[Integrations](https://spiral.ai/integrations) › [OpenClaw](https://spiral.ai/integrations/openclaw) › [DeepSeek V3.2](https://spiral.ai/integrations/openclaw/deepseek-v3-2)

# How to Use DeepSeek V3.2 in OpenClaw

DeepSeek V3.2 suits coding, math, and research that combines reasoning with tools. Unlike DeepSeek V3.2 Speciale, it supports tool calls in both thinking and non-thinking modes.

|  |  |
| --- | --- |
| Model | DeepSeek V3.2 |
| Available through | OpenRouter |
| Category | LLM |
| Price | Up to $0.002036 per run at the default inputs. $0.338 per 1M input tokens, $0.494 per 1M output tokens. |
| Returns | text, json |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with DeepSeek V3.2 in OpenClaw

- Each morning, use DeepSeek V3.2 to review new entries from the incident feed. Group likely duplicates, explain the evidence for each grouping, and suggest one diagnostic check per unresolved incident.
- Every Monday, use DeepSeek V3.2 with thinking enabled to compare new database release announcements from official sources. Report behavior changes relevant to replication and recovery, with links.
- Each day, use DeepSeek V3.2 to investigate unresolved questions from the technical research queue using available search tools. Stop after five searches per question and report any remaining uncertainty.
- Every Friday, use DeepSeek V3.2 to review the week's failed automation runs. Group failures by likely cause, cite the supporting run messages, and rank the next checks by how much uncertainty they resolve.
- Each morning, use DeepSeek V3.2 with thinking disabled to extract decisions, owners, and deadlines explicitly stated in new project updates. Mark missing details as unknown and keep the digest under 400 words.

## How to set up DeepSeek V3.2 in OpenClaw

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

### Use the Spiral skill

1. **Send OpenClaw 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 Spiral's MCP server

1. **Add the server**: On the machine that runs OpenClaw's Gateway:

```bash
openclaw mcp add spiral \
  --url https://api.spiral.ai/mcp \
  --transport streamable-http \
  --auth oauth
```

2. **Sign in**: In Settings › MCP, select Sign in on the Spiral server, sign in to Spiral and click Authorize. No API key.

```bash
openclaw mcp login spiral
```

3. **Reload and check**: A running Gateway may keep its old tool list: restart it, or Save & Publish in the Control UI.

```bash
openclaw mcp reload
openclaw mcp doctor spiral --probe
```

### 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 V3.2**: 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-v3.2",
    "input": {
      "messages": [
        {
          "role": "system"
        }
      ]
    }
  }'
```

Then paste one of the prompts above: OpenClaw finds DeepSeek V3.2 on Spiral, shows the price and runs it.

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

## DeepSeek V3.2 tools and prices

- [DeepSeek: DeepSeek V3.2](https://spiral.ai/tools/openrouter/deepseek/deepseek-v3.2) (OpenRouter): Up to $0.002036 per run at the default inputs. $0.338 per 1M input tokens, $0.494 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 V3.2 in OpenClaw?

DeepSeek V3.2 can turn recurring technical updates into research briefs and diagnostic queues. Define the evidence to collect, the questions to answer, and a stopping point for each run.

### Investigate a failing test

Use DeepSeek V3.2 to connect a failure trace to the relevant code, propose a small fix, and check it against the original failure.

### Review an algorithm

Ask DeepSeek V3.2 to examine correctness, runtime, and edge cases before proposing an alternative implementation.

### Check a math solution

Have DeepSeek V3.2 identify the first unsupported step in a proposed solution and verify the result with a separate calculation.

### Research a technical question

Use DeepSeek V3.2 with search tools to gather primary sources, compare their claims, and produce an answer with links and unresolved questions.

### Compare technical proposals

Give DeepSeek V3.2 the proposals and explicit requirements. Request a comparison that links each recommendation to supporting text and flags missing evidence.

### Triage recurring incidents

Use DeepSeek V3.2 to examine new incident descriptions, identify possible duplicates, and suggest the next diagnostic check for each unresolved issue.

### Check calculations with code

Pair DeepSeek V3.2 with a code execution tool to test formulas, inspect discrepancies, and explain which assumptions affect the result.

## Overview

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

## DeepSeek V3.2 in other agents

- [Amp](https://spiral.ai/integrations/amp/deepseek-v3-2)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/deepseek-v3-2)
- [Claude](https://spiral.ai/integrations/claude-desktop/deepseek-v3-2)
- [Claude Code](https://spiral.ai/integrations/claude-code/deepseek-v3-2)
- [Cline](https://spiral.ai/integrations/cline/deepseek-v3-2)
- [Codex](https://spiral.ai/integrations/codex/deepseek-v3-2)
- [Cursor](https://spiral.ai/integrations/cursor/deepseek-v3-2)
- [Devin](https://spiral.ai/integrations/devin/deepseek-v3-2)
- [dots](https://spiral.ai/integrations/dots/deepseek-v3-2)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/deepseek-v3-2)
- [Gemini](https://spiral.ai/integrations/gemini/deepseek-v3-2)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/deepseek-v3-2)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/deepseek-v3-2)
- [goose](https://spiral.ai/integrations/goose/deepseek-v3-2)
- [Grok](https://spiral.ai/integrations/grok/deepseek-v3-2)
- [Grok Build](https://spiral.ai/integrations/grok-build/deepseek-v3-2)
- [Hermes](https://spiral.ai/integrations/hermes/deepseek-v3-2)
- [Instinct](https://spiral.ai/integrations/instinct/deepseek-v3-2)
- [Manus](https://spiral.ai/integrations/manus/deepseek-v3-2)
- [Muse](https://spiral.ai/integrations/muse/deepseek-v3-2)
- [Muse Code](https://spiral.ai/integrations/muse-code/deepseek-v3-2)
- [n8n](https://spiral.ai/integrations/n8n/deepseek-v3-2)
- [Notion](https://spiral.ai/integrations/notion/deepseek-v3-2)
- [opencode](https://spiral.ai/integrations/opencode/deepseek-v3-2)
- [Perplexity](https://spiral.ai/integrations/perplexity/deepseek-v3-2)
- [Raycast](https://spiral.ai/integrations/raycast/deepseek-v3-2)
- [VS Code](https://spiral.ai/integrations/vscode/deepseek-v3-2)
- [Windsurf](https://spiral.ai/integrations/windsurf/deepseek-v3-2)
- [Zapier](https://spiral.ai/integrations/zapier/deepseek-v3-2)

## More OpenClaw guides

- [DeepSeek V3.1 Terminus](https://spiral.ai/integrations/openclaw/deepseek-v3-1-terminus)
- [DeepSeek V3.2 Exp](https://spiral.ai/integrations/openclaw/deepseek-v3-2-exp)
- [DeepSeek V3.1](https://spiral.ai/integrations/openclaw/deepseek-v3-1)
- [DeepSeek V4 Flash 0423](https://spiral.ai/integrations/openclaw/deepseek-v4-flash-0423)
- [DeepSeek V3 0324](https://spiral.ai/integrations/openclaw/deepseek-v3-0324)
- [DeepSeek V4 Flash 0731](https://spiral.ai/integrations/openclaw/deepseek-v4-flash-0731)

## Questions about DeepSeek V3.2 in OpenClaw

**Can OpenClaw use DeepSeek V3.2?**

Yes. Add Spiral to OpenClaw as an MCP server, and OpenClaw can find and run DeepSeek V3.2 like any built-in tool.

**How much does DeepSeek V3.2 cost in OpenClaw?**

Up to $0.002036 per run at the default inputs. $0.338 per 1M input tokens, $0.494 per 1M output tokens. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your OpenClaw plan is separate.

**Do I need an OpenRouter account to use DeepSeek V3.2 in OpenClaw?**

No. Spiral runs DeepSeek V3.2 on its own OpenRouter account. You sign in to Spiral once and never paste a key.

**How long does it take to set up DeepSeek V3.2 in OpenClaw?**

About two minutes: add the server, then sign in, then reload and check.

**Does OpenClaw wait while DeepSeek V3.2 runs?**

DeepSeek V3.2 runs in the background. OpenClaw starts the run, checks on it and gives you the text, json when it's ready.

**What is DeepSeek V3.2 useful for?**

Coding and math are practical starting points: DeepSeek evaluates V3.2 on both. It also supports tasks that combine reasoning with tool calls, such as investigating a bug or checking sources.

**When should I enable thinking?**

Try thinking for problems with several dependencies, such as debugging or comparing conflicting evidence. Try non-thinking for straightforward extraction, then compare accuracy on your own examples; tool calls work in either mode.

**How much context can DeepSeek V3.2 handle?**

The published model configuration specifies 163,840 token positions. That figure describes context capacity, not a promise that a single answer can contain that many tokens.

**What are DeepSeek V3.2's main weaknesses?**

DeepSeek acknowledges gaps in world knowledge compared with leading proprietary models and identifies token efficiency as a limitation. Supply source material for factual tasks and request a concise final answer.

**How does DeepSeek V3.2 differ from DeepSeek V3.2 Speciale?**

DeepSeek V3.2 supports reasoning alongside tool calls. DeepSeek V3.2 Speciale is designed for deep reasoning and does not support tool calling.

