GLM 5.1

Zai

Zai's flagship foundation model designed for long-horizon autonomous tasks. GLM-5.1 achieves 58.4 on SWE-Bench Pro, surpassing GPT-5.4, with overall performance aligned with Claude Opus 4.6. Built for sustained autonomous operation on single tasks for up to 8 hours, completing the full loop from planning and execution to iterative optimization. With 203K context, 128K output, thinking capabilities, and tool support, it excels at complex system engineering requiring depth, persistence, and production-grade deliverables.

Try Now

Capabilities

Thinking

Tool Use

Example Use Cases

Complex autonomous engineering tasks

Long-horizon agentic workflows requiring sustained execution

Production-grade code generation and iterative optimization

Technical Specifications

Context Window

202,752 tokens

Max Output

128,000 tokens

Pricing

Token Costs (per 1M tokens)

Cache Miss Input

$1.26

Non-Reasoning Output

$3.96

Cache Read Input

$0.25

Tool Costs (per 1K calls)

Web Search

$15

Code Execution

$0.19