ai.canshu.com
中文
VRAM Calculator Advisor & TCO API Pricing Compare Models Leaderboard GPUs

Search models, GPUs, and tools

↑↓ Navigate · Enter Open · ★ Watchlist prioritized ai.canshu.com
Zhipu AI
Open-Weight Zhipu AI · glm-4.7 · Text

GLM-4.7 Official Specifications, Pricing & Benchmarks

GLM-4.7 (glm-4.7) by Zhipu AI, released 2025-12-22, featuring 204,800 context window, 131,072 max output tokens, and Text input.

📋 GLM-4.7 Official API & System Card Specifications

Verified against official Zhipu AI developer documentation & pricing

API Model ID: glm-4.7

1. Identity & Capabilities

API Spec
API Model ID
glm-4.7
Release Date
2025-12-22
Weight License
Open-Weight (API Spec)
Native Reasoning
✅ Supported
Function Calling & JSON Schema
✅ 原生支持
Batch API 异步批处理
✅ Supported (50% off)

2. Context, Output & Modalities

Limits
Max Context Window
205,000 tokens (205K)
Max Output Tokens
131,072 tokens
Input Modalities
Text
Output Modalities
Text
Direct China Access
✅ Direct CN + RMB
Deployment Mode
Open-Weight + Cloud API

3. Official Pricing & Cache

CNY / 1M
Input / 1M Tokens
¥ 3
Cached Input / 1M
¥ 0.6 -80%
Output / 1M Tokens
¥ 14

🎛️ Official Sampling & Reasoning Parameters

Recommended generation settings & API parameter constraints

Official Reasoning & Tool Config
temperature=0.7 top_p=0.95 max_tokens=65,536

📊 GLM-4.7 Full Benchmark Scorecard

13 public benchmarks · ranks among 154 models · synced 2026-11-20

⚔️ Compare head-to-head

Source: ZeroEval / llm-stats.com (✓ = third-party verified, others vendor-reported).

Closest Self-Hostable Open-Weight Alternatives to GLM-4.7

Open-weight models with full HuggingFace weights for private GPU / Mac deployment

Compare with these →

Frequently Asked Questions

Is GLM-4.7 open-source or proprietary?

GLM-4.7 (glm-4.7) is a proprietary commercial model by Zhipu AI. Weights and internal layer dimensions are undisclosed; it is accessed via cloud API.

What are the context limit and API pricing of GLM-4.7?

GLM-4.7 supports 205K input context and 131,072 max output tokens, priced at ¥3/1M input (¥0.6/1M cached) and ¥14/1M output.