glm-4.5-air
Common Name: GLM-4.5 Air
ChatGLM
Released on Aug 13, 2025 12:00 AMKnowledge Cutoff Apr 1, 2025 12:00 AMSupportedTool InvocationSupportedReasoningZhipu AI's lightweight GLM-4.5 variant for cost-effective tasks.
Specifications
Context
131.1K
Maximum Output
98.3K
Inputtext
Outputtext
Performance (7-day Average)
Collecting…
Collecting…
Collecting…
Availability Trend (24h)
Pricing
< 32K
Input¥0.88/MTokens
Output¥2.20/MTokens
Cached Input¥0.176/MTokens
< 32K
Input¥0.88/MTokens
Output¥6.60/MTokens
Cached Input¥0.176/MTokens
32K-128K
Input¥1.32/MTokens
Output¥8.80/MTokens
Cached Input¥0.264/MTokens
Performance Metrics (24h)
Similar Models
¥0.55/¥3.30/M
ctx200Kmax128Kavail—tps—
InOutCap
Low-cost, high-speed variant of GLM-4.7 optimized for high-throughput inference at a fraction of the flagship price.
¥1.10/¥3.30/M
ctx128Kmax32Kavail—tps—
InOutCap
Zhipu AI's vision-reasoning model. Processes text, images, video, and files with strong front-end code replication and GUI analysis capabilities.
¥1.10/¥1.10/M
ctx1.0Mmax4Kavail—tps—
InOutCap
GLM-4 variant with extended 1M token context window for processing very long documents.
¥0.88/¥3.08/M
ctx1.0Mmax128Kavail—tps—
Zhipu AI's first natively multimodal GLM-5 series model (320B/18B MoE), served via official Zhipu API, with 1M context and visual coding capabilities.