GLM 4.7 Flash
GLM 4.7 Flash is a 30B-class model developed by Z.ai that focuses on balancing performance with operational efficiency. It is specifically optimized for agentic coding tasks, long-horizon planning, and complex reasoning.
GLM 4.7 Flash specs and pricing
- Provider: Z.ai
- Released: January 19, 2026
- Context window: 200K tokens
- Max output: 118K tokens
- Input: text
- Output: text
- Price: $0.06 input / $0.40 output per 1M tokens
- Reasoning: yes
- Tool calling: yes
What GLM 4.7 Flash is good at
- Complex coding projects
- Multi-step task planning
- Reasoning-heavy workflows
To-dos to try with GLM 4.7 Flash
- Analyze this multi-file codebase and suggest a refactoring plan for the authentication module.
- Break down this high-level project goal into a sequence of actionable technical tasks.
- Debug this script by identifying the logical error in the function execution flow.
FAQ
- What is the primary focus of GLM 4.7 Flash? This model is designed to provide a balance between performance and efficiency, with specific optimizations for coding and long-horizon task planning.
- Does GLM 4.7 Flash support tool calling? Yes, the model is built with native support for tool calling and reasoning capabilities.
- How much does GLM 4.7 Flash cost? GLM 4.7 Flash costs $0.06 per million input tokens and $0.40 per million output tokens through OpenRouter. In todo.is a typical agent step costs about 0.23 credits ($1 = 100 credits).
- What is the context window of GLM 4.7 Flash? GLM 4.7 Flash can read up to 200K tokens at once and write up to 118K tokens in one reply.
- Can I use GLM 4.7 Flash without coding? Yes. In todo.is you pick GLM 4.7 Flash 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.