GLM 5V Turbo
GLM 5V Turbo is a multimodal foundation model from Z.ai designed for vision-based coding and agent-driven workflows. It natively processes text, image, and video inputs to perform complex reasoning and long-horizon planning tasks.
GLM 5V Turbo specs and pricing
- Provider: Z.ai
- Released: April 1, 2026
- Context window: 203K tokens
- Max output: 131K tokens
- Input: images, text, video
- Output: text
- Price: $1.20 input / $4.00 output per 1M tokens
- Reasoning: yes
- Tool calling: yes
What GLM 5V Turbo is good at
- Analyzing video and image content for automated tasks
- Complex software development and coding projects
- Multi-step, long-horizon planning and agent-based workflows
To-dos to try with GLM 5V Turbo
- Analyze this 10-minute screen recording of a software bug and identify the exact line of code causing the crash.
- Review these 50 architectural diagrams and write a summary of the structural requirements.
- Plan a multi-step development roadmap for a new web application based on these design mockups.
FAQ
- What types of media can this model process? GLM 5V Turbo natively accepts text, image, and video files as input.
- What is the primary focus of this model? It is built by Z.ai specifically for vision-based coding and executing agent-driven tasks that require complex reasoning.
- How much does GLM 5V Turbo cost? GLM 5V 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 5V Turbo? GLM 5V Turbo can read up to 203K tokens at once and write up to 131K tokens in one reply.
- Can I use GLM 5V Turbo without coding? Yes. In todo.is you pick GLM 5V 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.