// Zhipu (Z.ai)
GLM-4.5V
A Zhipu (Z.ai) model. 3 prices across 3 channels side by side, each with its source and check date – plus specs, licence, speed and benchmarks.
- Official in/out per 1M
- ¥2 / ¥6
- Lowest (SiliconFlow)
- ¥1 / ¥6
- Context
- 66K
- AA index
- 6.7
Prices checked 2026-10-22Official sources linked on every rowNo estimates
01Specs at a glance
Official values first; gaps filled from OpenRouter’s API where the vendor page is silent.
| Vendor | Zhipu (Z.ai) |
|---|---|
| Context window | 66K (65,536 tokens) |
| Max output | 16K |
| Input | Text · Image |
| Output | Text |
| Tool calling / JSON | Yes / Yes |
| Weights & licence | Open weights · MIT · Hugging Face |
| Parameters | 108B (from weight files) |
| Released | Aug 11, 2025 |
| Model IDs | glm-4.5v · zai-org/GLM-4.5V · z-ai/glm-4.5v |
02Prices on 3 channels
Per 1M tokens, in the currency each source publishes (1 USD = 6.7 CNY for the blended column). Sorted: official first, then cheapest.
| Channel | Source | Input | Output | Cache hit | Blended $ | Context | Notes |
|---|---|---|---|---|---|---|---|
| Official Vendor’s China site, billed in CNY | Official 10-10 | ¥2 | ¥6 | — | 0.448 | 66K | Batch −50%Batch -50% |
| SiliconFlow Inference platform (own price page) | Platform 10-10 | ¥1 | ¥6 | — | 0.336 | — | SiliconFlow (硅基流动) own pricing page |
| Novita · fp8 Via OpenRouter / provider listed there | OpenRouter 10-22 | $0.6 | $1.8 | $0.11 | 0.9 | 66K | Novita price as listed on OpenRouter (pass-through; quantization=fp8; discount field=0); not checked against Novita's own page |
“Official” = vendor pricing page; “Platform” = the platform’s own pricing page; “OpenRouter” = price listed on OpenRouter, not checked on the platform’s site. Click a source tag to open the original page.
03Where you can use it
Derived only from the price sources above. Country restrictions are set by each vendor – check their terms before you sign up.
- Vendor’s China site, billed in CNY
Official - Inference platform (own price page)
SiliconFlow - Via OpenRouter / provider listed there
Novita - Self-host the open weights
GPU / VRAM sizing and build plans→
04Performance
Speed and AA index from Artificial Analysis public leaderboards (not our own tests); benchmark scores from our benchmark library, best result per benchmark.
- AA indexGLM-4.5V (Non-reasoning)
- 6.7
- Output speed (median)
- 54 tok/s
- Time to first token
- 2.69s
- AA index per $ (blended)
- 14.96
| Benchmark | Best score | Source | Date |
|---|---|---|---|
| LMArena Text | 1352 | official | 2026-10-08 |
| LMArena Vision | 1153 | official | 2026-10-02 |
05Price changes we recorded
All price changes →From our daily re-checks of the sources above.
No price change recorded since we started tracking (2026-10-10).
06More from Zhipu (Z.ai)
FAQ
How much does the GLM-4.5V API cost?
On the official pricing page: ¥2 / ¥6 per 1M input / output tokens (checked 2026-10-10). The lowest price we found is ¥1 / ¥6 on SiliconFlow.
What is the context window of GLM-4.5V?
66K tokens of context, up to 16K output tokens. Platforms may cap it lower – see the table.
Is GLM-4.5V open source?
Yes, the weights are published on Hugging Face (zai-org/GLM-4.5V). Licence: MIT.