# GLM-4.5 API prices

GLM-4.5 (glm) — 131k context, 98k max output.
19 metered per-token offers from 20 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| 302.AI | $0.286 | $1.142 | — | 131k |
| ZenMux | $0.2911 | $1.1645 | $0.0582 | 128k |
| NanoGPT | $0.3 | $1.3 | $0.15 | 128k |
| NanoGPT | $0.3 | $1.3 | $0.15 | 128k |
| Abacus | $0.6 | $2.2 | — | 131k |
| Hugging Face | $0.6 | $2.2 | — | 131k |
| Impossibl | $0.6 | $2.2 | $0.11 | 131k |
| Jiekou.AI | $0.6 | $2.2 | — | 131k |
| Kilo Gateway | $0.6 | $2.2 | $0.11 | 131k |
| DevPass (LLM Gateway) | $0.6 | $2.2 | $0.11 | 131k |
| LLM Gateway | $0.6 | $2.2 | $0.11 | 128k |
| Merge Gateway | $0.6 | $2.2 | $0.11 | 128k |
| NovitaAI | $0.6 | $2.2 | $0.11 | 131k |
| OpenRouter | $0.6 | $2.2 | $0.11 | 131k |
| OrcaRouter | $0.6 | $2.2 | $0.11 | 131k |
| Tempr Gateway | $0.6 | $2.2 | $0.11 | 131k |
| Vercel AI Gateway | $0.6 | $2.2 | $0.11 | 128k |
| Z.AI | $0.6 | $2.2 | $0.11 | 131k |
| Zhipu AI | $0.6 | $2.2 | $0.11 | 131k |

## Summary

- Cheapest input: $0.286 per 1M tokens (302.AI)
- Cheapest output: $1.142 per 1M tokens (302.AI)
- First-party: $2.2 per 1M output tokens (Z.AI)
- Free offers: ModelScope
- Subscription plans (not per-token): none
- Released: 2025-07-28
- Inputs: text

## FAQ

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

As of Oct 4, 2026, 302.AI has the lowest GLM-4.5 output price at $1.142 per 1M tokens, and 302.AI has the lowest input price at $0.286 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

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

Z.AI charges $0.6 per 1M input tokens and $2.2 per 1M output tokens for GLM-4.5.

### How many providers offer GLM-4.5?

20 providers list GLM-4.5 on Sovyron; 19 of them sell it at a metered per-token price.

### Is GLM-4.5 free?

1 provider(s) list a free-tier offer: ModelScope. Free tiers usually have rate limits.

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

GLM-4.5 supports a 131k-token context window and up to 98k output tokens.

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