GLM-4.5V
- In Input modalities: TextImageVideo Out Output modalities: Text
- Reasoning
- Reasoning can be off
- Tool use
- Open weights
Prices
3 offerings · prices as listedglm-4.5v| Conditions/ 1M tokens | Input | Cache read | Output |
|---|---|---|---|
| Standard | $0.60 | $0.11 | $1.80 |
Prices from Pricing (opens in a new tab) (checked Nov 1, 2026)
glm-4.5v| Conditions/ 1M tokens | Input | Cache read | Output |
|---|---|---|---|
| Standard | ¥2.00 | ¥0.40 | ¥6.00 |
| Prompts over 32K tokens | ¥4.00 | ¥0.80 | ¥12.00 |
Prices from 智谱 BigModel：API 定价 (opens in a new tab) (checked Nov 2, 2026)
Standard: the price a request with no conditions pays (the headline price elsewhere on the site).
Details
- Knowledge cutoff
- Apr 2025
- Family
- glm
- Model ID
Not stated on Zhipu AI’s pages: max input, reasoning efforts, max thinking budget, structured output, built-in tools, licence, aliases.
Run locally
Weights: zai-org/GLM-4.5V- Parameters 107.7B
- Active 12B · 128 experts, 8 per token
- Native precision BF16
- Layers 46
- KV cache per token 184 KB
- Config positions 64K (config.json max_position_embeddings)
- API context 63K (maker’s API)
- Needs
- ≈ 57.4 GB (weights 53.3 + KV cache 1.4 + overhead 2.7)
- Usable
- 21.6 GB (90% of its memory)
- In system memory
- 50.5 GB · the MoE experts in system memory, attention and shared layers on the GPU (llama.cpp --cpu-moe)
- Generation speed
- 12–18 tok/s (reads the active 12B per token)
- First token
- about 0.39–0.58 s for a 2K prompt
| Precision | Weights | Needs at 8K | On your hardware | Longest context |
|---|---|---|---|---|
| BF16 (native)maker’s file | 200.6 GB | ≈ 212.1 | ✕Doesn’t fit | — |
| Q8_0 | 106.6 GB | ≈ 113.3 | ✕Doesn’t fit | — |
| FP8maker’s file | 102.4 GB | ≈ 109.0 | ✕Doesn’t fit | — |
| Q6_K | 82.4 GB | ≈ 87.9 | ✕Doesn’t fit | — |
| Q5_K_M | 71.3 GB | ≈ 76.4 | ○Needs system memory 7–10 tok/s | — |
| Q5_0 | 69.0 GB | ≈ 73.9 | ○Needs system memory 7–10 tok/s | — |
| Q4_K_M | 60.9 GB | ≈ 65.4 | ○Needs system memory 11–16 tok/s | — |
| Q4_0 | 56.4 GB | ≈ 60.7 | ○Needs system memory 12–17 tok/s | — |
| IQ4_XS | 53.3 GB | ≈ 57.4 | ○Needs system memory 12–18 tok/s | — |
| Q3_K_Mquality drops | 49.0 GB | ≈ 52.9 | ○Needs system memory 13–20 tok/s | — |
| IQ3_XXSquality drops | 38.4 GB | ≈ 41.7 | ○Needs system memory 17–26 tok/s | — |
| Q2_Kquality drops | 37.6 GB | ≈ 40.9 | ○Needs system memory 18–26 tok/s | — |
| IQ2_XXSquality drops | 25.8 GB | ≈ 28.6 | ○Needs system memory 42–63 tok/s | — |
Click a row to choose a precision. “Maker’s file” sizes are the maker’s own files; others are parameters × bits per weight.
Compared with other hardware
Each at the highest precision it runs. Click one for details.
Smallest that runs it (Q4_K_M, 8K): GPU NVIDIA H100 SXM; unified memory Apple M5 Ultra (64-core GPU) · 96 GB.
Run commands
The maker publishes no files at this precision. Choose its native precision or one of its own builds, or quantise it yourself with llama.cpp.
Memory to fine-tune
Batch 1, 2,048-token sequences, gradient checkpointing; LoRA and QLoRA train rank-16 adapters on the attention projections.
Estimates; facts from the maker’s Hugging Face repositories, as of 2026-11-06. How it’s estimated
Cited scores
From third-party leaderboards, not measured by us- LMArena Text 1,352
#124 of 163 listed models · CI 1,344–1,361 · 4,817 votes
- LMArena Text · Chinese 1,356
#130 of 161 listed models · CI 1,320–1,393 · 235 votes
- LMArena Text · Coding 1,402
#123 of 163 listed models · CI 1,384–1,421 · 964 votes
- LMArena Text · Creative writing 1,309
#127 of 163 listed models · CI 1,286–1,332 · 613 votes
- LMArena (Arena), leaderboard-dataset on Hugging Face, licensed CC BY 4.0 · License · as of Oct 19 – 28, 2026
- changes we made
Changes
All changes →- 1 new price on Z.ai API Cache read $0.11
Sources
- Pricing (opens in a new tab) docs.z.ai · checked Nov 1, 2026
- 硅基流动：模型价格in Chinese (opens in a new tab) siliconflow.cn · checked Nov 1, 2026
- 智谱 BigModel：API 定价in Chinese (opens in a new tab) docs.bigmodel.cn · checked Nov 2, 2026
- GLM-4.5V (opens in a new tab) docs.z.ai · checked Nov 1, 2026
- 智谱 BigModel：GLM-4.5Vin Chinese (opens in a new tab) docs.bigmodel.cn · checked Nov 1, 2026
- New Released (opens in a new tab) docs.z.ai · checked Oct 10, 2026
- zai-org/GLM-4.5V model card (opens in a new tab) huggingface.co · checked Nov 1, 2026
- models.dev: glm-4.5v (community data, MIT) (opens in a new tab) github.com · checked Sep 30, 2026
- zai-org/GLM-4.5V model card (opens in a new tab) huggingface.co · checked Nov 1, 2026
- zai-org/GLM-4.5V model card (opens in a new tab) huggingface.co · checked Oct 30, 2026
- zai-org/GLM-4.5V config.json (opens in a new tab) huggingface.co · checked Oct 31, 2026
- zai-org/GLM-4.5V files (opens in a new tab) huggingface.co · checked Oct 30, 2026
- zai-org/GLM-4.5V-FP8 files (opens in a new tab) huggingface.co · checked Oct 31, 2026
- zai-org/GLM-4.5V README.md (opens in a new tab) huggingface.co · checked Nov 5, 2026
Zhipu AI’s official policies: data use, privacy, terms →
Some values on this page are still waiting to be checked against official pages: a filled dot is verified, a hollow one is not yet (with or without a source on file). How we verify data
Zhipu AI · China · z.ai
Related models
Snapshots, the same family and other models from this provider