[Integrations](https://spiral.ai/integrations) › [opencode](https://spiral.ai/integrations/opencode) › [Mistral Small 3.2 24B](https://spiral.ai/integrations/opencode/mistral-small-3-2-24b)

# How to Use Mistral Small 3.2 24B in opencode

Use Mistral Small 3.2 24B for document questions, structured extraction, and tool-assisted tasks. Compared with Mistral Small 3.1, it follows precise instructions better and produces fewer repetitive answers.

|  |  |
| --- | --- |
| Model | Mistral Small 3.2 24B |
| Available through | OpenRouter |
| Category | LLM |
| Price | Up to $0.001603 per run at the default inputs. $0.13 per 1M input tokens, $0.39 per 1M output tokens. |
| Returns | text, json |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with Mistral Small 3.2 24B in opencode

- Use Mistral Small 3.2 24B to review the current diff for behavior changes. Report only issues supported by the code, with file paths, affected behavior, and a suggested test.
- Use Mistral Small 3.2 24B to investigate the failing test output and relevant implementation. Explain the likely cause, propose the smallest patch, and identify the test that would verify it.
- Use Mistral Small 3.2 24B to compare the project's README with its public functions. List documentation claims that conflict with the code, citing the relevant file for each.
- Use Mistral Small 3.2 24B at temperature 0.15 to classify the project's issue descriptions as bug, feature request, documentation, or unclear. Return JSON with one classification and supporting excerpt per issue.
- Use Mistral Small 3.2 24B to explain the request validation flow in this project. Trace the relevant functions, show where errors are returned, and list any behavior you could not establish from the files.

## How to set up Mistral Small 3.2 24B in opencode

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

### Use Spiral's MCP server

1. **Add the server**: Leave out `--global` to add Spiral to the current project only. No header and no client ID or secret: opencode registers itself with Spiral.

```bash
opencode mcp add spiral --global --url https://api.spiral.ai/mcp
```

2. **Sign in**: Your browser opens. Sign in to Spiral, pick the organization and click Authorize, then return to the terminal. No API key. Inside opencode, `/mcps` starts the same sign-in.

```bash
opencode mcp auth spiral
```

3. **Check it**: Spiral shows as connected.

```bash
opencode mcp list
```

### Use the Spiral skill

1. **Send opencode 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 Mistral Small 3.2 24B**: 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": "mistralai/mistral-small-3.2-24b-instruct",
    "input": {
      "messages": [
        {
          "role": "system"
        }
      ]
    }
  }'
```

Then paste one of the prompts above: opencode finds Mistral Small 3.2 24B on Spiral, shows the price and runs it.

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

## Mistral Small 3.2 24B tools and prices

- [Mistral: Mistral Small 3.2 24B](https://spiral.ai/tools/openrouter/mistralai/mistral-small-3.2-24b-instruct) (OpenRouter): Up to $0.001069 per run at the default inputs. $0.0975 per 1M input tokens, $0.26 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 Mistral Small 3.2 24B in opencode?

Turn project code and documentation into focused explanations, proposed fixes, and structured review notes with Mistral Small 3.2. Give it the relevant files, the expected behavior, and a concrete output format.

### Extract support ticket details

Turn ticket text into JSON containing the issue, affected product, requested action, and supporting excerpt. Require null for information the customer did not provide.

### Answer questions about long documents

Ask focused questions about supplied policy or product documentation. Request the relevant section and a short supporting passage with each answer.

### Classify incoming messages

Sort messages into defined categories such as bug report, feature request, or account question. Include category definitions and a fallback for ambiguous messages.

### Draft multilingual support replies

Draft English, French, or German replies from supplied support policies. Keep product names unchanged and flag questions the policy does not answer.

### Explain code and propose focused fixes

Explain a function, investigate a reported failure, or propose a small patch using supplied code and error output. Request a test that demonstrates the expected behavior.

### Summarize meeting transcripts

Convert a supplied text transcript into decisions, action items, owners, and unresolved questions. Preserve uncertainty when an owner or deadline was not stated.

### Prepare tool-assisted status answers

Use defined lookup tools to obtain task-specific information, then turn the returned results into a concise answer. Keep unavailable information explicit.

### Compare revisions of written policies

Compare two supplied versions and list changed requirements, removed exceptions, and unanswered questions. Cite the relevant sections so a reviewer can check each difference.

## Overview

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

## Mistral Small 3.2 24B in other agents

- [Amp](https://spiral.ai/integrations/amp/mistral-small-3-2-24b)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/mistral-small-3-2-24b)
- [Claude](https://spiral.ai/integrations/claude-desktop/mistral-small-3-2-24b)
- [Claude Code](https://spiral.ai/integrations/claude-code/mistral-small-3-2-24b)
- [Cline](https://spiral.ai/integrations/cline/mistral-small-3-2-24b)
- [Codex](https://spiral.ai/integrations/codex/mistral-small-3-2-24b)
- [Cursor](https://spiral.ai/integrations/cursor/mistral-small-3-2-24b)
- [Devin](https://spiral.ai/integrations/devin/mistral-small-3-2-24b)
- [dots](https://spiral.ai/integrations/dots/mistral-small-3-2-24b)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/mistral-small-3-2-24b)
- [Gemini](https://spiral.ai/integrations/gemini/mistral-small-3-2-24b)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/mistral-small-3-2-24b)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/mistral-small-3-2-24b)
- [goose](https://spiral.ai/integrations/goose/mistral-small-3-2-24b)
- [Grok](https://spiral.ai/integrations/grok/mistral-small-3-2-24b)
- [Grok Build](https://spiral.ai/integrations/grok-build/mistral-small-3-2-24b)
- [Hermes](https://spiral.ai/integrations/hermes/mistral-small-3-2-24b)
- [Instinct](https://spiral.ai/integrations/instinct/mistral-small-3-2-24b)
- [Manus](https://spiral.ai/integrations/manus/mistral-small-3-2-24b)
- [Muse](https://spiral.ai/integrations/muse/mistral-small-3-2-24b)
- [Muse Code](https://spiral.ai/integrations/muse-code/mistral-small-3-2-24b)
- [n8n](https://spiral.ai/integrations/n8n/mistral-small-3-2-24b)
- [Notion](https://spiral.ai/integrations/notion/mistral-small-3-2-24b)
- [OpenClaw](https://spiral.ai/integrations/openclaw/mistral-small-3-2-24b)
- [Perplexity](https://spiral.ai/integrations/perplexity/mistral-small-3-2-24b)
- [Raycast](https://spiral.ai/integrations/raycast/mistral-small-3-2-24b)
- [VS Code](https://spiral.ai/integrations/vscode/mistral-small-3-2-24b)
- [Windsurf](https://spiral.ai/integrations/windsurf/mistral-small-3-2-24b)
- [Zapier](https://spiral.ai/integrations/zapier/mistral-small-3-2-24b)

## More opencode guides

- [Mistral Small 3.1 24B Instruct](https://spiral.ai/integrations/opencode/mistral-small-3-1-24b-instruct)
- [Mistral Small 4](https://spiral.ai/integrations/opencode/mistral-small-4)
- [Mistral Small 3](https://spiral.ai/integrations/opencode/mistral-small-3)
- [Mixtral 8x22B Instruct](https://spiral.ai/integrations/opencode/mixtral-8x22b-instruct)
- [Mistral Saba](https://spiral.ai/integrations/opencode/mistral-saba)
- [Moondream 3 Preview](https://spiral.ai/integrations/opencode/moondream-3-preview)

## Questions about Mistral Small 3.2 24B in opencode

**Can opencode use Mistral Small 3.2 24B?**

Yes. Add Spiral to opencode as an MCP server, and opencode can find and run Mistral Small 3.2 24B like any built-in tool.

**How much does Mistral Small 3.2 24B cost in opencode?**

Up to $0.001603 per run at the default inputs. $0.13 per 1M input tokens, $0.39 per 1M output tokens. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your opencode plan is separate.

**Do I need an OpenRouter account to use Mistral Small 3.2 24B in opencode?**

No. Spiral runs Mistral Small 3.2 24B on its own OpenRouter account. You sign in to Spiral once and never paste a key.

**How long does it take to set up Mistral Small 3.2 24B in opencode?**

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

**Does opencode wait while Mistral Small 3.2 24B runs?**

Mistral Small 3.2 24B runs in the background. opencode starts the run, checks on it and gives you the text, json when it's ready.

**What changed from Mistral Small 3.1?**

Mistral Small 3.2 follows precise instructions better and produces fewer repetitive answers. These improvements make it worth considering for tasks with strict formats and detailed requirements.

**How much context can Mistral Small 3.2 handle?**

Mistral documents a 128k-token context window. Treat that as the context limit, not the length of a single generated answer.

**Which languages does Mistral Small 3.2 support?**

It retains the multilingual capabilities documented for Mistral Small 3.1, including English, French, and German. State the desired response language explicitly when working across languages.

**What temperature should I start with?**

Mistral recommends 0.15. Start there for extraction, classification, and other tasks where you want consistent wording and structure, then evaluate the results on your own examples.

**Can Mistral Small 3.2 return JSON and request tools?**

Yes, it supports JSON output and native function calling. For extraction, specify the exact keys, allowed labels, and how to represent missing information.

