glm-4-airx

Common Name: GLM-4 AirX

ChatGLM
Released on Feb 17, 2025 12:00 AMSupportedTool Invocation
CompareTry in Chat

Zhipu AI's GLM-4 AirX variant optimized for high-speed inference.

Specifications

Context
8K
Maximum Output
16.4K
Inputtext
Outputtext

Performance (7-day Average)

Collecting…
Collecting…
Collecting…

Pricing

Input¥11.00/MTokens
Output¥11.00/MTokens

Availability Trend (24h)

Performance Metrics (24h)

Similar Models

¥8.80/¥17.60/M
ctx128Kmaxavailtps
InOutCap

Zhipu AI's GLM-4.5 X variant with enhanced performance.

¥5.50/¥24.20/M
ctx200Kmax128Kavailtps
InOutCap

GLM-5-Turbo is the fast variant of GLM-5, optimized for lower latency and cost while retaining strong agentic and coding performance.

¥6.60/¥26.40/M
ctx200Kmax128Kavailtps
InOutCap

GLM-5.1 is Zhipu AI's flagship model aligned with Claude Opus 4.6 in capability, featuring an 8-hour long-horizon agent runtime and top-tier performance on complex engineering tasks.

¥5.50/¥24.20/M
ctx200Kmax128Kavailtps
InOutCap

Multimodal coding base model built on GLM-5. Processes text, images, video, and files for multimodal agentic and coding workflows.