RadixArk · live price
DaisyRose 27B API pricing
DaisyRose 27B is an open-weight multimodal reasoning model from RadixArk, trained from Qwen3.8 27B using reinforcement learning only on long-horizon agent tasks, with no supervised fine-tuning or distillation. It is...
Small and cheap (under $1 per 1M)Tool callingReasoningimage input
- Input
- $0.15
- per 1M tokens
- Output
- $1.88
- per 1M tokens
- Cached input
- $0.037
- per 1M tokens
- Context
- 262K
- 236K max output
List price from OpenRouter, which passes RadixArk's price through without markup. Refreshed hourly. Released November 21, 2026. Model id radixark/daisyrose-27b.
What DaisyRose 27B costs in practice
At list price, before any batch or caching discount.
1,000 chat messages
$1.09
1,000 input + 500 output tokens each
1,000 RAG questions
$2.14
8,000 input + 500 output tokens each
100 coding-agent steps
$0.83
30,000 input + 2,000 output tokens each, no caching
DaisyRose 27B price history
No price change since we started tracking on 2026-11-21. We record prices daily; changes will show here.
DaisyRose 27B price by host
One host serves this model through OpenRouter.
- DeepInfra$0.15 in · $1.88 out · 262K ctx · 100.0% uptime 24h
Where to buy RadixArk credits for less
DaisyRose 27B costs the same per token everywhere it's sold through OpenRouter. What changes is the price of the credits. Live quotes for $100 of usage:
DaisyRose 27B cost calculator
Enter your monthly tokens to price your own usage.
Usage at list price$26.25/ month(quotes below are for $26.00: purchases run from $5.00 to $10,000.00)
Cheaper alternatives to DaisyRose 27B
Other labs' models in the same price range or the one below, cheaper per token.
| Model | Input / 1M | Output / 1M |
|---|---|---|
| MiniMax: MiniMax M3.1 Flash | $0.075 | $0.3 |
| DeepSeek: DeepSeek V4.1 Flash 1017 | $0.15 | $0.6 |
| Anthropic: Claude Haiku 5.5 | $0.1 | $0.5 |
| OpenAI: GPT-6 Luna Pro | $0.1 | $0.5 |
| OpenAI: GPT-6 Luna | $0.1 | $0.5 |
| Qwen: Qwen3.8 Omni Flash | $0.15 | $0.47 |