- Type
- Open weightsMIT License
- Params
- 754B
- Context
- 205K
about 154K words of context
Our take
Written Aug 3, 2026GLM 5 is a large downloadable text model from Z.AI with a permissive MIT licence and a 204,800-token request limit. It scores well on coding leaderboards and is available from nine different providers, though its total parameter count may overstate its actual per-token workload.
Pick this when you need open weights with no licensing strings attached — the MIT licence allows commercial use, modification and redistribution. Use it for coding workloads where its measured coding score is the relevant signal, or for long-document text tasks up to 204,800 tokens. Skip it if you need image, audio or video input, or if you need guaranteed throughput consistency across providers.
The case for it
- Permissive MIT licence with no attribution or copyleft requirements, allowing commercial use and redistribution.
- Strong measured coding performance relative to its overall chat score, with a 40.7-point gap favouring coding.
- Ten offers from nine providers, with the lowest price point shared by two hosts.
- 204,800-token request limit for long-document processing.
The case against it
- Total parameter count of 754 billion with active parameter count undisclosed, so efficiency is unverified in our data.
- Throughput varies dramatically across providers — a 5.9× spread between the fastest and slowest measured, and even the cheapest providers differ by 1.3×.
- Hard prompts and web development coding trail its own general coding score by 19.5 and 62.7 points respectively.
How good is it?
IntelligencePuzzles, maths, exam questions
Arena Text (overall)29th of 143 · 1456.7
CodingWriting and fixing code on its own
Arena Coding38th of 143 · 1497.4
AgenticPlanning, calling tools, staying on task
GLM 5 is not on Arena Agent (IPS), which is where the rating would come from, so there is no rating here. It is on SWE-bench Verified, in 7th of 39 with 72.8.
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 5 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 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?
- 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.
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.
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 17 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
- $0.95 in / $2.55 out
- Context served
- 205K
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| GMICloudfp8 | $0.60 / $1.92 | 203K | 45 tok/s | No | Yesunknown period | Unknown |
| StreamLakefp8 | $0.60 / $1.92 | 198K | 37 tok/s | No | Yesunknown period | Unknown |
| DeepInfrafp4 | $0.60 / $2.08 | 203K | not measured | Unknown | Unknown | Unknown |
| DeepInfrafp4 | $0.60 / $2.08 | 203K | 53 tok/s | No | No | Confirmed |
| Baidufp8 | $0.70 / $2.24 | 203K | 42 tok/s | No | Yesunknown period | Unknown |
| DigitalOcean Gradient | $0.75 / $2.40 | 64K | 7 tok/s | No | No | Confirmed |
| SiliconFlowfp8 | $0.95 / $2.55 | 205K | 32 tok/s | No | No | Confirmed |
| Chutesfp8 | $0.95 / $2.55 | 203K | 47 tok/s | No | Yesunknown period | Unknown |
| OpenRouter | $0.95 / $2.55 | 205K | not measured | Unknown | Unknown | Unknown |
| AtlasCloudfp8 | $0.95 / $3.15 | 203K | 39 tok/s | No | Yesunknown period | Unknown |
| Novita AIfp8 | $1.00 / $3.20 | 203K | 34 tok/s | No | No | Confirmed |
| Venice AIfp8 | $1.00 / $3.20 | 198K | 50 tok/s | No | No | Confirmed |
| Parasailfp8 | $1.00 / $3.20 | 203K | 37 tok/s | No | No | Confirmed |
| Z.AIfp8 | $1.00 / $3.20 | 203K | 32 tok/s | No | No | Confirmed |
| Amazon Bedrock | $1.00 / $3.20 | 203K | 49 tok/s | No | No | Confirmed |
| Novita AI | $1.00 / $3.20 | 203K | not measured | Unknown | Unknown | Unknown |
| Phala | $1.20 / $3.50 | 203K | 12 tok/s | No | No | Confirmed |
DeepInfra
Baidu
DigitalOcean Gradient
Novita AI
Amazon BedrockAcross the 17 listings we hold: 14 say they do not train on prompts, 0 say they do and 3 do not say. 9 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 |
|---|---|---|---|
| GMICloudfp8 | ✓ | ✓ | ✓ |
| StreamLakefp8 | ✓ | ✓ | ✓ |
| DeepInfrafp4 | |||
| DeepInfrafp4 | ✓ | ✓ | ✓ |
| Baidufp8 | ✓ | ✓ | ✓ |
| DigitalOcean Gradient | ✓ | ✓ | ✓ |
| SiliconFlowfp8 | ✓ | ✗ | ✗ |
| Chutesfp8 | ✓ | ✓ | ✓ |
| OpenRouter | ✓ | ✓ | ✓ |
| AtlasCloudfp8 | ✓ | ✓ | ✓ |
| Novita AIfp8 | ✓ | ✗ | ✗ |
| Venice AIfp8 | ✓ | ✓ | ✓ |
| Parasailfp8 | ✓ | ✓ | ✓ |
| Z.AIfp8 | ✓ | ✗ | ✗ |
| Amazon Bedrock | ✓ | ✗ | ✗ |
| Novita AI | |||
| Phala | ✓ | ✓ | ✓ |
Tool calling: 15 of 17 listings say yes, 2 publish no parameter list. JSON output: 11 of 17 listings say yes, 4 say no, 2 publish no parameter list. Strict schema: 11 of 17 listings say yes, 4 say no, 2 publish no parameter list.
Models people weigh against GLM 5
When we formed this view
Dates behind this page
Prices last checked 3d 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.
- 2 of 17 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.
- 3 of 17 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-5
- Architecture
- Mixture of experts
- Modality record
- text->text
- Catalogue slug
- z-ai-glm-5