Zhipu: glm-4.5v:free
glm-4.5v:free
64K context32K outReasoningToolsVisionCacheStructured
Released Aug 11, 2025Knowledge cutoff 2024Updated Aug 11, 2025
A flagship vision-language model based on GLM-4.5-Air (106B total/12B active). It specializes in "Thinking Mode" for complex visual reasoning, multi-page document parsing, and zero-shot GUI automation, matching Gemini 2.5 Pro performance.
Pricing
Input price
$0.00/ 1M tokens
Output price
$0.00/ 1M tokens
Context window 128K tokensCompatible endpoints openaiVendor Zhipu
Performance
Loading performance data...
Usage & Ranking
Loading usage...
Supported parameters
All providers = every upstream serving this model supports it. Some providers = depends on which upstream handles the request. Default = the value sent when you leave the parameter unset.
| Parameter | Providers | Default |
|---|---|---|
| frequency_penalty | Some providers | Not sent by default |
| include_reasoning | All providers | - |
| max_tokens | All providers | - |
| presence_penalty | Some providers | - |
| reasoning | All providers | - |
| repetition_penalty | Some providers | - |
| response_format | All providers | - |
| seed | Some providers | - |
| stop | Some providers | - |
| temperature | All providers | 0.75 |
| tool_choice | All providers | - |
| tools | All providers | - |
| top_k | All providers | - |
| top_p | All providers | Not sent by default |