What is Z.ai: GLM 4.7's context window?

Z.ai: GLM 4.7 supports a context window of 200,000 tokens, allowing you to process large documents and maintain long conversations.

How to use Z.ai: GLM 4.7 API via Ofox?

Simply set your base URL to https://api.ofox.run/v1 and use your Ofox API key. The API is OpenAI-compatible — just change the base URL and API key in your existing code.

Z.ai: GLM 4.7

Name: Z.ai: GLM 4.7
Brand: z-ai
Price: 0.39999999999999997 USD
Availability: InStock

Chat

z-ai/glm-4.7

Compare Try in Playground Get started

GLM-4.7 is Z.ai's flagship GLM model released on 2025-12-23, built around advanced reasoning and best-in-class Chinese language understanding. It supports reasoning, function calling (tool use), prompt caching, and web search, letting it plan multi-step tasks and bring in external information when a request calls for it. Context: 200K tokens, output: 128K, leaving room for long documents and extended agent traces. Available via OpenAI and Anthropic protocols through Ofox.

Context Window

200K

Max Output Tokens

128K

Released

2025-12-23

Capabilities

Function CallingReasoningPrompt CachingWeb Search

Available Providers

Z.aiAliyun

Supported Protocols

openaianthropic

Providers

Aliyunprovider.type: "aliyun"

Input Tokens

$0.4/M

Output Tokens

$2.2/M

Cache Read

$0.086/M

$0.11/M

Web Search

$0.01/R

Protocols

openai/v1/chat/completions

anthropic

Z.aiprovider.type: "zai"

Input Tokens

$0.4/M

Output Tokens

$2.2/M

Cache Read

$0.11/M

Web Search

$0.01/R

Protocols

openai/v1/chat/completions

anthropic

Playground

Open in OfoxChat

Code Examples

from openai import OpenAI

client = OpenAI(
    base_url="https://api.ofox.run/v1",
    api_key="YOUR_OFOX_API_KEY",
)

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

print(response.choices[0].message.content)

Benchmarks

LMArena ↗Evaluated as glm-4.7

Z.ai: GLM 4.7 scores 1443 in the Overall category of the LMArena text leaderboard (style control), ranking #64 of 374 models based on 12,095 human preference votes (updated 2026-07-12).

Benchmark scores for glm-4.7 on LMArena
Category	95% CI	Rank	Votes
Overall	1436–1449	#64 of 374	12,095
Hard Prompts	1455–1471	#61 of 374	6,602
Coding	1474–1498	#70 of 369	2,411
Math	1407–1449	#80 of 362	707
Creative Writing	1392–1419	#72 of 372	1,917
Instruction Following	1418–1438	#67 of 374	3,209
Chinese	1465–1509	#57 of 344	683

Source: LMArena · CC BY 4.0 · Updated 2026-07-12 · Methodology ↗ · Ranks compare models within each category of the LMArena text leaderboard (style control). Scores come from third-party human preference evaluations, not from OFOX.