DaisyRose 27B
DaisyRose 27B is an open-weight multimodal model developed by RadixArk, built from Qwen3.8 27B using reinforcement learning focused on long-horizon agent tasks. It supports both text and image inputs and is designed specifically for complex reasoning and tool-calling applications.
DaisyRose 27B specs and pricing
- Provider: RadixArk
- Released: November 21, 2026
- Context window: 262K tokens
- Max output: 236K tokens
- Input: text, images
- Output: text
- Price: $0.15 input / $1.88 output per 1M tokens
- Reasoning: yes
- Tool calling: yes
What DaisyRose 27B is good at
- Complex multi-step reasoning tasks
- Analyzing images alongside text data
- Executing long-horizon agent workflows
To-dos to try with DaisyRose 27B
- Analyze this architectural diagram and outline the steps required to implement the system.
- Review these five linked documents and create a project plan based on the goals identified in each.
- Use the provided search tool to find current data and summarize the findings into a report.
FAQ
- What is the primary focus of DaisyRose 27B? The model is specifically trained for long-horizon agent tasks and complex reasoning.
- Can this model process images? Yes, DaisyRose 27B is a multimodal model that accepts both text and image inputs.
- How much does DaisyRose 27B cost? DaisyRose 27B costs $0.15 per million input tokens and $1.88 per million output tokens through OpenRouter. In todo.is a typical agent step costs about 0.68 credits ($1 = 100 credits).
- What is the context window of DaisyRose 27B? DaisyRose 27B can read up to 262K tokens at once and write up to 236K tokens in one reply.
- Can I use DaisyRose 27B without coding? Yes. In todo.is you pick DaisyRose 27B 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.