Vision GLM

GLM-4.7

Zhipu AI GLM-4.7 multimodal model

12B
Parameters
128K
Context Window
2.5×
Credit Rate
Starter
Min Tier

Overview

GLM-4.7 is a high-performance multimodal model within the GLM family, engineered for developers requiring robust vision-language integration. With 12 billion parameters and FP16 quantization, it strikes an optimal balance between inference speed and analytical depth. The model supports a massive 128,000-token context window, enabling seamless processing of lengthy documents and complex visual data streams without losing coherence. This architecture makes it particularly effective for tasks involving detailed image analysis, optical character recognition, and contextual reasoning across mixed media inputs.

Accessible through the starter tier on LLM Resayil, GLM-4.7 offers a proprietary license suitable for commercial applications requiring strict compliance and reliability. The 2.5x credit multiplier reflects its advanced multimodal capabilities, providing cost-effective scaling for production environments. Developers should choose this model when building applications that demand precise visual understanding alongside natural language processing, such as automated documentation systems or interactive visual assistants. Its streamlined integration ensures low-latency responses while maintaining high accuracy across diverse operational workflows. This combination of accessibility and power makes it an ideal choice for scaling intelligent features without compromising on performance standards.

Specifications

Display Name GLM-4.7
Family GLM
Category Vision
Parameters 12B
Context Window 128,000 tokens
Quantization FP16
License PROPRIETARY
Min Tier Starter
Status Available

Pricing

2.5×
credits per token
1K 2,500 Credits
10K 25,000 Credits
100K 250,000 Credits
View Pricing Plans

Code Examples

from openai import OpenAI

client = OpenAI(
    base_url="https://llmapi.resayil.io/v1/",
    api_key="YOUR_API_KEY"
)

response = client.chat.completions.create(
    model="glm-4.7",
    messages=[
        {"role": "user", "content": "Hello!"}
    ]
)

print(response.choices[0].message.content)
const response = await fetch(
    "https://llmapi.resayil.io/v1/chat/completions",
    {
        method: "POST",
        headers: {
            "Content-Type": "application/json",
            "Authorization": "Bearer YOUR_API_KEY"
        },
        body: JSON.stringify({
            model: "glm-4.7",
            messages: [
                { role: "user", content: "Hello!" }
            ]
        })
    }
);

const data = await response.json();
console.log(data.choices[0].message.content);
curl https://llmapi.resayil.io/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "glm-4.7",
    "messages": [
      {"role": "user", "content": "Hello!"}
    ]
  }'

Use Cases

Analyzing complex charts and graphs from images
Extracting text from scanned documents using OCR
Describing images for accessibility and content moderation
Processing long documents with embedded images and text
Visual question answering based on uploaded photos

Related Models

Start building with GLM-4.7

Get 1,000 free credits when you sign up — no credit card required.