# GLM-4.5-Air API prices

GLM-4.5-Air (glm-air) — 131k context, 131k max output.
17 metered per-token offers from 17 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| ZenMux | $0.1165 | $0.2911 | $0.0233 | 128k |
| submodel | $0.1 | $0.5 | — | 131k |
| NanoGPT | $0.12 | $0.8 | $0.06 | 128k |
| NanoGPT | $0.12 | $0.8 | $0.06 | 128k |
| Hugging Face | $0.13 | $0.85 | — | 131k |
| Kilo Gateway | $0.13 | $0.85 | $0.025 | 131k |
| DevPass (LLM Gateway) | $0.13 | $0.85 | $0.025 | 131k |
| NovitaAI | $0.13 | $0.85 | $0.025 | 131k |
| OpenRouter | $0.13 | $0.85 | $0.025 | 131k |
| Impossibl | $0.2 | $1.1 | $0.03 | 131k |
| LLM Gateway | $0.2 | $1.1 | $0.03 | 128k |
| Merge Gateway | $0.2 | $1.1 | $0.03 | 128k |
| OrcaRouter | $0.2 | $1.1 | $0.03 | 131k |
| Tempr Gateway | $0.2 | $1.1 | $0.03 | 131k |
| Vercel AI Gateway | $0.2 | $1.1 | $0.03 | 128k |
| Z.AI | $0.2 | $1.1 | $0.03 | 131k |
| Zhipu AI | $0.2 | $1.1 | $0.03 | 131k |

## Summary

- Cheapest input: $0.1 per 1M tokens (submodel)
- Cheapest output: $0.2911 per 1M tokens (ZenMux)
- First-party: $1.1 per 1M output tokens (Z.AI)
- Free offers: none
- Subscription plans (not per-token): none
- Released: 2025-07-28
- Inputs: text

## FAQ

### What is the cheapest GLM-4.5-Air API?

As of Oct 4, 2026, ZenMux has the lowest GLM-4.5-Air output price at $0.2911 per 1M tokens, and submodel has the lowest input price at $0.1 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How much does GLM-4.5-Air cost on Z.AI?

Z.AI charges $0.2 per 1M input tokens and $1.1 per 1M output tokens for GLM-4.5-Air.

### How many providers offer GLM-4.5-Air?

17 providers list GLM-4.5-Air on Sovyron; 17 of them sell it at a metered per-token price.

### Is GLM-4.5-Air free?

No provider in the Sovyron catalog lists a free tier for GLM-4.5-Air.

### What is the context window of GLM-4.5-Air?

GLM-4.5-Air supports a 131k-token context window and up to 131k output tokens.

HTML page: https://sovyron.com/models/glm-4-5-air/
Full dataset: https://sovyron.com/data/catalog.json