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
about 152K words of context
Our take
Written Aug 3, 2026GLM 4.7 Flash is a 31.2-billion-parameter text-only model from Z.AI with a permissive MIT licence and a measured coding strength that sits well above its other benchmark scores. It is positioned as a low-cost, downloadable option for developers who need open-weight flexibility rather than peak all-round performance.
Pick this for coding tasks where its measured coding score is the standout result, or for budget text-only inference with open-weight flexibility. Use it when throughput matters and you can access the faster host option. Skip it if you need image, video or audio support, if creative writing quality is critical, or if you want a model with more even benchmark coverage across chat and reasoning tasks.
The case for it
- Strongest measured capability is coding, with an Arena Coding Elo 55.6 points above its own next-best score and 111.4 points above its creative writing score.
- Permissive MIT licence allows commercial use, modification and redistribution.
- Lowest-in-class pricing with multiple providers at the floor rate: five of seven tracked offers match the cheapest tier.
- Stable benchmark readings across evaluation dates, with maximum score drift of 0.15 points across all six Arena categories.
The case against it
- Creative writing is a clear weak point relative to other capabilities, sitting 111.4 points below its coding score and 74.77 points below its hard-prompts score.
- Text-to-text only; no image, video or audio support, and the active parameter count is undisclosed so true per-token compute cost remains unknown.
- Throughput varies 3.5 times across providers at similar pricing, with no data for three of the seven offers.
How good is it?
IntelligencePuzzles, maths, exam questions
Arena Text (overall)93rd of 143 · 1367.8
CodingWriting and fixing code on its own
Arena Coding91st of 143 · 1423.4
Arena Coding is the only board that has scored it for this.
AgenticPlanning, calling tools, staying on task
Nobody we watch has scored GLM 4.7 Flash 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 4.7 Flash 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%
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.
Check against your own machine → · All 71 devices, with every size →
Or rent it from someone else
Cheapest of 7 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
- $0.060 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 |
|---|---|---|---|---|---|---|
| OpenRouter | $0.060 / $0.40 | 203K | not measured | Unknown | Unknown | Unknown |
| DeepInfrabf16 | $0.060 / $0.40 | 203K | 38 tok/s | No | No | Confirmed |
| DeepInfrabfloat16 | $0.060 / $0.40 | 203K | not measured | Unknown | Unknown | Unknown |
| Novita AI | $0.070 / $0.40 | 200K | not measured | Unknown | Unknown | Unknown |
| Novita AIbf16 | $0.070 / $0.40 | 200K | 11 tok/s | No | No | Confirmed |
| Venice AIfp8 | $0.060 / $0.40 | 128K | 18 tok/s | No | No | Confirmed |
| Cloudflare Workers AI | $0.060 / $0.40 | 131K | 23 tok/s | No | Yesunknown period | Unknown |
DeepInfra
Novita AI
Cloudflare Workers AIAcross the 7 listings we hold: 4 say they do not train on prompts, 0 say they do and 3 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 | ✓ | ✓ | ✓ |
| DeepInfrabf16 | ✓ | ✓ | ✓ |
| DeepInfrabfloat16 | |||
| Novita AI | |||
| Novita AIbf16 | ✓ | ✓ | ✗ |
| Venice AIfp8 | ✓ | ✓ | ✓ |
| Cloudflare Workers AI | ✓ | ✓ | ✓ |
Tool calling: 5 of 7 listings say yes, 2 publish no parameter list. JSON output: 5 of 7 listings say yes, 2 publish no parameter list. Strict schema: 4 of 7 listings say yes, 1 says no, 2 publish no parameter list.
When we formed this view
Dates behind this page
Prices last checked 3d ago
What we do not know about this model yet
- 2 of 7 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 7 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-4.7-Flash
- Architecture
- Mixture of experts
- Modality record
- text->text
- Catalogue slug
- z-ai-glm-4-7-flash