GLM 5 Turbo
GLM 5 Turbo is a text-based model developed by Z.ai, released in March 2026. It is specifically optimized for fast inference and agent-driven workflows, featuring built-in reasoning and tool-calling capabilities.
GLM 5 Turbo specs and pricing
- Provider: Z.ai
- Released: March 15, 2026
- Context window: 203K tokens
- Max output: 131K tokens
- Input: text
- Output: text
- Price: $1.20 input / $4.00 output per 1M tokens
- Reasoning: yes
- Tool calling: yes
What GLM 5 Turbo is good at
- Automating complex agent-driven workflows
- Tasks requiring multi-step reasoning
- Applications needing frequent tool interaction
To-dos to try with GLM 5 Turbo
- Analyze this multi-step project plan and identify potential bottlenecks for an automated agent.
- Use the provided tool definitions to execute a multi-step data retrieval task.
- Draft a logical sequence of actions to resolve this specific customer support ticket.
FAQ
- What is the primary focus of GLM 5 Turbo? This model is designed for fast inference and strong performance in agent-driven environments.
- Does this model support external tool integration? Yes, GLM 5 Turbo includes native support for tool calling to assist in agent workflows.
- How much does GLM 5 Turbo cost? GLM 5 Turbo costs $1.20 per million input tokens and $4.00 per million output tokens through OpenRouter. In todo.is a typical agent step costs about 3.92 credits ($1 = 100 credits).
- What is the context window of GLM 5 Turbo? GLM 5 Turbo can read up to 203K tokens at once and write up to 131K tokens in one reply.
- Can I use GLM 5 Turbo without coding? Yes. In todo.is you pick GLM 5 Turbo as your agent's model and write to-dos in plain words, on the web, the Android app, WhatsApp or Telegram. No API key needed: credits are included, or you can bring your own key.
JavaScript is required to use the todo.is app.