GLM-4.5-Air pricing and specs
GLM-4.5-Air pricing and specsLighter GLM-4.5 variant for fast coding assistance and cheaper agents
GLM-4.5-Air price per 1M tokens
| Type | ₽ / 1M | $ / 1M |
|---|---|---|
| Input tokens | 16,9 ₽ | $0.2 |
| Output tokens | 92,96 ₽ | $1.1 |
| Cache read | 2,54 ₽ | $0.03 |
| Cache write | 0 ₽ | $0 |
Prices in rubles as of 18.09.2026 at the CBR rate: 1 $ = 84.51 ₽.
GLM-4.5-Air specs and limits
- Context window
- 131K
- Max output
- 98K
- Input
- text
- Output
- text
- Family
- glm-air
- Released
- 2025-07-28
- Updated
- 2025-07-28
- Knowledge cutoff
- 2025-04
- Also known as
- glm air, glm-4.5 air, glm-4.6 air, glm-4.7 air, glm-5 air, glm-5.1 air
What GLM-4.5-Air can do
- ✓Reasoning
- ✓Tool calling
- —Structured output
- —Attachments / files
- —Vision (images)
- ✓Temperature control
- ✓Open weights
GLM-4.5-Air benchmarks
| Benchmark | Score | Metric |
|---|---|---|
| Artificial Analysis Coding Index | 23.8 | index |
| SciCode | 30.6 | percent correct |
| Terminal-Bench Hard | 20.5 | success rate |
Model weights
Frequently asked questions
How much does the GLM-4.5-Air API cost?
Input costs $0.2 per 1M tokens (16.9 ₽) and output costs $1.1 per 1M (92.96 ₽). Zhipu AI bills the prompt and the completion separately, so the price of a call depends on how long both are. Ruble figures use the Bank of Russia rate of 84.51 ₽ per dollar for September 2026.
How much do 1,000 GLM-4.5-Air tokens cost?
List prices are quoted per 1M tokens, so 1,000 tokens cost a thousandth of that: divide $0.2 for input and $1.1 for output by 1,000. The same rates in rubles are 16.9 ₽ and 92.96 ₽ per 1M tokens. Both prompt tokens and completion tokens are billed.
How many tokens does GLM-4.5-Air hold?
The GLM-4.5-Air context window is 131K tokens (131,072). Everything shares that budget: the system prompt, the dialogue history, attached files and the answer the model writes. The figure comes from the Zhipu AI model card as of September 2026.
What are the GLM-4.5-Air limits?
The context window is 131K tokens (131,072) and a single response is capped at 98K tokens, so longer output has to be generated in parts. Rate limits are set by Zhipu AI per account and depend on your plan rather than on the model, so they are not listed here.
How is the GLM-4.5-Air price in rubles calculated?
Providers quote their tariffs in US dollars, so the ruble amounts here are a conversion at the official Bank of Russia rate of 84.51 ₽ per dollar. For GLM-4.5-Air that gives 16.9 ₽ per 1M input tokens and 92.96 ₽ per 1M output tokens. When the rate moves, the ruble price moves with it.
How is GLM-4.5-Air different from other GLM models?
GLM-4.5-Air belongs to the GLM Air family at Zhipu AI. Models in the GLM line differ in context size, price per 1M tokens and supported capabilities, so compare them by the numbers on their cards rather than by the name. Every GLM model is listed on the provider page.
Can GLM-4.5-Air reason?
Yes, GLM-4.5-Air declares a reasoning mode: it works through intermediate steps before it answers. Those steps add output tokens, so a call with a long reasoning chain costs more and takes longer than a plain completion. Capabilities declared for the model: reasoning, tool calling.
What capabilities does GLM-4.5-Air support?
The declared capabilities of GLM-4.5-Air are: reasoning, tool calling. It accepts text as input, and every attachment consumes tokens from the shared context window of 131K tokens. The list comes from the Zhipu AI model card and is refreshed with the catalog as of September 2026.
Does GLM-4.5-Air have open weights?
Yes, GLM-4.5-Air ships with open weights, so it can be downloaded and served on your own hardware instead of being used only through the Zhipu AI API. What you may do with it is set by the license shown on the card. Catalog prices cover hosted API access.