIfp8 | $0.20 / $1.10 | 131K | 45 tok/s | No | No | Confirmed |
Novita AIAcross the 5 listings we hold: 3 say they do not train on prompts, 0 say they do and 2 do not say. 3 appear in the zero-retention registry we check; the rest are unknown to us rather than confirmed either way.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
- ✓
- Supported
- ✗
- Not supported
- Not published
- host gave no parameter list
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| OpenRouter | ✓ | ✗ | ✗ |
| Novita AI | |||
| Novita AIbf16 | ✓ | ✗ | ✗ |
| SiliconFlowfp8 | ✓ | ✗ | ✗ |
| Z.AIfp8 | ✓ | ✗ | ✗ |
Tool calling: 4 of 5 listings say yes, 1 publishes no parameter list. JSON output: 0 of 5 listings say yes, 4 say no, 1 publishes no parameter list. Strict schema: 0 of 5 listings say yes, 4 say no, 1 publishes no parameter list.
When we formed this view
Dates behind this page
Prices last checked 4d ago
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 5 listings publish no parameter list, so what their API accepts is unknown to us.
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 2 of 5 listings do not say whether they train on prompts.
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-Air
- Architecture
- Mixture of experts
- Modality record
- text->text
- Catalogue slug
- z-ai-glm-4-5-air