Qwen3.8 27B is an open-weight dense vision-language model from Qwen.
GLM 4.5 Air
GLM-4.5-Air is the lightweight variant of our latest flagship model family, also purpose-built for agent-centric applications.
SharkScore
#178 in Models
Why it scores 36.5
GLM 4.5 Air has a SharkScore of 36.5/100, ranked #178 of 608 in Models (updated 2026-11-19).
Each part compares GLM 4.5 Air with other listings in Models. Evidence covers 87% of the score's weight.
- Adoption
- 34 · 30%
- User reviews
- no data · 25%
- Maintenance
- 1 · 20%
- Trust & transparency
- 80 · 15%
- Momentum
- no data · 10%
Paying never changes this score. How ranking works · method v2026-11-18.2
RankShark review of GLM 4.5 Air
Automated evaluation by RankShark · 18 Nov 2026 · method v1.0 · How we review
We were not paid for this review.
As of 2026-11-18, GLM 4.5 Air is a text model for agent-oriented applications; the measured OpenRouter listing reports a 131,072-token context window and prices of $0.13 per million input tokens and $0.85 per million output tokens.
GLM-4.5-Air is a text-generation model in Z.ai’s GLM-4.5 family. The vendor describes it as a compact model for agent applications, with reasoning and non-thinking modes. It is available through API services and as an open-sourced model under the MIT license. [E1]
Best for
- Developers building agent applications that use text, reasoning, or tool calls. · model card
- Teams looking for a model with a reported 131,072-token context window and per-token OpenRouter pricing. · OpenRouter
Not for
- Applications that require image, audio, or other non-text input or output; the OpenRouter listing specifies text input and output. · OpenRouter
Key features
- Reasoning modes. The vendor says the model supports thinking mode for complex reasoning and tool use, and non-thinking mode for immediate responses. · model card
- Compact model design. The vendor says GLM-4.5-Air has 106 billion total parameters and 12 billion active parameters. · model card
- Open-source release. The vendor says the model is released under the MIT license and can be used commercially and for secondary development. · model card
- Context window. The OpenRouter listing reports a 131,072-token context window; RankShark measured the same figure on 2026-11-18. · OpenRouter
- Tool-use parameters. The OpenRouter listing includes tool_choice and tools among its supported parameters. · OpenRouter
Pros
- The vendor describes separate thinking and non-thinking modes, including support for reasoning and tool use. · model card
- The vendor says the model is MIT-licensed and permits commercial use and secondary development. · model card
- The OpenRouter listing reports per-token input and output prices and a 131,072-token context window. · OpenRouter
Cons
- The OpenRouter listing specifies text input and text output, not image or audio modalities. · OpenRouter
- The OpenRouter listing gives a knowledge cutoff of 2024-12-31. · OpenRouter
- No free plan or free trial stated on the pages we checked.
- Whether customer data is used for model training is not stated on the pages we checked.
Pricing
| Plan | Price | Limits |
|---|---|---|
| OpenRouter token pricing | $0.13 per million input tokens; $0.85 per million output tokens | No monthly plan or allowance stated. The listing reports a 131,072-token context window. |
Checked 18 Nov 2026
- Free plan
- Not stated (checked 18 Nov 2026)
- Free trial
- Not stated (checked 18 Nov 2026)
- Trains on customer data
- Not stated (checked 18 Nov 2026)
- Data retention
- Not stated (checked 18 Nov 2026)
- Data regions
- Not stated (checked 18 Nov 2026)
- Data processing agreement
- Not stated (checked 18 Nov 2026)
- AI models used
- GLM-4.5-Air · model card, OpenRouter
- API
- OpenRouter lists chat completions, completions, messages, and responses endpoints. The model page also points to Z.ai and Zhipu AI API services. · model card, OpenRouter
- SDKs
- Not stated (checked 18 Nov 2026)
- Webhooks
- Not stated (checked 18 Nov 2026)
- Platforms
- OpenRouter; Z.ai API Platform (Global); Zhipu AI Open Platform (Mainland China). · model card, OpenRouter
- Security claims
- No security certification stated (checked 18 Nov 2026)
What we measured
- Context window (OpenRouter listing) · now
- 131,072 tokens
- Price per million tokens (OpenRouter listing) · now
- $0.13 in, $0.85 out
- Package downloads · 30 days
- 1,124,156
How we tested · sources
- Hourly uptime and response-time checks of the product's URL.
- Repository, release and download data from GitHub, npm, PyPI and Hugging Face where they exist.
- We did not sign up, pay, or use the product as a customer.
- model card: https://huggingface.co/zai-org/GLM-4.5-Air · fetched 18 Nov 2026
- OpenRouter: https://openrouter.ai/z-ai/glm-4.5-air · fetched 18 Nov 2026
- 18 Nov 2026: Plans or prices changed on the pricing page.
Something wrong? Report an error with a public link that shows it; corrections re-run the review.
Top alternatives to GLM 4.5 Air
See all- 67.1ModelOpen source
- 65.5
Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per t
ModelOpen source - 64.7
Qwen3.8 Flash is a multimodal reasoning model from Alibaba.
ModelOpen source - 64.3
Qwen3.6 27B is a dense 27-billion-parameter language model from the Qwen Team at Alibaba, released in April 2026.
ModelOpen source