GLM 5V Turbo
Z.ai · released Apr 1, 2026
- Type
- Closed
- Input
- $1.20
- Output
- $4.00
- Cached
- $0.24
List price · per 1M tokens · Z.AI at 203K context · source ↗
Our take
Written Sep 7, 2026GLM 5V Turbo is a hosted-only multimodal model from Z.ai that handles text, images and video across a 202,752-token window. Its measured strengths sit in coding and hard prompts, with Arena scores in the mid-1400s, though creative writing and web development lag well behind.
Choose this for coding tasks where its Arena Coding score is the standout signal, or for hard prompts and mathematics in the 1440s–1450s range. It suits long-context work up to 202,752 tokens, and pricing is identical across all three providers so there is no arbitrage hunt. Skip it if you need self-hosting, a permissive licence, or strong creative writing and web development output.
The case for it
- Coding is its clear peak skill, 57.8 points above its own overall Arena Text score and 89 points above its WebDev score.
- Hard prompts and mathematics both exceed its overall standing by 19.5 and 9.4 points respectively.
- Identical pricing across OpenRouter, Novita and Z.ai — no provider shopping needed.
- 39 tokens per second on the native Z.ai host.
The case against it
- Creative writing and web development trail its coding strength by 89 points each.
- Instruction following sits 10.3 points below its own overall score, and 67.1 below coding.
- Proprietary weights with no licence disclosed — no self-host or redistribution path.
How good is it?
EverydayGeneral questions and everyday reasoning
Arena Text (overall)68th of 168 · 1433
CodingWriting and fixing code on its own
Arena Coding62nd of 168 · 1488
AgenticPlanning, calling tools, staying on task
Not yet scored on Arena Agent.
WritingDrafting and rewriting prose
Arena Creative Writing64th of 168 · 1403
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.
Where to rent it
Prices checked 4 hours ago — each listing carries its own date.
Novita AI, direct
Why this differs from the header. The strip above quotes Z.AI's own list price; this is the cheapest live offer, whoever is serving it — a reseller undercutting a lab is ordinary commerce, not an error.
- per 1M tokens
- $1.20 in / $4.00 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 | $1.20 / $4.00checked 4 hours ago | 203K | not measured | Unknown | Unknown | Unknown |
| Novita AIDirect | $1.20 / $4.00checked 4 hours ago | 205K | not measured | Unknown | Unknown | Unknown |
| Z.AIfp8Through OpenRouter | $1.20 / $4.00checked 4 hours ago | 203K131K max reply | 41 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 5V Turbo
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
- 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.
Licence and identifiers
What the licence allowsWe hold no licence record for this model. Inside are the identifiers you need to pull it — its Hugging Face repo where we have one, our slug and a machine-readable card.
Licence
We hold no licence record for this model, and no record of published weights either — so we can neither summarise its terms nor point you at the weights.
Identifiers
- Takes in, gives back
- Text, images and video in, text out
- Catalogue slug
- z-ai-glm-5v-turbo