[Integrations](https://spiral.ai/integrations) › [opencode](https://spiral.ai/integrations/opencode) › [Claude Opus Latest](https://spiral.ai/integrations/opencode/claude-opus-latest)

# How to Use Claude Opus Latest in opencode

Claude Opus Latest suits codebase migrations, difficult debugging, and detailed document analysis. Anthropic currently lists Opus 5.5 as its latest Opus model, with improvements over Opus 5 in long coding tasks and written communication.

|  |  |
| --- | --- |
| Model | Claude Opus Latest |
| Available through | Anthropic |
| Category | LLM |
| Price | Up to $0.10686 per run at the default inputs. $5.20 per 1M input tokens, $0.26 per 1M cached input tokens, $6.50 per 1M cache write tokens, $10.40 per 1M 1-hour cache write tokens, $26.00 per 1M output tokens; for a prompt above 200,000 tokens, $10.40 per 1M input tokens, $0.52 per 1M cached input tokens, $13.00 per 1M cache write tokens, $20.80 per 1M 1-hour cache write tokens, $39.00 per 1M output tokens. |
| Returns | text, json |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with Claude Opus Latest in opencode

- Use Claude Opus Latest to investigate the failing tests in this project. Reproduce the failure, identify its cause, make a focused fix, and report the checks you ran.
- Use Claude Opus Latest to review the current diff for bugs. For each finding, give the affected location, a concrete failure scenario, and its impact; omit speculative style comments.
- Use Claude Opus Latest to plan a migration of this project's deprecated dependencies. Read the manifests and affected code, identify compatibility risks, and propose stages with explicit verification criteria.
- Use Claude Opus Latest to refactor the project's most tightly coupled service. Explain the dependency problem, preserve its public behavior, and verify the affected paths.
- Use Claude Opus Latest to implement the feature described in this project's issue notes. Map each acceptance criterion to the relevant code and report which criteria you verified.

## How to set up Claude Opus Latest 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 Claude Opus Latest**: 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": "anthropic",
    "model": "~anthropic/claude-opus-latest",
    "input": {
      "messages": [
        {
          "role": "system"
        }
      ]
    }
  }'
```

Then paste one of the prompts above: opencode finds Claude Opus Latest on Spiral, shows the price and runs it.

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

## Claude Opus Latest tools and prices

- [Claude Opus Latest](https://spiral.ai/tools/anthropic/~anthropic/claude-opus-latest) (Anthropic): Up to $0.10686 per run at the default inputs. $5.20 per 1M input tokens, $0.26 per 1M cached input tokens, $6.50 per 1M cache write tokens, $10.40 per 1M 1-hour cache write tokens, $26.00 per 1M output tokens; for a prompt above 200,000 tokens, $10.40 per 1M input tokens, $0.52 per 1M cached input tokens, $13.00 per 1M cache write tokens, $20.80 per 1M 1-hour cache write tokens, $39.00 per 1M output tokens.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| stop |  | — |  |
| tools |  | — |  |
| reasoning |  | — | Reasoning effort; reasoning tokens count toward max_tokens. |
| max_tokens | 1 to 128000 | — | The most output tokens to generate. On a reasoning model the reasoning tokens count toward it: a cap too low for the effort can end with no answer (finish_reason length). |
| tool_choice |  | — |  |
| response_format |  | — |  |

## What can you do with Claude Opus Latest in opencode?

Claude Opus can help carry a difficult code change across a large project, from investigation through verification. Give it repository context, acceptance criteria, and a clear boundary for the work.

### Migrate an older codebase

Use Claude Opus Latest to plan and carry out a framework or language migration. Specify the behavior to preserve and the checks each stage must pass.

### Trace a difficult bug

Give Claude Opus Latest the failing behavior, relevant code, and reproduction steps. Request a root-cause explanation, a focused fix, and evidence that the fix addresses the failure.

### Review a substantial code change

Ask Claude Opus Latest to inspect a change for concrete defects, explain their impact, and identify the conditions that trigger them.

### Refactor a tangled subsystem

Use Claude Opus Latest to map dependencies and simplify a subsystem while preserving its public behavior. Define the boundaries before requesting edits.

### Build a feature across several components

Give Claude Opus Latest acceptance criteria for a feature spanning application layers. Ask it to implement the change and report which criteria it verified.

### Turn extensive material into a decision memo

Provide Claude Opus Latest with the relevant text and a specific decision. Request alternatives, supporting passages, assumptions, and questions the material leaves unanswered.

### Prepare multilingual explanations

Ask Claude Opus Latest to explain supplied material in the audience's language. Specify terminology, reading level, and which names or technical terms to preserve.

## Overview

- [Anthropic Claude](https://spiral.ai/providers/anthropic)
- [All opencode guides](https://spiral.ai/integrations/opencode)

## Claude Opus Latest in other agents

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

## More opencode guides

- [Claude Opus 5.5](https://spiral.ai/integrations/opencode/claude-opus-5-5)
- [Claude Sonnet 4.6](https://spiral.ai/integrations/opencode/claude-sonnet-4-6)
- [Claude Opus 5](https://spiral.ai/integrations/opencode/claude-opus-5)
- [Claude Sonnet 5](https://spiral.ai/integrations/opencode/claude-sonnet-5)
- [Claude Opus 4.8](https://spiral.ai/integrations/opencode/claude-opus-4-8)
- [Claude Sonnet 5.5](https://spiral.ai/integrations/opencode/claude-sonnet-5-5)

## Questions about Claude Opus Latest in opencode

**Can opencode use Claude Opus Latest?**

Yes. Add Spiral to opencode as an MCP server, and opencode can find and run Claude Opus Latest like any built-in tool.

**How much does Claude Opus Latest cost in opencode?**

Up to $0.10686 per run at the default inputs. $5.20 per 1M input tokens, $0.26 per 1M cached input tokens, $6.50 per 1M cache write tokens, $10.40 per 1M 1-hour cache write tokens, $26.00 per 1M output tokens; for a prompt above 200,000 tokens, $10.40 per 1M input tokens, $0.52 per 1M cached input tokens, $13.00 per 1M cache write tokens, $20.80 per 1M 1-hour cache write tokens, $39.00 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 Anthropic account to use Claude Opus Latest in opencode?**

No. Spiral runs Claude Opus Latest on its own Anthropic account. You sign in to Spiral once and never paste a key.

**How long does it take to set up Claude Opus Latest in opencode?**

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

**Does opencode wait while Claude Opus Latest runs?**

Claude Opus Latest runs in the background. opencode starts the run, checks on it and gives you the text, json when it's ready.

**What is Claude Opus good at?**

Claude Opus is a strong fit for difficult software work: migrations, debugging, refactoring, and code review. Anthropic currently positions Opus 5.5 for long coding tasks and knowledge work.

**How much text can Claude Opus handle?**

The current Opus 5.5 has a 1 million token context window and a standard output limit of 128,000 tokens. These are token limits, so avoid treating them as fixed word counts.

**Can Claude Opus work in multiple languages?**

Yes. Anthropic documents multilingual capabilities for its current models, including Opus 5.5; specify the language and audience you want in the request.

**Which reasoning effort should I choose?**

For the current Opus 5.5, start with medium effort and compare results on representative tasks. Use extra-high or maximum effort when testing shows a useful improvement.

**Can I trust every answer from Claude Opus?**

No. Claude can produce incorrect statements or contradict the supplied context. For research and analysis, request supporting passages and check important claims against the original material.

