GLM 5.2
Z.ai's GLM 5.2 is a large-scale reasoning model designed for complex, long-horizon tasks. It features a 1-million-token context window and supports both tool calling and text-based reasoning.
GLM 5.2 specs and pricing
- Provider: Z.ai
- Released: June 16, 2026
- Context window: 1M tokens
- Max output: 944K tokens
- Input: text
- Output: text
- Price: $0.006 input / $7.00 output per 1M tokens
- Reasoning: yes
- Tool calling: yes
What GLM 5.2 is good at
- Long-horizon agent workflows
- Project-level software engineering
- Complex tasks requiring extended reasoning
To-dos to try with GLM 5.2
- Analyze a large codebase to identify architectural inconsistencies across multiple modules.
- Manage a multi-step project plan by tracking dependencies and updating task statuses.
- Synthesize information from an extensive collection of technical documentation to answer specific engineering queries.
FAQ
- What is the primary strength of GLM 5.2? The model is specifically designed for large-scale reasoning and long-horizon workflows.
- Does this model support external tools? Yes, GLM 5.2 includes built-in support for tool calling.
- How much does GLM 5.2 cost? GLM 5.2 costs $0.006 per million input tokens and $7.00 per million output tokens through OpenRouter. In todo.is a typical agent step costs about 1 credits ($1 = 100 credits).
- What is the context window of GLM 5.2? GLM 5.2 can read up to 1M tokens at once and write up to 944K tokens in one reply.
- Can I use GLM 5.2 without coding? Yes. In todo.is you pick GLM 5.2 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.