DaisyRose 27B is a large language model made by RadixArk, added to the catalog on 21 Nov 2026. It has a context window of 262,144 tokens and costs $0.15 per 1M input tokens and $1.875 per 1M output tokens. It accepts text and images and produces text. Typical uses: summarising long documents, answering questions about images and analyzing text alongside images.
Price checked ยท source: OpenRouter
What DaisyRose 27B is
RadixArk: DaisyRose 27B is an open-weight multimodal reasoning model from RadixArk. It accepts text and images as input and produces text. Its stated context length is 262,144 tokens, and its maximum output is 235,929 tokens. The model supports reasoning, tool use, structured outputs, and response-format controls. The catalog identifies Qwen3.8 27B as its starting model and says DaisyRose was trained with reinforcement learning only on long-horizon agent tasks, without supervised fine-tuning or distillation.
These capabilities suit requests that combine written prompts with image input or call for an organized text response. The context window can hold long prompts and substantial reference material, while the maximum output allows for lengthy text responses. Tool support may be relevant in workflows where tools are made available, although the catalog does not identify specific tools or actions. Structured-output and response-format support can be used when an application needs a particular form of text, but the supported schemas or formats are not specified. Based on the listed inputs and outputs, possible tasks include summarizing documents, discussing image content, and creating structured written responses. The facts do not state image size limits, language coverage, or measured performance, so these properties cannot be inferred from the listing.
Key features
- Accepts text and image inputs and produces text
- Has a context length of 262,144 tokens
- Supports outputs of up to 235,929 tokens
- Supports reasoning and tool use
- Supports structured outputs and response formats
Typical uses
- Summarising long documents
- Answering questions about images
- Analyzing text alongside images
- Producing structured text responses
DaisyRose 27B pricing
US dollars, list price through OpenRouter.
| Item | Standard |
|---|---|
| Input, per 1M tokens | $0.15 |
| Output, per 1M tokens | $1.875 |
| Cached input read, per 1M tokens | $0.0375 |
No price change since it was added on 21 Nov 2026.
| What a task costs | Cost |
|---|---|
| Answer a short question500 in / 300 out | $0.0006 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.0053 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.0083 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.025 |
DaisyRose 27B specifications
| Model id | radixark/daisyrose-27b |
|---|---|
| Version | daisyrose-27b-20261120 |
| Context window | 262,144 tokensAbout 196,608 English words |
| Max output | 235,929 tokens |
| Knowledge cutoff | Not published |
| Added to catalog | 21 Nov 2026 |
| Input types | text, image |
|---|---|
| Output types | text |
| Tool calling | Yes |
| Structured outputs | Yes |
| Reasoning effort control | Yes |
| Content moderation | Not applied by provider |
Sample outputs
The same prompts are given to every model, and the unedited output is shown with the date it was produced. Upend does not publish leaderboard scores it did not run.
No output has been recorded for DaisyRose 27B yet.