[Integrations](https://spiral.ai/integrations) › [opencode](https://spiral.ai/integrations/opencode) › [MiMo V2.6 Pro UltraSpeed](https://spiral.ai/integrations/opencode/mimo-v2-6-pro-ultraspeed)

# How to Use MiMo V2.6 Pro UltraSpeed in opencode

MiMo V2.6 Pro UltraSpeed suits interactive coding and complex text analysis. Xiaomi describes it as retaining MiMo V2.6 Pro performance with up to 20 times faster output, aimed at tasks where response speed matters.

|  |  |
| --- | --- |
| Model | MiMo V2.6 Pro UltraSpeed |
| Available through | OpenRouter |
| Category | LLM |
| Price | Up to $0.046525 per run at the default inputs. $5.655 per 1M input tokens, $11.31 per 1M output tokens. |
| Returns | text, json |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with MiMo V2.6 Pro UltraSpeed in opencode

- Use MiMo V2.6 Pro UltraSpeed to inspect this project's checkout flow. Trace duplicate submissions, propose the smallest fix, implement it, and run the tests that cover the changed behavior.
- Use MiMo V2.6 Pro UltraSpeed to refactor the largest function in this project without changing its public behavior. Explain the dependencies first, then make the change and check relevant edge cases.
- Use MiMo V2.6 Pro UltraSpeed to build an accessible filterable table using this project's existing components. Include keyboard operation, an empty state, and tests for filtering behavior.
- Use MiMo V2.6 Pro UltraSpeed to compare the API specification with this project's implementation. Return JSON containing mismatches, with path, expected behavior, observed behavior, and evidence for each item.
- Use MiMo V2.6 Pro UltraSpeed to investigate the failing tests in this project. Separate the root cause from secondary failures, implement a focused correction, and report which checks passed.

## How to set up MiMo V2.6 Pro UltraSpeed 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 MiMo V2.6 Pro UltraSpeed**: 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": "xiaomi/mimo-v2.6-pro-ultraspeed",
    "input": {
      "messages": [
        {
          "role": "system"
        }
      ]
    }
  }'
```

Then paste one of the prompts above: opencode finds MiMo V2.6 Pro UltraSpeed on Spiral, shows the price and runs it.

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

## MiMo V2.6 Pro UltraSpeed tools and prices

- [Xiaomi: MiMo-V2.6-Pro-UltraSpeed](https://spiral.ai/tools/openrouter/xiaomi/mimo-v2.6-pro-ultraspeed) (OpenRouter): Up to $0.046525 per run at the default inputs. $5.655 per 1M input tokens, $11.31 per 1M output tokens.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| stop |  | — |  |
| tools |  | — |  |
| top_p | 0 to 1 | — |  |
| reasoning |  | — | Reasoning effort; reasoning tokens count toward max_tokens. |
| max_tokens | 1 to 131072 | — | The most output tokens to generate. |
| temperature | 0 to 2 | — |  |

## What can you do with MiMo V2.6 Pro UltraSpeed in opencode?

Turn project requirements into code, refactors, and targeted debugging work with MiMo V2.6 Pro UltraSpeed. Its long context window supports substantial project context, while its coding focus suits iterative changes.

### Refactor a complex function

Ask MiMo V2.6 Pro UltraSpeed to trace behavior, propose a smaller implementation, and identify tests that would expose a regression.

### Build a front-end prototype

Give MiMo V2.6 Pro UltraSpeed a written specification for an interface, including its interactions and acceptance criteria, and request working code.

### Compare lengthy specifications

Have MiMo V2.6 Pro UltraSpeed compare supplied specification text and produce a table of contradictions, changed requirements, and unresolved decisions.

### Classify support conversations

Use MiMo V2.6 Pro UltraSpeed to extract the reported problem, assign a category from a fixed list, and return structured ticket data.

### Extract meeting actions

Turn meeting transcript text into tasks, owners, and deadlines with MiMo V2.6 Pro UltraSpeed. Specify null for details the transcript does not provide.

### Check a mathematical argument

Ask MiMo V2.6 Pro UltraSpeed to inspect a supplied derivation, identify unsupported steps, and test the conclusion against boundary cases.

### Extract records from unstructured text

Give MiMo V2.6 Pro UltraSpeed a record template and source text, then request JSON with explicit types and missing-value rules.

## Overview

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

## MiMo V2.6 Pro UltraSpeed in other agents

- [Amp](https://spiral.ai/integrations/amp/mimo-v2-6-pro-ultraspeed)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/mimo-v2-6-pro-ultraspeed)
- [Claude](https://spiral.ai/integrations/claude-desktop/mimo-v2-6-pro-ultraspeed)
- [Claude Code](https://spiral.ai/integrations/claude-code/mimo-v2-6-pro-ultraspeed)
- [Cline](https://spiral.ai/integrations/cline/mimo-v2-6-pro-ultraspeed)
- [Codex](https://spiral.ai/integrations/codex/mimo-v2-6-pro-ultraspeed)
- [Cursor](https://spiral.ai/integrations/cursor/mimo-v2-6-pro-ultraspeed)
- [Devin](https://spiral.ai/integrations/devin/mimo-v2-6-pro-ultraspeed)
- [dots](https://spiral.ai/integrations/dots/mimo-v2-6-pro-ultraspeed)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/mimo-v2-6-pro-ultraspeed)
- [Gemini](https://spiral.ai/integrations/gemini/mimo-v2-6-pro-ultraspeed)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/mimo-v2-6-pro-ultraspeed)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/mimo-v2-6-pro-ultraspeed)
- [goose](https://spiral.ai/integrations/goose/mimo-v2-6-pro-ultraspeed)
- [Grok](https://spiral.ai/integrations/grok/mimo-v2-6-pro-ultraspeed)
- [Grok Build](https://spiral.ai/integrations/grok-build/mimo-v2-6-pro-ultraspeed)
- [Hermes](https://spiral.ai/integrations/hermes/mimo-v2-6-pro-ultraspeed)
- [Instinct](https://spiral.ai/integrations/instinct/mimo-v2-6-pro-ultraspeed)
- [Manus](https://spiral.ai/integrations/manus/mimo-v2-6-pro-ultraspeed)
- [Muse](https://spiral.ai/integrations/muse/mimo-v2-6-pro-ultraspeed)
- [Muse Code](https://spiral.ai/integrations/muse-code/mimo-v2-6-pro-ultraspeed)
- [n8n](https://spiral.ai/integrations/n8n/mimo-v2-6-pro-ultraspeed)
- [Notion](https://spiral.ai/integrations/notion/mimo-v2-6-pro-ultraspeed)
- [OpenClaw](https://spiral.ai/integrations/openclaw/mimo-v2-6-pro-ultraspeed)
- [Perplexity](https://spiral.ai/integrations/perplexity/mimo-v2-6-pro-ultraspeed)
- [Raycast](https://spiral.ai/integrations/raycast/mimo-v2-6-pro-ultraspeed)
- [VS Code](https://spiral.ai/integrations/vscode/mimo-v2-6-pro-ultraspeed)
- [Windsurf](https://spiral.ai/integrations/windsurf/mimo-v2-6-pro-ultraspeed)
- [Zapier](https://spiral.ai/integrations/zapier/mimo-v2-6-pro-ultraspeed)

## More opencode guides

- [MiMo V2.6 Pro](https://spiral.ai/integrations/opencode/mimo-v2-6-pro)
- [MiMo-V2.5](https://spiral.ai/integrations/opencode/mimo-v2-5)
- [Mi:dm K 3.0 Pro](https://spiral.ai/integrations/opencode/mi-dm-k-3-0-pro)
- [MiMo-V2.5-Pro](https://spiral.ai/integrations/opencode/mimo-v2-5-pro)
- [Magnum v4 72B](https://spiral.ai/integrations/opencode/magnum-v4-72b)
- [MiMo-V2.6 Flash](https://spiral.ai/integrations/opencode/mimo-v2-6-flash)

## Questions about MiMo V2.6 Pro UltraSpeed in opencode

**Can opencode use MiMo V2.6 Pro UltraSpeed?**

Yes. Add Spiral to opencode as an MCP server, and opencode can find and run MiMo V2.6 Pro UltraSpeed like any built-in tool.

**How much does MiMo V2.6 Pro UltraSpeed cost in opencode?**

Up to $0.046525 per run at the default inputs. $5.655 per 1M input tokens, $11.31 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 MiMo V2.6 Pro UltraSpeed in opencode?**

No. Spiral runs MiMo V2.6 Pro UltraSpeed on its own OpenRouter account. You sign in to Spiral once and never paste a key.

**How long does it take to set up MiMo V2.6 Pro UltraSpeed in opencode?**

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

**Does opencode wait while MiMo V2.6 Pro UltraSpeed runs?**

MiMo V2.6 Pro UltraSpeed runs in the background. opencode starts the run, checks on it and gives you the text, json when it's ready.

**What is MiMo V2.6 Pro UltraSpeed best suited for?**

Interactive coding, complex refactoring, and text analysis that requires several reasoning steps are practical fits. Xiaomi positions it for work where response speed matters.

**How does UltraSpeed differ from MiMo V2.6 Pro?**

Xiaomi describes UltraSpeed as retaining MiMo V2.6 Pro performance while producing output up to 20 times faster. Treat that figure as Xiaomi's stated maximum, rather than an expected speedup for every task.

**How much text can MiMo V2.6 Pro UltraSpeed handle?**

Xiaomi lists a 1M-token context window and a maximum output of 128K tokens. Those are token limits, not fixed word or page counts.

**Does JSON mode guarantee the exact structure I request?**

No. Define the required keys, types, nesting, and missing-value rules in your prompt, then validate the result against your intended structure.

**Can I tune temperature while deep thinking is enabled?**

Custom temperature and nucleus-sampling settings are overridden in thinking mode. Use explicit instructions and examples to specify the answer's format and scope.

