Try MiniMax FastH3 from Fastvideo →
Sign InStart Building

Task History

Click to see output list

No tasks yet

Go to Models
LLM & ChatActive

zai-org / GLM-4.7-Flash

GLM-4.7-Flash

byzai-org

A chat-based language model optimized for conversational AI tasks with support for custom prompts and session management.

ChatLLMReasoningBf16
Model ID
GLM-4.7-Flash
Provider
zai-org
Updated
1770991218
wiro playground—zai-org/GLM-4.7-Flash
Reset to defaults

Prompt to send to the model.

Sample outputs
Updated 1770991218

GLM-4.7-Flash LLM Chat Model

Overview

GLM-4.7-Flash is a large language model designed for chat-based interactions. It supports customizable prompts, session tracking, and various sampling parameters for fine-tuned responses.

What you can build

  • Chatbots with persistent conversation history
  • Interactive Q&A systems
  • Dialogue-based AI assistants

Inputs

  • Prompt: The input text to generate a response for
  • User ID (optional): Unique identifier for user session tracking
  • Session ID (optional): Identifier for managing multiple user sessions
  • System Prompt (optional): System-level guidance for the model's behavior

Outputs

  • Generated text response based on the provided prompt

Recommended settings

  • Temperature: 0.7 for balanced creativity and coherence
  • Top P: 0.95 for diverse yet relevant outputs
  • Do Sample: Enabled for creative tasks

Limitations

  • Performance depends on input quality and context length
  • Not suitable for real-time applications without optimization

Safety & compliance

  • Designed to avoid harmful, unethical, or illegal content
  • Includes safeguards for socially unbiased and positive responses

API quick start

Run GLM-4.7-Flash with a single API call.

POST https://api.wiro.ai/v1/Run/zai-org/GLM-4.7-Flash
{
  "prompt": "Explain quantum mechanics clearly and con…",
  "user_id": "...",
  "session_id": "...",
  "system_prompt": "You are a helpful, respectful and honest …"
}
View full API docs