GLM 4.7 Flash
Z.ai · released Jan 19, 2026 · zai-org/GLM-4.7-Flash
- Type
- Open weightsMIT License
- Params
- 31.2B
- Context
- 203K
active per word not recorded by us · about 152K words of context
Our take
The case for it
- The licence allows commercial use, changes and redistribution (MIT), so the terms are not the thing to weigh here.
- Cheap to run through a host: its cheapest listed input rate sits well under the mid-size field, so high-volume work is where it earns its place.
The case against it
- Measured quality is in the bottom third of the Arena Text board: 116th of 168 as of 25 Sep 2026, and 126th of 168 on Arena Creative Writing as of 25 Sep 2026.
- The only scores supplied are Arena preference scores, which record which answer people preferred rather than whether it was correct, so nothing here measures coding or reasoning outside those boards.
- At 31.2 billion parameters it needs a machine that can hold the whole model, so check the fit verdict below before planning to run it yourself.
How good is it?
EverydayGeneral questions and everyday reasoning
Arena Text (overall)116th of 168 · 1365
CodingWriting and fixing code on its own
Arena Coding113th of 168 · 1423
Arena Coding is the only board that has scored it for this.
AgenticPlanning, calling tools, staying on task
Not yet scored on Arena Agent.
WritingDrafting and rewriting prose
Arena Creative Writing126th of 168 · 1306
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 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?
Comfortable fit
GeForce RTX 4090 · 24 GB
Room to spare. 1.2 GB spare means a 10% error in the size would not change the answer.
GeForce RTX 5090 · 32 GB
Room to spare. 9.2 GB spare means a 10% error in the size would not change the answer.
Apple M1 Pro (16-core GPU) · 32 GB
Room to spare. 2.4 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 57 min and 28 days ago — each listing carries its own date.
- per 1M tokens
- $0.060 in / $0.40 out
- Context served
- 203K
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouterOpenRouter's own listing | $0.060 / $0.40checked 60 min ago | 200K | not measured | Unknown | Unknown | Unknown |
| DeepInfrabf16Direct | $0.060 / $0.40checked 28 days ago | 203K | not measured | Unknown | Unknown | Unknown |
| Novita AIbf16Direct and through OpenRouter | $0.070 / $0.40checked 58 min ago directchecked 23 days ago through OpenRouter | 200K | not measured | DirectUnknownThrough OpenRouterNo | DirectUnknownThrough OpenRouterNo | DirectUnknownThrough OpenRouterConfirmed |
| Venice AIfp8Through OpenRouter | $0.060 / $0.40checked 57 min ago | 128K16K max reply | 20 tok/s | No | No | Confirmed |
| Cloudflare Workers AIThrough OpenRouter | $0.060 / $0.40checked 57 min ago | 131K118K max reply | 24 tok/s | No | Yesunknown period | Unknown |
OpenRouter
Novita AI
Cloudflare Workers AIAcross the 5 listings we hold: 3 say they do not train on prompts (1 of them only through OpenRouter), 0 say they do and 2 do not say. 2 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 | ✓ | ✓ | ✓ |
| DeepInfrabf16Direct | |||
| Novita AIbf16Direct and through OpenRouter | ✓ | ✓ | ✗ |
| Venice AIfp8Through OpenRouter | ✓ | ✓ | ✓ |
| Cloudflare Workers AIThrough OpenRouter | ✓ | ✓ | ✓ |
Tool calling: 4 of 5 listings say yes, 1 publishes no parameter list. JSON output: 4 of 5 listings say yes, 1 publishes no parameter list. Strict schema: 3 of 5 listings say yes, 1 says no, 1 publishes no parameter list.
Models people weigh against GLM 4.7 Flash
When we formed this view
Recent changes
What moved
input −52% ($0.125 → $0.060 per 1M tokens), output −20% ($0.50 → $0.40 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
- 1 of 5 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 5 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-4.7-Flash
- Architecture
- Mixture of experts
- Takes in, gives back
- Text in, text out
- Catalogue slug
- z-ai-glm-4-7-flash