GLM 4.5 Air
ChatGLM-4.5-Air-FP8
GLM 4.5 Air on FlexAI: Zhipu AI LLM, ChatGLM License, served via the OpenAI-compatible Token Factory at the live market-tracked rate.
Pricing
Input
$0.125 / M tokens
Output
$0.85 / M tokens
Cached input
$0.0187 / M tokens
Context
128K tokens
API endpoint
/v1/chat/completions
Compatibility
OpenAI
Parameters
~106B MoE (12B active)
License
ChatGLM License
Hardware
2× H100
Quantization
FP8
Estimate your monthly cost
M tokens
M tokens
Cache hit rate25%
Share of input tokens served from prompt cache: repeated system prompts, long documents, and multi-turn context.
7.5M × $0.125/M input$0.94
2.5M × $0.0187/M cached input$0.05
2M × $0.85/M output$1.7
Estimated monthly cost$2.69
Saved vs. no caching$0.26 (9%)
Estimate only, at the current market-tracked rate. Usage-based; no minimums.
Get an API keyQuick Start
GLM-4.5-Air-FP8
from openai import OpenAI
client = OpenAI(
base_url="https://tokens.flex.ai/v1",
api_key="your-api-key",
)
response = client.chat.completions.create(
model="GLM-4.5-Air-FP8",
messages=[
{"role": "user", "content": "Hello!"}
],
)
print(response.choices[0].message.content)