GLM-5.2 API pricing on OpenRouter
Every OpenRouter GLM-5.2 rate we track, compared against 20 providers serving the same model.
The cheapest GLM-5.2 input price we currently track is $0.300/1M on Liquid Inference.
The cheapest GLM-5.2 output price is $0.300/1M on Liquid Inference.
OpenRouter GLM-5.2 rates
Prices per 1M tokens. Batch and cached-input rates are shown where the provider publishes them.
| Mode | Input | Output |
|---|---|---|
| Batch | $0.322/1M | $0.989/1M |
| Standard | $0.620/1M | $2.42/1M |
About GLM-5.2
- Creator
- Z.ai
- Context
- 1.0M
- Modalities
- text
- Open weights
- Yes
GLM-5.2 on other providers
- Liquid Inference$0.300/1M
- Avian Compute$0.495/1M
- Deep Infra$0.563/1M
- Runcrate$0.591/1M
- Heabsy$0.840/1M
- Geodd$0.900/1M
- EcoHash$1.00/1M
- PopNow$1.24/1M
- IO.NET$1.26/1M
- Baseten$1.40/1M
- DigitalOcean$1.40/1M
- Empirio Labs$1.40/1M
- GMI Cloud$1.40/1M
- Morse$1.40/1M
- Novita AI$1.40/1M
- RouterPlus$1.40/1M
- Together AI$1.40/1M
- Prime Intellect$1.54/1M
- VoltageGPU$2.50/1M
About OpenRouter
OpenRouter provides a unified API for accessing hundreds of AI models from multiple providers. It aggregates models from OpenAI, Anthropic, Google, Meta, Mistral, and many others, offering a single endpoint with automatic fallback routing and provider optimization.
Frequently Asked Questions
How much does GLM-5.2 cost on OpenRouter?
OpenRouter serves GLM-5.2 from $0.322 per 1M input tokens, across 2 tracked pricing modes. Prices are collected daily — see the table above for current input, output, and cached-input rates.
Is OpenRouter the cheapest way to run GLM-5.2?
OpenRouter ranks #5 of 20 providers we track serving GLM-5.2 on input price. The cheapest input price right now is on Liquid Inference. The lowest output price is $0.300/1M on Liquid Inference. Rates change often, and throughput, latency and context limits differ between providers — check the comparison above before committing.
Does OpenRouter offer batch or cached pricing for GLM-5.2?
We track 2 GLM-5.2 offerings from OpenRouter. Batch and cached-input rates appear in the table above when the provider publishes them; blank cells mean we have no current figure for that mode.