DaisyRose 27B
DaisyRose 27B is RadixArk’s multimodal reasoning model for coding, tool use and long-horizon agent tasks. Built from Qwen3.8-27B using reinforcement learning without supervised fine-tuning or distillation, it accepts text and images and returns text. It supports function calling, JSON-schema output and a 262,144-token context window, with up to 65,536 output tokens. Thinking is on by default; choose low, medium or high effort, or turn it off. The weights are released under Apache 2.0.
- Reasoning
- Vision
- Tool Calling
- Structured Output
Added Nov 20, 2026
Pricing
Auto routing · per 1M tokens- Input
- $0.15
- Output
- $1.88
- Cache read
- $0.0375
Specifications
- Context window
- 262.1K
- Max output
- 65.5K
- Parameters
- 27.8B
Benchmarks
No public benchmark scores for this model yet.
Providers
Choose or restrict providers with the API. Provider-selection prices include the selection markup. Provider selection guide · Pricing API (JSON, USD per 1K tokens)
| $0.15 | $1.88 | $0.0375 | N/A | N/A | |
| $0.15 | $1.88 | $0.0375 | N/A | N/A | |
| $0.157 | $1.97 | $0.0394 | N/A | N/A |
Batch rows for this model use normal routing and cost the same as standard API requests. Set provider in a row to choose a provider.