Specification

Release date: 19 Jan 2026
Source:OpenRouter public model & pricing listingT2observed 1 h agomedium
Openness: open-weights
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
License: mit
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 8 min agomedium
Architecture: Glm4MoeLiteForCausalLM
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 8 min agomedium
Parameters: 31.2B
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
Context window: 200K tokens
Source:OpenRouter public model & pricing listingT2observed 1 h agomedium
Max output: 118K tokens
Source:OpenRouter public model & pricing listingT2observed 1 h agomedium
Modalities: text
Source:OpenRouter public model & pricing listingT2observed 1 h agomedium
Input modalities: text
Source:OpenRouter public model & pricing listingT2observed 1 h agomedium
Output modalities: text
Source:OpenRouter public model & pricing listingT2observed 1 h agomedium
Languages: en, zh
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 8 min agomedium
File size: 62.5 GB
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 8 min agomedium
Hugging Face repo: zai-org/GLM-4.7-Flash
Source:OpenRouter public model & pricing listingT2observed 1 h agomedium
Pipeline tag: text-generation
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
Model card: huggingface.co/zai-org/GLM-4.7-Flash
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
Downloads: 1,890,101
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 8 min agomedium
Likes: 1,837
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 8 min agomedium
Gated: No
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 8 min agomedium
Hf inference providers: deepinfra, featherless-ai, novita, zai-org
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 8 min agomedium
Last modified: 2026-01-29T08:06:19+00:00
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
Library name: transformers
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 8 min agomedium
Downloads all time: 13,124,652
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 8 min agomedium
Model type: glm4_moe_lite
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 8 min agomedium
Openrouter id: z-ai/glm-4.7-flash
Source:OpenRouter public model & pricing listingT2observed 1 h agomedium
Supported parameters: frequency_penalty, include_reasoning, logit_bias, logprobs, max_tokens, min_p, presence_penalty, reasoning, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_logprobs, top_p
Source:OpenRouter public model & pricing listingT2observed 1 h agomedium
Tags: transformers, safetensors, glm4_moe_lite, text-generation, en, zh
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 8 min agomedium
Weights dtype: BF16, F32
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 8 min agomedium

Each value shows its source, tier and observation time. Conflicting claims are kept side by side and flagged — never averaged. How AI Atlas records facts →

Provenance

Attributed facts

31

Source tiers

T231

Freshest observation

8 min ago

Conflicts

None

Modalities

Modalities: text
Input: text
Output: text

Capabilities

Tool calling
Yes
OpenRouter public model & pricing listing · T2
Structured output
Yes
OpenRouter public model & pricing listing · T2
Reasoning
Yes
OpenRouter public model & pricing listing · T2
Vision
Unavailable
Audio
Unavailable
Fine-tuning available
Unavailable

Context window: 200K tokens
Source:OpenRouter public model & pricing listingT2observed 1 h agomedium
Max output: 118K tokens
Source:OpenRouter public model & pricing listingT2observed 1 h agomedium
Languages: en, zh
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 8 min agomedium

No benchmark results recorded

Results appear when a tier 1–3 source publishes them; we never copy scores without a source.

Current prices

Current prices per 1M tokens
Provider	Input / 1M	Output / 1M	Cached in	Batch in / out	Context	Observed	Source
Z.ai APIz-ai/glm-4.7-flash	$0.06	$0.40	—	—	131.1K	1 h ago	openrouter.aiT2

USD per 1M tokens as published by each provider (USD). Rows are append-only: every change is kept in the history below.

Available through 1

Z.ai API

Price history

Input price · USD / 1M tokens

Output price · USD / 1M tokens

Z.ai API

Estimated

Memory need = bytes per parameter (4-bit ≈ 0.5 × 1.15 overhead, 8-bit 1.0, fp16 2.0) + a KV-cache allowance. Not a measurement.

Estimated hardware fit
Hardware	Quantization	Memory	Est. need	Fits
Apple M3 Ultra	4bit	—	18.4 GB	Yes
AMD Instinct MI325X	4bit	256 GB	18.4 GB	Yes
AMD Instinct MI300X	4bit	192 GB	18.4 GB	Yes
Apple M2 Ultra	4bit	—	18.4 GB	Yes
NVIDIA B200	4bit	180 GB	18.4 GB	Yes
NVIDIA H200	4bit	141 GB	18.4 GB	Yes
Apple M1 Ultra	4bit	—	18.4 GB	Yes
Apple M3 Max	4bit	—	18.4 GB	Yes
Apple M4 Max	4bit	—	18.4 GB	Yes
NVIDIA DGX Spark	4bit	128 GB	18.4 GB	Yes
Apple M2 Max	4bit	—	18.4 GB	Yes
NVIDIA A100 80GB	4bit	80 GB	18.4 GB	Yes
NVIDIA H100 SXM	4bit	80 GB	18.4 GB	Yes
Apple M1 Max	4bit	—	18.4 GB	Yes
Apple M4 Pro	4bit	—	18.4 GB	Yes
Apple M3 Pro	4bit	—	18.4 GB	Yes
Apple M1 Pro	4bit	—	18.4 GB	Yes
Apple M2 Pro	4bit	—	18.4 GB	Yes
Apple M4	4bit	—	18.4 GB	Yes
NVIDIA GeForce RTX 5090	4bit	32 GB	18.4 GB	Yes
Apple M2	4bit	—	18.4 GB	Yes
Apple M3	4bit	—	18.4 GB	Yes
NVIDIA GeForce RTX 3090	4bit	24 GB	18.4 GB	Yes
NVIDIA GeForce RTX 4090	4bit	24 GB	18.4 GB	Yes
Apple M1	4bit	—	18.4 GB	No

Ancestors 0

None recorded.

This model

GLM 4.7 Flash

31.2B params

Quantizations 0

None recorded.

Descendants 1

cerebras/GLM-4.7-Flash-REAP-23B-A3B23B

Papers 1

arXiv:2508.06471Active

Repositories 0

No repositories linked yet.

As of

Rewind the record: see this entity's attributes exactly as AI Atlas knew them on a given day.

Claim history · Description

1 claims · 1 propertiesShow all properties

Descriptiondescription1

Claim history for Description
Value	Valid from → to	Status	Source	Confidence	Extractor
As a 30B-class SOTA model, GLM-4.7-Flash offers a new option that balances performance and efficiency. It is further optimized for agentic coding use cases, strengthening coding capabilities, long-horizon task planning,...	11 Sept 2026 21:10 UTC → current	current	OpenRouter public model & pricing listingT2	medium	deterministic

Claims are temporal and append-only: a new observation closes the previous claim (valid_to) instead of overwriting it. Conflicting claims from different sources are kept side by side and flagged — never averaged. Methodology →

19 Jan 2026
New modelModelGLM 4.7 FlashZ.ai (Zhipu AI)
New model: GLM 4.7 Flash (Z.ai (Zhipu AI))
openrouter
openrouter.ai
11 Sept 2026
Listed by providerModelGLM 4.7 FlashZ.ai (Zhipu AI)
Z.ai API lists GLM 4.7 Flash at $0.0605 in / $0.4 out per 1M tokens
openrouter
openrouter.ai

Full timeline →

Source documents
Source	Document	Type	Tier	Last observed	Snapshots
Hugging Face Hub (public pages, model cards, papers)	huggingface.co/zai-org/GLM-4.7-Flash	model_page	T2· Quality secondary	8 min ago	1
Hugging Face Hub (public pages, model cards, papers)	huggingface.co/cerebras/GLM-4.7-Flash-REAP-23B-A3B	model_page	T2· Quality secondary	49 min ago	2
Hugging Face Hub (public pages, model cards, papers)	huggingface.co/models?author=zai-org&p=0&sort=downloads	listing	T2· Quality secondary	1 h ago	2
OpenRouter public model & pricing listing	openrouter.ai/api/v1/models	catalogue	T2· Quality secondary	1 h ago	1

Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.