Skip to content
Not available in this workspace
OpenRouterOpenRouter
© 2026 OpenRouter, Inc

Product

  • Chat
  • Rankings
  • Benchmarks
  • Apps
  • Discover
  • Models
  • Collections
  • Providers
  • Pricing
  • Enterprise
  • Labs

Company

  • About
  • Blog
  • Careers
    Hiring
  • Privacy
  • Terms of Service
  • Support
  • Works With OR
  • Data

Developer

  • Documentation
  • API Reference
  • Developer Platform
  • Status

Connect

  • Discord
  • GitHub
  • LinkedIn
  • X
  • YouTube
Favicon for z-ai

Z.ai: GLM 5

z-ai/glm-5

Model weights
Compare

GLM-5 is Z.ai’s flagship open-source foundation model engineered for complex systems design and long-horizon agent workflows. Built for expert developers, it delivers production-grade performance on large-scale programming tasks, rivaling leading closed-source models. With advanced agentic planning, deep backend reasoning, and iterative self-correction, GLM-5 moves beyond code generation to full-system construction and autonomous execution.

Modalities

In / Out Price

40% off

$0.60 / $1.92per 1M

Context

205K

Released

Feb 11, 2026

Compare

About Z.ai: GLM 5

OpenRouter makes Z.ai: GLM 5 available through a unified, OpenAI-compatible API using the model ID z-ai/glm-5. Requests can be routed across 11 providers, including StreamLake, GMICloud, DeepInfra, Baidu Qianfan, DigitalOcean, SiliconFlow, AtlasCloud, Amazon Bedrock and 3 more, with automatic failover when an endpoint is unavailable.

Z.ai: GLM 5 accepts text and returns text. It has a 204,800-token context window and a maximum output of 128,000 tokens.

On OpenRouter, Z.ai: GLM 5 costs $0.60/M input tokens and $1.92/M output tokens, with separate rates for Cache Read at $0.12/M tokens. Effective pricing can be lower when prompt caching applies. It was released on February 11, 2026.

More models from Z.ai

  • GLM 5.3
  • GLM 5.2
  • GLM 5.1

Frequently asked questions

GLM-5 is Z.ai’s flagship open-source foundation model engineered for complex systems design and long-horizon agent workflows. Built for expert developers, it delivers production-grade performance on large-scale programming tasks, rivaling leading closed-source models.

GLM 5 costs $0.60/M input tokens and $1.92/M output tokens, with separate rates for Cache Read at $0.12/M tokens.

GLM 5 has a 204,800 token context window. It supports up to 128,000 completion tokens.

Yes. GLM 5 accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.

GLM 5 is served by 11 providers on OpenRouter: StreamLake, GMICloud, DeepInfra, Baidu Qianfan, DigitalOcean, SiliconFlow, AtlasCloud, Amazon Bedrock and 3 more. Requests are routed to the best available provider, with automatic failover to the others, and you can pin or exclude providers with provider routing.

GLM 5 was released on February 11, 2026.