- Type
- Open weightsMIT License
- Params
- 754B
- Context
- 205K
active per word not recorded by us · about 154K words of context
Our take
Written Sep 2, 2026GLM 5 is a large downloadable text model from Z.ai with a permissive MIT licence and a 204,800-token request limit. Its strongest measured skill is coding, with a 72.8% score on real-world software engineering tasks, though its maths and creative writing scores trail that peak.
Pick this for coding-heavy workloads or end-to-end software engineering where you need open weights and a permissive licence. Use it for long-context text work at 204,800 tokens, or when you want provider choice with a competitive floor rate. Skip it if you need multimodal input, if maths or creative writing matter more than code, or if you want the fastest throughput without paying a steep premium.
The case for it
- Strongest measured skill is coding: 39.8 points above its own overall chat score, and 54.9 points above its maths score.
- Resolves real GitHub issues end-to-end at 72.8% on SWE-bench Verified.
- Permissive MIT licence allows commercial use, modification and redistribution.
- Seventeen hosted offers, with four providers at the same floor rate.
The case against it
- Maths and creative writing lag its coding peak by 49+ points each.
- Premium throughput costs 67% more than the cheapest rate.
- Active parameter count undisclosed, so efficiency versus dense or mixture-of-experts alternatives is unverified in our data.
How good is it?
An open-weights text model for everyday questions and drafting prose.
- getting answers to everyday questionsArena Text (overall) · 40th of 168
- drafts, rewrites and editingArena Creative Writing · 30th of 168
EverydayGeneral questions and everyday reasoning
Arena Text (overall)40th of 168 · 1457
CodingWriting and fixing code on its own
Arena Coding54th of 168 · 1498
AgenticPlanning, calling tools, staying on task
Not yet scored on Arena Agent. It is on SWE-bench Verified, in 7th of 42 with 72.8.
WritingDrafting and rewriting prose
Arena Creative Writing30th of 168 · 1447
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 model8 scoresEvery figure we hold, from 8 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.
Radeon RX 7900 XT · 20 GB
Too large for this card. The weights do not fit even with part of them offloaded to system memory.
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 57 min and 28 days ago — each listing carries its own date.
- per 1M tokens
- $0.60 in / $1.92 out
- Context served
- 205K
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouterOpenRouter's own listing | $0.60 / $1.92checked 59 min ago | 205K | not measured | Unknown | Unknown | Unknown |
| StreamLakefp8Through OpenRouter | $0.60 / $1.92checked 57 min ago | 198K128K max reply | 59 tok/s | No | Yesunknown period | Unknown |
| GMICloudfp8Through OpenRouter | $0.60 / $1.92checked 57 min ago | 203K182K max reply | 61 tok/s | No | Yesunknown period | Unknown |
| DeepInfrafp4Direct | $0.60 / $2.08checked 28 days ago | 203K | not measured | Unknown | Unknown | Unknown |
| Baidufp8Through OpenRouter | $0.70 / $2.24checked 57 min ago | 203K131K max reply | 50 tok/s | No | Yesunknown period | Unknown |
| SiliconFlowfp8Through OpenRouter | $0.95 / $2.55checked 57 min ago | 205K131K max reply | 53 tok/s | No | No | Confirmed |
| Venice AIfp8Through OpenRouter | $1.00 / $3.20checked 57 min ago | 198K32K max reply | 57 tok/s | No | No | Confirmed |
| Novita AIfp8Direct and through OpenRouter | $1.00 / $3.20checked 58 min ago directchecked 57 min ago through OpenRouter | 203K131K max reply through OpenRouter | 41 tok/sthrough OpenRouter | DirectUnknownThrough OpenRouterNo | DirectUnknownThrough OpenRouterNo | DirectUnknownThrough OpenRouterConfirmed |
| Amazon BedrockThrough OpenRouter | $1.00 / $3.20checked 57 min ago | 203K131K max reply | 59 tok/s | No | No | Confirmed |
| Z.AIfp8Through OpenRouter | $1.00 / $3.20checked 57 min ago | 203K131K max reply | 50 tok/s | No | No | Confirmed |
DeepInfra
Baidu
Novita AI
Amazon BedrockAcross the 10 listings we hold: 8 say they do not train on prompts (1 of them only through OpenRouter), 0 say they do and 2 do not say. 5 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 | ✓ | ✓ | ✓ |
| StreamLakefp8Through OpenRouter | ✓ | ✓ | ✓ |
| GMICloudfp8Through OpenRouter | ✓ | ✓ | ✓ |
| DeepInfrafp4Direct | |||
| Baidufp8Through OpenRouter | ✓ | ✓ | ✓ |
| SiliconFlowfp8Through OpenRouter | ✓ | ✗ | ✗ |
| Venice AIfp8Through OpenRouter | ✓ | ✓ | ✓ |
| Novita AIfp8Direct and through OpenRouter | ✓ | ✗ | ✗ |
| Amazon BedrockThrough OpenRouter | ✓ | ✗ | ✗ |
| Z.AIfp8Through OpenRouter | ✓ | ✗ | ✗ |
Tool calling: 9 of 10 listings say yes, 1 publishes no parameter list. JSON output: 5 of 10 listings say yes, 4 say no, 1 publishes no parameter list. Strict schema: 5 of 10 listings say yes, 4 say no, 1 publishes no parameter list.
Models people weigh against GLM 5
When we formed this view
Recent changes
What moved
input +33% ($0.75 → $1.00 per 1M tokens), output +33% ($2.40 → $3.20 per 1M tokens)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 10 listings publishes no parameter list, so what its API accepts is unknown to us.
- 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.
- 2 of 10 listings do not say whether they train 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-5
- Architecture
- Mixture of experts
- Takes in, gives back
- Text in, text out
- Catalogue slug
- z-ai-glm-5