[Integrations](https://spiral.ai/integrations) › [OpenClaw](https://spiral.ai/integrations/openclaw) › [Mistral Medium 3.5](https://spiral.ai/integrations/openclaw/mistral-medium-3-5)

# How to Use Mistral Medium 3.5 in OpenClaw

Mistral Medium 3.5 handles multi-step coding, research, and structured extraction with a 256k context window. It combines instruction following and reasoning, and outscored Devstral 2 on Mistral's SWE-Bench Verified evaluation.

|  |  |
| --- | --- |
| Model | Mistral Medium 3.5 |
| Available through | OpenRouter |
| Category | LLM |
| Price | Up to $0.040005 per run at the default inputs. $1.95 per 1M input tokens, $9.75 per 1M output tokens. |
| Returns | text, json |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with Mistral Medium 3.5 in OpenClaw

- Every weekday morning, use Mistral Medium 3.5 to summarize updates received since the previous report. Return decisions, blockers, and next actions in under 400 words, with a source link for each item.
- Each hour, use Mistral Medium 3.5 to classify new support messages as billing, technical support, or product feedback. Summarize each in English and draft a response in the customer's original language.
- Every Friday, use Mistral Medium 3.5 with reasoning enabled to compare this week's research updates. Report five supported findings, any contradictions, and unanswered questions, linking each finding to its source.
- After each meeting, use Mistral Medium 3.5 to extract decisions and action items from the transcript supplied by the workflow. Include owners, deadlines, and supporting passages; mark missing details as unknown.
- Each evening, use Mistral Medium 3.5 to turn the day's incident updates into a timeline. Separate confirmed causes from hypotheses and finish with unresolved questions in under 300 words.

## How to set up Mistral Medium 3.5 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 Mistral Medium 3.5**: 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-medium-3-5",
    "input": {
      "messages": [
        {
          "role": "system"
        }
      ]
    }
  }'
```

Then paste one of the prompts above: OpenClaw finds Mistral Medium 3.5 on Spiral, shows the price and runs it.

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

## Mistral Medium 3.5 tools and prices

- [Mistral: Mistral Medium 3.5](https://spiral.ai/tools/openrouter/mistralai/mistral-medium-3-5) (OpenRouter): Up to $0.040005 per run at the default inputs. $1.95 per 1M input tokens, $9.75 per 1M output tokens.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| seed |  | — |  |
| stop |  | — |  |
| tools |  | — |  |
| top_p | 0 to 1 | — |  |
| reasoning |  | — | Reasoning effort; reasoning tokens count toward max_tokens. |
| max_tokens | 1 to 209715 | — | The most output tokens to generate. |

## What can you do with Mistral Medium 3.5 in OpenClaw?

Turn recurring streams of updates into structured digests and triage queues with Mistral Medium 3.5. Define the reporting period, categories, and evidence required for each result.

### Bug fixes across several modules

Trace a reported failure through related code, propose a patch, and check it against a reproduction and regression tests.

### Module refactoring

Refactor a module against explicit behavior requirements, then summarize the changes and test results for review.

### Research briefs with evidence

Combine supplied research into a brief that links conclusions to sources and separates open questions from supported findings.

### Structured record extraction

Turn supplied text into consistent records using a defined schema, examples, and a rule for missing values.

### Multilingual support triage

Classify English, French, Spanish, and German inquiries, summarize the issue in English, and draft a reply in the customer's language.

### Recurring operational digests

Summarize incoming updates into decisions, unresolved issues, and next actions, preserving the source of each item.

### Long-document comparison

Compare supplied reports or specifications within the 256k context window and produce a table of agreements, contradictions, and unanswered questions.

### Test planning and generation

Convert requirements and implementation details into tests covering expected behavior, boundary conditions, and failure cases.

## Overview

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

## Mistral Medium 3.5 in other agents

- [Amp](https://spiral.ai/integrations/amp/mistral-medium-3-5)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/mistral-medium-3-5)
- [Claude](https://spiral.ai/integrations/claude-desktop/mistral-medium-3-5)
- [Claude Code](https://spiral.ai/integrations/claude-code/mistral-medium-3-5)
- [Cline](https://spiral.ai/integrations/cline/mistral-medium-3-5)
- [Codex](https://spiral.ai/integrations/codex/mistral-medium-3-5)
- [Cursor](https://spiral.ai/integrations/cursor/mistral-medium-3-5)
- [Devin](https://spiral.ai/integrations/devin/mistral-medium-3-5)
- [dots](https://spiral.ai/integrations/dots/mistral-medium-3-5)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/mistral-medium-3-5)
- [Gemini](https://spiral.ai/integrations/gemini/mistral-medium-3-5)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/mistral-medium-3-5)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/mistral-medium-3-5)
- [goose](https://spiral.ai/integrations/goose/mistral-medium-3-5)
- [Grok](https://spiral.ai/integrations/grok/mistral-medium-3-5)
- [Grok Build](https://spiral.ai/integrations/grok-build/mistral-medium-3-5)
- [Hermes](https://spiral.ai/integrations/hermes/mistral-medium-3-5)
- [Instinct](https://spiral.ai/integrations/instinct/mistral-medium-3-5)
- [Manus](https://spiral.ai/integrations/manus/mistral-medium-3-5)
- [Muse](https://spiral.ai/integrations/muse/mistral-medium-3-5)
- [Muse Code](https://spiral.ai/integrations/muse-code/mistral-medium-3-5)
- [n8n](https://spiral.ai/integrations/n8n/mistral-medium-3-5)
- [Notion](https://spiral.ai/integrations/notion/mistral-medium-3-5)
- [opencode](https://spiral.ai/integrations/opencode/mistral-medium-3-5)
- [Perplexity](https://spiral.ai/integrations/perplexity/mistral-medium-3-5)
- [Raycast](https://spiral.ai/integrations/raycast/mistral-medium-3-5)
- [VS Code](https://spiral.ai/integrations/vscode/mistral-medium-3-5)
- [Windsurf](https://spiral.ai/integrations/windsurf/mistral-medium-3-5)
- [Zapier](https://spiral.ai/integrations/zapier/mistral-medium-3-5)

## More OpenClaw guides

- [Mistral Medium 3.1](https://spiral.ai/integrations/openclaw/mistral-medium-3-1)
- [Mistral NeMo](https://spiral.ai/integrations/openclaw/mistral-nemo)
- [Mistral Medium 3](https://spiral.ai/integrations/openclaw/mistral-medium-3)
- [Mistral Saba](https://spiral.ai/integrations/openclaw/mistral-saba)
- [Mistral Large 4](https://spiral.ai/integrations/openclaw/mistral-large-4)
- [Mistral Small 3](https://spiral.ai/integrations/openclaw/mistral-small-3)

## Questions about Mistral Medium 3.5 in OpenClaw

**Can OpenClaw use Mistral Medium 3.5?**

Yes. Add Spiral to OpenClaw as an MCP server, and OpenClaw can find and run Mistral Medium 3.5 like any built-in tool.

**How much does Mistral Medium 3.5 cost in OpenClaw?**

Up to $0.040005 per run at the default inputs. $1.95 per 1M input tokens, $9.75 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 Mistral Medium 3.5 in OpenClaw?**

No. Spiral runs Mistral Medium 3.5 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 Medium 3.5 in OpenClaw?**

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

**Does OpenClaw wait while Mistral Medium 3.5 runs?**

Mistral Medium 3.5 runs in the background. OpenClaw starts the run, checks on it and gives you the text, json when it's ready.

**What is Mistral Medium 3.5 best suited for?**

Multi-step coding, research synthesis, and tasks that combine tool use with structured output. Give it a concrete deliverable, such as a tested patch, an evidence table, or extracted records.

**How much context can Mistral Medium 3.5 handle?**

Mistral specifies a 256k-token context window. Treat that as a context limit, not a promise that it can write a 256k-token answer.

**When should I enable reasoning?**

Mistral recommends reasoning for complex prompts and agentic coding. Its recommended temperature with high reasoning effort is 0.7.

**Can Mistral Medium 3.5 work in multiple languages?**

Yes. Supported languages include English, French, Spanish, German, Russian, Chinese, and Japanese; specify the language you want in the result.

**What are Mistral Medium 3.5's weaknesses?**

NVIDIA documents weaker non-agentic benchmark results and more verbose responses than some closed-source competitors. Ask for a fixed length and explicit acceptance criteria, and check generated code with tests.

