GLM 4.5
Z.ai (Zhipu AI)huggingface.co/zai-org/GLM-4.5
GLM-4.5 is our latest flagship foundation model, purpose-built for agent-based applications. It leverages a Mixture-of-Experts (MoE) architecture and supports a context length of up to 128k tokens. GLM-4.5 delivers significantly...
Updated 9 min ago · first seen 11 Sept 2026
model_01M294WWDZ0204TZY1EFTAP042
- Parameters
- 358.3B
- T2 · 1 h ago
- Context
- 131.1K tokens
- T2 · 1 h ago
- Released
- 20 Jul 2025
- T2 · 11 min ago
- License
- mit
- T2 · 11 min ago
- Knowledge cutoff
- Dec 2024
- T2 · 1 h ago
Specification
- Release date
- 20 Jul 2025
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 11 min 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 11 min agomedium
- Architecture
- Glm4MoeForCausalLM
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 11 min agomedium
- Parameters
- 358.3B
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
- Context window
- 131.1K tokens
Source:OpenRouter public model & pricing listingT2observed 1 h agomedium
- Max output
- 98.3K tokens
Source:OpenRouter public model & pricing listingT2observed 1 h agomedium
- Knowledge cutoff
- Dec 2024
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 11 min agomedium
- File size
- 716.7 GB
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 11 min agomedium
- Hugging Face repo
- zai-org/GLM-4.5
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
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
- Downloads
- 80,225
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 9 min agomedium
- Likes
- 1,411
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 9 min agomedium
- Gated
- No
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 11 min agomedium
- Hf inference providers
- zai-org
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 11 min agomedium
- Last modified
- 2025-08-11T13:27:03+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 11 min agomedium
- Downloads all time
- 1,068,472
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 9 min agomedium
- Model type
- glm4_moe
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 11 min agomedium
- Openrouter expiration date
- 31 Dec 2026
Source:OpenRouter public model & pricing listingT2observed 1 h agomedium
- Openrouter id
- z-ai/glm-4.5
Source:OpenRouter public model & pricing listingT2observed 1 h agomedium
- Supported parameters
- include_reasoning, max_tokens, reasoning, response_format, temperature, tool_choice, tools, top_k, top_p
Source:OpenRouter public model & pricing listingT2observed 1 h agomedium
- Tags
- transformers, safetensors, glm4_moe, text-generation, en, zh
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 11 min agomedium
- Weights dtype
- BF16, F32
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 11 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
33
Source tiers
T233
Freshest observation
9 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
- 131.1K tokens
Source:OpenRouter public model & pricing listingT2observed 1 h agomedium
- Max output
- 98.3K tokens
Source:OpenRouter public model & pricing listingT2observed 1 h agomedium
- Knowledge cutoff
- Dec 2024
Source:OpenRouter public model & pricing listingT2observed 1 h agomedium
- Languages
- en, zh
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 11 min agomedium
No benchmark results recorded
Current prices
| Provider | Input / 1M | Output / 1M | Cached in | Batch in / out | Context | Observed | Source |
|---|---|---|---|---|---|---|---|
| Z.ai APIz-ai/glm-4.5 | $0.60 | $2.2 | $0.11 | — | 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
Price history
Input price · USD / 1M tokens
Output price · USD / 1M tokens
- Z.ai API
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.
| Hardware | Quantization | Memory | Est. need | Fits |
|---|---|---|---|---|
| Apple M3 Ultra | 4bit | — | 206.5 GB | Yes |
| AMD Instinct MI325X | 4bit | 256 GB | 206.5 GB | Yes |
| AMD Instinct MI300X | 4bit | 192 GB | 206.5 GB | No |
| Apple M2 Ultra | 4bit | — | 206.5 GB | No |
| NVIDIA B200 | 4bit | 180 GB | 206.5 GB | No |
| NVIDIA H200 | 4bit | 141 GB | 206.5 GB | No |
| Apple M1 Ultra | 4bit | — | 206.5 GB | No |
| Apple M3 Max | 4bit | — | 206.5 GB | No |
| Apple M4 Max | 4bit | — | 206.5 GB | No |
| NVIDIA DGX Spark | 4bit | 128 GB | 206.5 GB | No |
| Apple M2 Max | 4bit | — | 206.5 GB | No |
| NVIDIA A100 80GB | 4bit | 80 GB | 206.5 GB | No |
| NVIDIA H100 SXM | 4bit | 80 GB | 206.5 GB | No |
| Apple M1 Max | 4bit | — | 206.5 GB | No |
| Apple M4 Pro | 4bit | — | 206.5 GB | No |
| Apple M3 Pro | 4bit | — | 206.5 GB | No |
| Apple M1 Pro | 4bit | — | 206.5 GB | No |
| Apple M2 Pro | 4bit | — | 206.5 GB | No |
| Apple M4 | 4bit | — | 206.5 GB | No |
| NVIDIA GeForce RTX 5090 | 4bit | 32 GB | 206.5 GB | No |
| Apple M2 | 4bit | — | 206.5 GB | No |
| Apple M3 | 4bit | — | 206.5 GB | No |
| NVIDIA GeForce RTX 3090 | 4bit | 24 GB | 206.5 GB | No |
| NVIDIA GeForce RTX 4090 | 4bit | 24 GB | 206.5 GB | No |
| Apple M1 | 4bit | — | 206.5 GB | No |
No lineage recorded
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 · Openrouter id
Openrouter idopenrouter_id1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| z-ai/glm-4.5 | → 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 →
GLM 4.5: release date changed from 2025-07-25 to 2025-07-20
Release date25 Jul 2025→20 Jul 2025huggingfaceZ.ai API lists GLM 4.5 at $0.6 in / $2.2 out per 1M tokens
openrouter
| Source | Document | Type | Tier | Last observed | Snapshots |
|---|---|---|---|---|---|
| Hugging Face Hub (public pages, model cards, papers) | huggingface.co/zai-org/GLM-4.5 | model_page | T2· Quality secondary | 9 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.