Z.AI: GLM 4.7

Inference Model ID: z-ai/glm-4.7

Overview

Property	Value
Model Name	Z.AI: GLM 4.7
Model ID	z-ai/glm-4.7
Author	Z.AI
Created	December 22, 2025
Context Length	202,752 tokens
Input Modalities	Text
Output Modalities	Text
Supports Reasoning	Yes
Model Group	Other

Description

GLM-4.7 is Z.AI's latest flagship model, featuring upgrades in two key areas: enhanced programming capabilities and more stable multi-step reasoning/execution.

Pricing

Type	Price
Input	$0.40 per 1M tokens
Output	$1.50 per 1M tokens

Supported Parameters

Core Parameters

Parameter	Description
max_tokens	Maximum number of tokens to generate
temperature	Sampling temperature (default: 1)
top_p	Nucleus sampling probability (default: 0.95)
top_k	Top-k sampling
stop	Stop sequences

Penalty Parameters

Parameter	Description
frequency_penalty	Frequency penalty for token repetition
presence_penalty	Presence penalty for token repetition
repetition_penalty	Repetition penalty

Reasoning Parameters

Parameter	Description
reasoning	Enable reasoning mode
include_reasoning	Include reasoning in response

Tool Parameters

Parameter	Description
tools	List of available tools
tool_choice	Tool selection strategy (supports "auto")

Other Parameters

Parameter	Description
seed	Random seed for reproducibility

Default Values

Parameter	Default
Temperature	1
Top P	0.95
Frequency Penalty	None

Performance

Recent Analytics (Last 2 Days)

Metric	Value
Total Requests	117,074
Total Prompt Tokens	2,032,262,419
Total Completion Tokens	183,036,106
Reasoning Tokens	122,365,409

Related Models

Other models from Z.AI available on LangMart:

Model	ID	Context	Pricing (Input/Output)	Description
GLM 4.6V	z-ai/glm-4.6v	131K	$0.30/$0.90 per M	Multimodal model for visual understanding
GLM 4.6	z-ai/glm-4.6	200K	-	Superior coding, advanced reasoning, agent capabilities
GLM 4.6 (exacto)	z-ai/glm-4.6:exacto	-	-	Exacto variant of GLM 4.6
GLM 4.5	z-ai/glm-4.5	-	-	Previous generation model
GLM 4.5 Air	z-ai/glm-4.5-air	-	-	Lighter variant
GLM 4.5 Air (Free)	z-ai/glm-4.5-air:free	-	Free	Free tier version
GLM 4-32B	z-ai/glm-4-32b-0414	-	-	32B parameter model

Providers

Chutes (Primary Provider)

Property	Value
Adapter	ChutesAdapter
Max Completion Tokens	65,535
Quantization	bf16
Input Price	$0.0000004 per token
Output Price	$0.0000015 per token

Data Policy:

• Allows training on prompts
• Retains prompts
• No external publishing

Features:

• Supports tool choice (auto)
• Returns reasoning content

AtlasCloud (Secondary Provider)

Property	Value
Adapter	AtlasCloudAdapter
Quantization	fp8
Context Length	Same as primary (202,752)

Data Policy:

• No training on prompts
• Does not retain prompts

Features

• Reasoning Tokens: Wrapped in <think> tags
• Multipart Requests: Supported
• Abortable Requests: Supported
• Quick Start Type: Reasoning

Usage Example

curl https://api.langmart.ai/v1/chat/completions \
  -H "Authorization: Bearer $LANGMART_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "z-ai/glm-4.7",
    "messages": [
      {
        "role": "user",
        "content": "Explain quantum computing in simple terms."
      }
    ],
    "temperature": 0.7,
    "max_tokens": 1000
  }'

Reasoning Example

curl https://api.langmart.ai/v1/chat/completions \
  -H "Authorization: Bearer $LANGMART_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "z-ai/glm-4.7",
    "messages": [
      {
        "role": "user",
        "content": "Solve this step by step: What is 15% of 240?"
      }
    ],
    "reasoning": true,
    "include_reasoning": true
  }'

---

Data sourced from LangMart on December 23, 2025