GLM-4.5-Air pricing, context window and limits
GLM-4.5-Air costs $0.2 per million input tokens and $1.1 per million output tokens at Zhipu GLM list price. It accepts up to 131,072 tokens of context and returns up to 98,304 tokens.
- Model id
glm-4.5-air - Snapshot
What does GLM-4.5-Air cost?
| Input | $0.2 |
|---|---|
| Output | $1.1 |
| Cached input (read) | $0.03 |
| Cache write | $0 |
US dollars per million tokens. A dash means no price is published.
How much can GLM-4.5-Air read and write?
| Context window | 131,072 |
|---|---|
| Max output | 98,304 |
What can GLM-4.5-Air do?
| Vision (image input) | No |
|---|---|
| Tool calling | Yes |
| Structured output | No |
| Reasoning | Yes |
| Input | text |
| Output | text |
What does a request to GLM-4.5-Air cost?
| A typical request: 1,000 tokens in, 500 out | $0.00075 |
|---|---|
| A long request: 10,000 tokens in, 1,000 out | $0.0031 |
| 1,000 typical requests | $0.75 |
| 1 million tokens in and 1 million out | $1.3 |
Input read from the provider's prompt cache costs $0.03 per million tokens instead of $0.2, 85% less. A request that repeats a 1,000-token prompt from the cache costs $0.00058 instead of $0.00075.
Among 17 Zhipu GLM models with a published price, GLM-4.5-Air is the 6th cheapest by input price. Its context window is the 12th largest of 17. List prices only; discounts, batch prices and prices above 200K tokens are not shown.
How do I call GLM-4.5-Air through DVARA?
Configure the chatglm provider in the DVARA LLM Gateway and send the model id glm-4.5-air. DVARA, the AI gateway, applies your policies, audit and cost attribution to the call. See LLM cost attribution and budgets.
In DVARA, if you haven't set your own price for a model, its calls are costed at the price in the catalogue that ships with your DVARA version. A price you set in Flightdeck always wins. You can switch catalogue prices off. Then a model with no price you set gets no cost record: its calls count against no budget and appear in no report, and the gateway records the model as unpriced. Every cost record says which price it used.
Which other Zhipu GLM models are there?
- GLM-4.5$0.6 in · $2.2 out · 131K context
- GLM-4.5-Flash$0 in · $0 out · 131K context
- GLM-4.5V$0.6 in · $1.8 out · 64K context
- GLM-4.6$0.6 in · $2.2 out · 205K context
- GLM-4.6V$0.3 in · $0.9 out · 128K context
- GLM-4.6V-Flash$0 in · $0 out · 128K context
- GLM-4.7$0.6 in · $2.2 out · 205K context
- GLM-4.7-Flash$0 in · $0 out · 200K context
- GLM-4.7-FlashX$0.07 in · $0.4 out · 200K context
- GLM-5$1 in · $3.2 out · 205K context
- GLM-5.1$1.4 in · $4.4 out · 200K context
- GLM-5.2$1.4 in · $4.4 out · 1M context
Which models from other providers are similar to GLM-4.5-Air?
These are the closest in context window and input price, one per provider.
- NVIDIA Nemotron Nano 12B v2 VL BF16Amazon Bedrock · $0.2 in · $0.6 out · 131K context
- Qwen-VL MaxAlibaba Qwen · $0.23 in · $0.574 out · 131K context
- GPT OSS 120BGroq · $0.15 in · $0.6 out · 131K context
- Command RCohere · $0.15 in · $0.6 out · 128K context
- Mistral NemoMistral AI · $0.15 in · $0.15 out · 128K context