Spiral gives your agent every tool with one account. Browse the tools →

Codex · LLMReleased 2026-11-18

How to Use DaisyRose 27B in Codex

DaisyRose 27B is built for coding, terminal work, and problems that take several linked steps. It combines image understanding with a 262,144-token context and thinks before answering.

Prompts to try with DaisyRose 27B in Codex

Copy an example into Codex, or ask in your own words.

Use DaisyRose 27B to investigate the failing tests in this project. Reproduce one failure, trace its cause, make a focused fix, and report the verification result.

DaisyRose 27BCodex
Try asking
  • Use DaisyRose 27B to review the current diff. Trace changed behavior through its callers and report only issues with a concrete failure example.

  • Use DaisyRose 27B to add pagination to this project's existing list endpoint. Follow the current conventions, cover empty and final pages, and verify the acceptance criteria.

  • Use DaisyRose 27B to diagnose this project's build failure. Find the first actionable error, make the smallest justified correction, and rerun the relevant build command.

  • Use DaisyRose 27B to plan the database migration described in the issue. Inspect the schema and callers, identify compatibility risks, and write an ordered implementation and rollback plan.

How to set up DaisyRose 27B in Codex

Pick the way that suits you. Each takes about two minutes.

Use Spiral's MCP server

  1. Add the hosted server
    codex mcp add spiral --url https://api.spiral.ai/mcp
  2. Sign in

    Codex opens the browser: sign in to Spiral and click Authorize. No API key. codex mcp list then shows Spiral.

    codex mcp login spiral

Use the Spiral skill

  1. Send Codex this message

    Your agent reads Spiral's skill and sets itself up.

    set up https://spiral.ai/SKILL.md
  2. Sign in or paste a key

    Approve Spiral in the browser, or give the agent a key from the console.

Use the Spiral CLI

  1. Install and sign in

    Installs the Spiral CLI, signs you in and adds its skill to your coding agents.

    npx -y spiral-cli@latest init

Call the Spiral API

  1. Create an API key

    In the console, under API keys.

  2. Run DaisyRose 27B

    One request; the result comes back by polling or a webhook.

    curl https://api.spiral.ai/v1/runs \
      -H "Authorization: Bearer $SPIRAL_API_KEY" \
      -H "Content-Type: application/json" \
      -H "Idempotency-Key: $(uuidgen)" \
      -d '{
        "provider": "openrouter",
        "model": "radixark/daisyrose-27b",
        "input": {
          "messages": [
            {
              "role": "user",
              "content": "Hello!"
            }
          ]
        }
      }'

Then paste one of the prompts above: Codex finds DaisyRose 27B on Spiral, shows the price and runs it.

DaisyRose 27B providers and prices

Spiral runs DaisyRose 27B through OpenRouter. Open a card for today's price, with every fee included.

OpenRouterLLM
RadixArk: DaisyRose 27B
radixark/daisyrose-27b

Settings you can ask for

Ask Codex for any of these in your prompt.

SettingAllowed valuesDefaultDescription
Seeda whole number
Min p0 to 1
Top ka whole number from 0
Top p0 to 1
Max tokens1 to 235929

The most output tokens to generate. On a reasoning model the reasoning tokens count toward it: a cap too low for the effort can end with no answer (finish_reason length).

Temperature0 to 2
Presence penalty-2 to 2
Reasoning effortnone, low, medium, or xhighxhigh

How much the model reasons.

Frequency penalty-2 to 2
Repetition penalty0 to 2

Every API field of RadixArk: DaisyRose 27B is on its tool page: open its card above.

What can you do with DaisyRose 27B in Codex?

Turn a bug report or feature request into code changes with checks against the intended behavior. DaisyRose 27B targets coding and terminal work, making repository investigations a useful place to evaluate it.

Reproduce and fix a software bug

Give DaisyRose 27B the failure, expected behavior, and relevant code. Ask it to reproduce the problem, propose a focused fix, and verify the result.

Implement a feature with acceptance checks

Describe the feature and its constraints, then ask for an implementation and checks tied to each requirement.

Diagnose a failed build

Use compiler output and build logs to investigate a failure. Request the first actionable cause, a proposed correction, and a command that would verify it.

Review a proposed code change

Ask DaisyRose 27B to trace a change through its callers and identify concrete failure paths. Require a reproducible example for each reported issue.

Plan a software migration

Supply the current behavior and target requirements. Request an ordered migration plan with dependency checks, validation criteria, and rollback points.

Explain a technical diagram

Pair an architecture diagram with a specific question. Ask DaisyRose 27B to describe the visible components, trace a request, and flag details the image does not establish.

Questions about DaisyRose 27B in Codex

Can Codex use DaisyRose 27B?

Yes. Add Spiral to Codex as an MCP server, and Codex can find and run DaisyRose 27B like any built-in tool.

How much does DaisyRose 27B cost in Codex?

Up to $0.575085 per run at the default inputs. $0.195 per 1M input tokens, $2.4375 per 1M output tokens. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Codex plan is separate.

Do I need an OpenRouter account to use DaisyRose 27B in Codex?

No. Spiral runs DaisyRose 27B on its own OpenRouter account. You sign in to Spiral once and never paste a key.

How long does it take to set up DaisyRose 27B in Codex?

About two minutes: add the hosted server, then sign in.

Does Codex wait while DaisyRose 27B runs?

DaisyRose 27B runs in the background. Codex starts the run, checks on it and gives you the text, json when it's ready.

What is DaisyRose 27B best suited for?

Its stated focus is coding, terminal tasks, and software engineering. Consider it for debugging, implementation work, and technical problems that require several connected steps.

How much context does DaisyRose 27B support?

The documented context window is 262,144 tokens. Treat that as the context limit, not a promise that one answer can contain that many tokens.

Does DaisyRose 27B generate images?

Its documented output is text. Image understanding lets it reason about visual input; it does not produce image files.

Which sampling settings should I start with?

RadixArk evaluates thinking mode with temperature 1.0, top-p 0.95, top-k 20, and min-p 0, using xhigh reasoning effort. Use these as a starting point when comparing results on your own tasks.

Can I trust DaisyRose 27B to finish difficult terminal tasks correctly?

RadixArk reports 12.0% pass@1 on Terminal-Bench 4.1, so difficult terminal work remains a limitation. Ask for test results and check the finished work before accepting it.

Get started

Start using DaisyRose 27B in Codex

One Spiral account for every tool your agent needs. No subscription; you pay per run.

Paste this into Codex:

Set up Codex

set up https://spiral.ai/SKILL.md
Are you an AI agent? See setup options