GLM-4.5 Air FP8
GLM-4.5 Air FP8 is Zhipu AI's language model with a 128K context window, starting at $0.2 / 1M input and $1.10 / 1M output. An FP8-quantized version of the GLM-4.5 Air MoE model, optimized for memory-efficient deployment while preserving agentic reasoning capabilities.
Capabilities
Input1/5
Text✓
Image·
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities3/13
Reasoning·
Adaptive Reasoning·
Function Calling✓
Parallel Function Calling✓
Structured Outputs✓
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·
Pricing by Provider
US Dollar ($)
Per 1M tokens
| Provider | Standard | |
|---|---|---|
| Input $ / 1M | Output $ / 1M | |
| $0.2 | $1.10 | |
Cost Calculator
US Dollar ($)
Preset:
Other Models
| Model | Tier | Released | Context | Input / 1M | Output / 1M |
|---|---|---|---|---|---|
| GLM-5.2 | — | 1.0M | $1.20 | $4.10 | |
| GLM-5V Turbo | — | 200K | $1.20 | $4.00 | |
| GLM-5 Turbo | — | 262K | $1.20 | $4.00 | |
| GLM-5.1 Non-Reasoning | — | — | — | — | — |
| GLM-5 Non-Reasoning | — | — | — | — | — |
| GLM-5 Code | — | — | 200K | $1.20 | $5.00 |
| GLM-4.6V Flash | Flash | 128K | — | — | |
| GLM-4 32B | — | 128K | $0.100 | $0.100 | |
| GLM-4.7 FlashX | — | 200K | $0.060 | $0.400 | |
| GLM-4.7 Non-Reasoning | — | — | — | — | — |