Overview
GLM 5.1 is Z.ai's flagship foundation model with a 200K context window and up to 128K output tokens. It features multiple thinking modes, function calling, MCP (Model Context Protocol) support, and cache-aware billing for cost-efficient long-context processing.
Key Features
- 200K context window — Process up to 200K tokens per request with 128K max output
- Multiple thinking modes — Covers different task requirements for deeper analysis
- Function calling & MCP — Native tool invocation and Model Context Protocol support for agentic workflows
- Cache-aware billing — 81% cost reduction on cached input tokens ($0.26 vs $1.40 per 1M tokens)
- Structured output — JSON and other structured formats
- OpenAI-compatible API — Drop-in replacement using chat completions format
Pricing
Per Million Tokens
Input Price: $1.40
Input Cache Hit: $0.26
Output Price: $4.40
Parameters
No input schema available.