Zhipu AI GLM 4.5 Air (free)

GLM 4.5 Air (free) by Zhipu AI excels in the Coding category, where it ranks #146 with a composite score of 73/100. GLM-4.5-Air is the lightweight variant of our latest flagship model family, also purpose-built for agent-centric applications. Like GLM-4.5, it adopts the Mixture-of-Experts (MoE) architecture but with a more compact parameter size. GLM-4.5-Air also supports hybrid inference modes, offering a "thinking mode" for advanced reasoning and tool use, and a "non-thinking mode" for real-time interaction. Users can control the reasoning behaviour with the `reasoning` `enabled` boolean. [Learn more in our docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#enable-reasoning-with-default-config) It is particularly strong in areas highlighted by its top benchmark performance and adoption metrics, making it suitable for both individual developers and enterprise teams looking for a reliable coding solution.

GLM 4.5 Air (free) is priced at $0.00 per million input tokens and $0.00 per million output tokens (USD). Contact the provider for volume discounts and enterprise pricing. Pricing is competitive within the coding category and reflects the model's quality-to-cost ratio.

In the Coding category, GLM 4.5 Air (free) holds rank #146 out of 6 models tracked. Its quality rank is #146 and adoption rank is #146. You can use our comparison tool at /compare to see detailed side-by-side metrics with specific alternatives. Key differentiators include its composite scoring across benchmarks, community sentiment, and real-world adoption rates.

GLM 4.5 Air (free) has been evaluated across 5 different signals. Its strongest areas include Capabilities (50/100), Pricing (30/100), Context Window (81/100). These scores are derived from industry-standard benchmarks, community ratings, and real-world performance metrics. The composite score of 73/100 reflects a weighted combination of all tracked signals.

GLM 4.5 Air (free) is available as a free, open-source model. You can run it locally or use it through various hosting providers. Some API providers may charge for hosted inference, so check individual provider pricing.