[Integrations](https://spiral.ai/integrations) › [Muse](https://spiral.ai/integrations/muse) › [DeepSeek R1 0528](https://spiral.ai/integrations/muse/deepseek-r1-0528)

# How to Use DeepSeek R1 0528 in Muse

Use DeepSeek R1 0528 for math problems, coding, and logic tasks that need careful reasoning. Compared with the original DeepSeek R1, it improves front-end generation and adds JSON output and function calling.

|  |  |
| --- | --- |
| Model | DeepSeek R1 0528 |
| Available through | OpenRouter |
| Category | LLM |
| Price | Up to $0.011472 per run at the default inputs. $0.65 per 1M input tokens, $2.795 per 1M output tokens. |
| Returns | text, json |
| Runs | In the background |
| Setup | About 2 minutes, with a Spiral API key |

## Prompts to try with DeepSeek R1 0528 in Muse

- Use DeepSeek R1 0528 to solve this problem: a rectangle has perimeter 50 meters and area 150 square meters. Find its dimensions and verify both conditions.
- Use DeepSeek R1 0528 to plan 12 workshops across three rooms and four time slots. Each workshop needs one slot; two instructors each teach three workshops and cannot overlap. Ask for the instructor assignments before scheduling.
- Use DeepSeek R1 0528 to compare binary search and linear search for a sorted list of one million numbers. Explain the assumptions, worst-case work, and when sorting would change the decision.
- Use DeepSeek R1 0528 with a temperature of 0.6 to check this argument: all approved requests are logged; some logged requests failed; therefore some approved requests failed. Give a counterexample if it is invalid.
- Use DeepSeek R1 0528 to compare a four-day rollout with a two-week rollout. Ask me for staffing, dependencies, and acceptance criteria, then return a decision table with unresolved assumptions.

## How to set up DeepSeek R1 0528 in Muse

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

### Use the Muse connector

1. **Create an API key**: Create one under API keys in the Spiral console.

2. **Send Muse this message**: Muse reads Spiral's skill and asks for an API key.

```text
set up https://spiral.ai/SKILL.md
```

3. **Give Muse the key**: Paste the key when Muse asks for it, never in the chat itself.

### Use the Spiral skill

1. **Send Muse 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.

```bash
npx -y spiral-cli@latest init
```

### Call the Spiral API

1. **Create an API key**: In the console, under API keys.

2. **Run DeepSeek R1 0528**: One request; the result comes back by polling or a webhook.

```bash
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": "deepseek/deepseek-r1-0528",
    "input": {
      "messages": [
        {
          "role": "system"
        }
      ]
    }
  }'
```

Then paste one of the prompts above: Muse finds DeepSeek R1 0528 on Spiral, shows the price and runs it.

Setup guide in the docs: https://spiral.ai/docs/quickstarts/muse

## DeepSeek R1 0528 tools and prices

- [DeepSeek: R1 0528](https://spiral.ai/tools/openrouter/deepseek/deepseek-r1-0528) (OpenRouter): Up to $0.0122 per run at the default inputs. $0.7423 per 1M input tokens, $2.9718 per 1M output tokens.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| seed |  | — |  |
| stop |  | — |  |
| min_p | 0 to 1 | — |  |
| tools |  | — |  |
| top_k | 0 to … | — |  |
| top_p | 0 to 1 | — |  |

## What can you do with DeepSeek R1 0528 in Muse?

Work through mathematical problems and decisions with competing constraints using DeepSeek R1 0528. Give it the relevant facts and ask for a concise explanation, a checked result, and any assumptions that remain.

### Diagnose a difficult bug

Give DeepSeek R1 0528 the relevant code, failing input, and expected behavior. Ask for a minimal reproduction and a proposed fix to test.

### Choose an algorithm

Compare approaches against concrete input sizes, memory limits, and edge cases. Request an implementation and a complexity analysis.

### Check a mathematical solution

Supply the problem and a proposed solution. Ask it to check assumptions, identify invalid steps, and verify the result by another method.

### Draft a front-end component

Describe the component's states, interactions, and accessibility requirements. Generate code, then inspect the rendered result and test its controls.

### Find conflicting requirements

Provide a numbered specification and ask which rules contradict each other. Request a concrete example for each conflict.

### Compare constrained plans

Provide the available choices, hard constraints, and decision criteria. Ask for a recommendation with the assumptions that could change it.

### Turn analysis into JSON

Ask for a structured decision record containing the conclusion, supporting evidence, and unresolved questions. Validate the returned JSON before using it downstream.

## Overview

- [OpenRouter](https://spiral.ai/providers/openrouter)
- [All Muse guides](https://spiral.ai/integrations/muse)

## DeepSeek R1 0528 in other agents

- [Amp](https://spiral.ai/integrations/amp/deepseek-r1-0528)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/deepseek-r1-0528)
- [Claude](https://spiral.ai/integrations/claude-desktop/deepseek-r1-0528)
- [Claude Code](https://spiral.ai/integrations/claude-code/deepseek-r1-0528)
- [Cline](https://spiral.ai/integrations/cline/deepseek-r1-0528)
- [Codex](https://spiral.ai/integrations/codex/deepseek-r1-0528)
- [Cursor](https://spiral.ai/integrations/cursor/deepseek-r1-0528)
- [Devin](https://spiral.ai/integrations/devin/deepseek-r1-0528)
- [dots](https://spiral.ai/integrations/dots/deepseek-r1-0528)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/deepseek-r1-0528)
- [Gemini](https://spiral.ai/integrations/gemini/deepseek-r1-0528)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/deepseek-r1-0528)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/deepseek-r1-0528)
- [goose](https://spiral.ai/integrations/goose/deepseek-r1-0528)
- [Grok](https://spiral.ai/integrations/grok/deepseek-r1-0528)
- [Grok Build](https://spiral.ai/integrations/grok-build/deepseek-r1-0528)
- [Hermes](https://spiral.ai/integrations/hermes/deepseek-r1-0528)
- [Instinct](https://spiral.ai/integrations/instinct/deepseek-r1-0528)
- [Manus](https://spiral.ai/integrations/manus/deepseek-r1-0528)
- [Muse Code](https://spiral.ai/integrations/muse-code/deepseek-r1-0528)
- [n8n](https://spiral.ai/integrations/n8n/deepseek-r1-0528)
- [Notion](https://spiral.ai/integrations/notion/deepseek-r1-0528)
- [OpenClaw](https://spiral.ai/integrations/openclaw/deepseek-r1-0528)
- [opencode](https://spiral.ai/integrations/opencode/deepseek-r1-0528)
- [Perplexity](https://spiral.ai/integrations/perplexity/deepseek-r1-0528)
- [Raycast](https://spiral.ai/integrations/raycast/deepseek-r1-0528)
- [VS Code](https://spiral.ai/integrations/vscode/deepseek-r1-0528)
- [Windsurf](https://spiral.ai/integrations/windsurf/deepseek-r1-0528)
- [Zapier](https://spiral.ai/integrations/zapier/deepseek-r1-0528)

## More Muse guides

- [DeepSeek Pro Latest](https://spiral.ai/integrations/muse/deepseek-pro-latest)
- [DeepSeek V3](https://spiral.ai/integrations/muse/deepseek-v3)
- [DeepSeek Flash Latest](https://spiral.ai/integrations/muse/deepseek-flash-latest)
- [DeepSeek V3 0324](https://spiral.ai/integrations/muse/deepseek-v3-0324)
- [DaisyRose 27B](https://spiral.ai/integrations/muse/daisyrose-27b)
- [DeepSeek V3.1](https://spiral.ai/integrations/muse/deepseek-v3-1)

## Questions about DeepSeek R1 0528 in Muse

**Can Muse use DeepSeek R1 0528?**

Yes. Add Spiral to Muse as an MCP server, and Muse can find and run DeepSeek R1 0528 like any built-in tool.

**How much does DeepSeek R1 0528 cost in Muse?**

Up to $0.011472 per run at the default inputs. $0.65 per 1M input tokens, $2.795 per 1M output tokens. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Muse plan is separate.

**Do I need an OpenRouter account to use DeepSeek R1 0528 in Muse?**

You need no OpenRouter account. Muse uses one Spiral API key for every tool, and Spiral runs DeepSeek R1 0528 on its own OpenRouter account.

**How long does it take to set up DeepSeek R1 0528 in Muse?**

About two minutes: create an API key, then send Muse this message, then give Muse the key.

**Does Muse wait while DeepSeek R1 0528 runs?**

DeepSeek R1 0528 runs in the background. Muse starts the run, checks on it and gives you the text, json when it's ready.

**What is DeepSeek R1 0528 good at?**

Math, programming, and general logic are its clearest fits. Try it for an algorithm explanation, a difficult bug, or a decision with several constraints.

**What changed from the original DeepSeek R1?**

DeepSeek reports improved front-end generation and reduced hallucinations. R1 0528 also adds JSON output and function calling.

**What temperature should I use?**

Start at 0.6. DeepSeek recommends staying between 0.5 and 0.7 to reduce endless repetition and incoherent responses.

**Can I trust its factual answers?**

Verify factual claims against sources. DeepSeek's own SimpleQA results fell from 30.1 for the original R1 to 27.8 for R1 0528, so better reasoning does not guarantee better factual recall.

**How much context can DeepSeek R1 0528 handle?**

DeepSeek documents 128K tokens for the open-weight model. That is a context capacity, not a promise of a 128K-token answer.

