🎁 Sign up, get $1. Join Discord, get $5！
Models
Experience Center
Activity
Docs
Resource
Console
C

GLM 5.3 Flash

Z.aiModel IDglm-5.3-flash
C

GLM 5.3 Flash

Z.aiModel IDglm-5.3-flash

GLM-5.3-Flash was released by Z.ai in August 2026. The model is the first natively multimodal model in the GLM-5 series, with 320B total parameters, 18B active parameters, hybrid attention, and support for text, image, and video inputs.

ModeText / Image / Audio / Video → Text
Input price$0.15 / 1M tokens
Output price$0.499999999999999 / 1M tokens
Context length1048576 tokens

Capabilities & limits

Use cases
Not available
Model capabilities
Not available
Model Brand
Z.ai
Input modality
Text / Image / Audio / Video
Output modality
Text
Max output
131072 tokens

Pricing

ProviderBilling typePrice summary
C
ChatGLM-Custom
Per token
Input price$0.15per 1M tokens
Completion price$0.499999999999999per 1M tokens
Cache read price$0.03per 1M tokens
Cache write price—
C
ChatGLM-Balanced
Per token
Input price$0.15per 1M tokens
Completion price$0.499999999999999per 1M tokens
Cache read price$0.03per 1M tokens
Cache write price—

Integration

Code Example

curl http://127.0.0.1:4179/v1/chat/completions \
  -H "Authorization: Bearer <YOUR_API_KEY>" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "glm-5.3-flash",
    "messages": [
      {
        "role": "user",
        "content": "Hello"
      }
    ]
  }'

Replace <YOUR_API_KEY> with the API key generated on your token management page.

Authentication

All requests must include the Authorization: Bearer <TOKEN> header.

Endpoint Path

POST
openai

Supported Parameters

ParameterTypeDefaultDescription
string-
string-
string-
string-
string-
string-
string-

Rate Limits

RPM

No rate limits configured

RPM = requests per minute.