sophnet/GLM-4.6

sophnet/GLM-4.6

Zhipu AI’s flagship language model supports complex agent tasks and high-precision code generation.
2025-09-30
LLM
Model capability: thinkingModel capability: function_call
Input:
$0.286/1M tokens
Output:
$1.143/1M tokens
Bulk order? Contact your manager for exclusive deals

API Overview

GLM-4.6 is Zhipu AI’s flagship language model, a versatile large-scale model that excels in “longer context and stronger coding and reasoning capabilities.” Its core positioning is as a high-performance inference engine designed to support complex agent tasks and high-precision code generation.

  • Doubled Context Length: The context window has been expanded from 128K to 200K tokens, enabling effortless handling of ultra-long documents and multi-turn complex tasks.
  • Leading Code Generation Capabilities: Outperforms in real-world scenarios such as Claude Code and Kilo Code, delivering more refined front-end page generation.
  • Significantly Enhanced Reasoning: Supports tool calls, with logic reasoning and multi-step task processing capabilities far surpassing those of GLM-4.5.
  • More Powerful Agents: Integrates more seamlessly into search-based and tool-based agent frameworks, ensuring more reliable task execution.
  • Natural Writing Style: Matches human preferences more closely, offering greater immersion in role-playing and creative writing.
  • Overall Superior Performance: Outperforms GLM-4.5 in all eight publicly available benchmarks, rivaling Claude Sonnet 4 and DeepSeek-V3.1-Terminus.

───────────────────────────────────────────────────────────────────

Core Capabilities

📚 200K Ultra-Long Context: Supports ultra-long text understanding and generation, easily handling complex scenarios such as legal and scientific research.

💻 Code Generation Expert: Delivers more precise front-end rendering in real-world applications, significantly outperforming in benchmarks like LCB.

Enhanced Tool-Aided Reasoning: Natively supports calling external tools during reasoning, enabling a seamless “think-action” loop.

🧰 Agent-Friendly Architecture: Deeply adapted to Agent frameworks, making task decomposition and tool scheduling more efficient.

✍️ Human-like Writing Style: Features natural and fluent tone, providing more authentic role-playing and multi-style content generation.

🏆 Multi-dimensional Performance Leadership: Outperforms previous models across all eight benchmarks, firmly placing it among the top-tier models both domestically and internationally.

───────────────────────────────────────────────────────────────────

Related Evaluations

“Claude Sonnet 4.5 vs. GLM-4.6: A Battle of Chinese and Foreign Large Language Models in Programming—Has the Winner Been Decided Yet?”

Playground

Log in to explore more features! Click to Log In

API Analytics

API Reference (1)

API DescriptionAPI EndpointRequest MethodStabilityParameter Description
Chat(SophNet)
POST
Stable
View Details

API Pricing

$
ModelDescriptionContextOfficial Price302.AI Price

sophnet/GLM-4.6

-
128000

Input$0.286 / 1M tokens
Output$1.143 / 1M tokens

Input$0.286/ 1M tokens
Output$1.143/ 1M tokens
Original Price