// Zhipu (Z.ai)
GLM 4.5 Air
A Zhipu (Z.ai) model. 3 prices across 2 channels side by side, each with its source and check date – plus specs, licence, speed and benchmarks.
- Official in/out per 1M
- —
- Lowest (Novita)
- $0.13 / $0.85
- Context
- 131K
- AA index
- 11.1
Prices checked 2026-10-22Official sources linked on every rowNo estimatesCheapest LLM APIs →
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 | 131K (131,072 tokens) |
| Max output | 98K |
| Input | Text |
| Output | Text |
| Tool calling / JSON | Yes / No |
| Weights & licence | Open weights · MIT · Hugging Face |
| Parameters | 110B (from weight files) |
| Released | Jul 25, 2025 |
| Model IDs | z-ai/glm-4.5-air · zai-org/GLM-4.5-Air |
02Prices on 2 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 |
|---|---|---|---|---|---|---|---|
| Novita · bf16 Via OpenRouter / provider listed there | OpenRouter 10-22 | $0.13 | $0.85 | $0.025 | 0.31 | 131K | Novita price as listed on OpenRouter (pass-through; quantization=bf16; discount field=0); not checked against Novita's own page |
| SiliconFlow · fp8 Via OpenRouter / provider listed there | OpenRouter 10-22 | $0.14 | $0.86 | — | 0.32 | 131K | SiliconFlow price as listed on OpenRouter (pass-through; quantization=fp8; discount field=0); not checked against SiliconFlow's own page |
| SiliconFlow Inference platform (own price page) | Platform 10-10 | ¥1 | ¥6 | — | 0.336 | — | SiliconFlow (硅基流动) own pricing 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.
- Via OpenRouter / provider listed there
Novita · SiliconFlow - Inference platform (own price page)
SiliconFlow - 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-4.5-Air
- 11.1
- Output speed (median)
- 80 tok/s
- Time to first token
- 2.31s
- AA index per $ (blended)
- 35.77
| Benchmark | Best score | Source | Date |
|---|---|---|---|
| LMArena Text | 1373 | official | 2026-10-08 |
| MMLU-Pro | 81.4% | vendor | 2026-03-11 |
| Humanity's Last Exam | 8.1% | compiled | 2025-07-20 |
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 4.5 Air API cost?
There is no official pay-as-you-go price in our data. The lowest listed price is $0.13 / $0.85 on Novita.
What is the context window of GLM 4.5 Air?
131K tokens of context, up to 98K output tokens. Platforms may cap it lower – see the table.
Is GLM 4.5 Air open source?
Yes, the weights are published on Hugging Face (zai-org/GLM-4.5-Air). Licence: MIT.