GLM-4.5 Air
zhipu/glm-4.5-airGenuinely free and genuinely useful, the open on-ramp to the GLM family for every developer.
Model overview
Context window
128K
tokens
Input price
—
quoted on request
Output price
—
quoted on request
Weekly volume
—
tokens / week
Open weights
Yes
self-hostable
Capabilities
3
of 11 tags
Description
GLM-4.5 Air is a language model from Zhipu AI. Webparam does not stock this model yet and can source it on request — tell us what you need it for and we will come back with availability and a price. Zhipu AI’s stated focus is open agentic GLM family. Its mean it can also be self-hosted under its licence.
Capabilities
- Tool calling
- Calls functions you define and returns their arguments as structured data, the basis of agents.
- Streaming
- Emits tokens as they are generated, so answers appear progressively rather than all at once.
- Open weights
- The parameters are published, so the model can be inspected, fine-tuned and self-hosted under its licence.
Strengths & weaknesses
Strengths
- Free at point of use
- Real tool-calling support
- Open weights
Weaknesses
- Rate limits apply on free tier
- Quality ceiling below paid siblings
Pricing
| Rate | Price | Unit |
|---|---|---|
| Input | — quoted on request | — |
| Output | — quoted on request | — |
This model is not provisioned yet; the rate is quoted on request.
Context window
128Ktokens
covers prompt and response together, so a long input leaves less room for the answer.
Supported features
| Feature | Support |
|---|---|
| Tool calling | Supported |
| JSON mode | Not supported |
| Streaming | Supported |
| Vision input | Not supported |
| Audio input | Not supported |
| Long context | Not supported |
| Open weights | Supported |
| Reasoning | Not supported |
| Fine-tunable | Not supported |
| Batch | Not supported |
| Caching | Not supported |
Example use cases
Prototyping
Learning
Low-stakes automation
Comparison
Compare against anything →| Attribute | GLM-4.5 Air | Nemotron Super | GLM-4.6 |
|---|---|---|---|
| Context window | 128K | 128K | 200K |
| Input price | R0.00 | R0.00 | R0.00 |
| Output price | — not charged | — not charged | — not charged |
| Tool calling | Supported | Supported | Supported |
| JSON mode | Not supported | Not supported | Supported |
| Vision input | Not supported | Not supported | Not supported |
| Open weights | Supported | Supported | Supported |
| Prompt caching | Not supported | Not supported | Supported |
Best value in each row is highlighted. Blank cells are facts the supplier does not publish, not zeroes.
Provider information
View Zhipu AI →Zhipu AI · 智谱AI · Beijing, China · est. 2019
Born from Tsinghua University research, Zhipu's GLM family became the open ecosystem's agentic specialist: models tuned for tool use and multi-step work, released under permissive licences. Its free Air tier made capable open models accessible to every developer.
Recent releases
Documentation
Frequently asked questions
Input is billed at R0.00 per 1M tokens, and there is no separate output charge. Every figure on this page is an illustrative placeholder.
Yes. GLM-4.5 Air's parameters are published, so it can be downloaded, inspected, fine-tuned and self-hosted under its licence. Self-hosting trades per-token pricing for infrastructure you run.
Prompt and response share one window: GLM-4.5 Air accepts up to 128K tokens in total, so a long input leaves less room for the answer. The median across language models is 256K. Recall is strongest well inside the limit. Test at your real prompt depth before relying on the ceiling.
Nemotron Super is the closest neighbour in the catalogue, with 128K of context at R0.00 per 1M tokens in. Put both in a comparison before wiring a fallback chain, so the trade-off is a decision rather than a default.