[Integrations](https://spiral.ai/integrations) › [Muse Code](https://spiral.ai/integrations/muse-code) › [OpenAI documentation search](https://spiral.ai/integrations/muse-code/openai-documentation-search)

# How to Use OpenAI documentation search in Muse Code

Returns search results from OpenAI's public documentation service. Use it to locate the guide or reference page that answers a question before reading the page itself.

|  |  |
| --- | --- |
| Model | OpenAI documentation search |
| Available through | Alexandria |
| Category | Developer |
| Price | $0.00873 per call. |
| Returns | json |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with OpenAI documentation search in Muse Code

- Use OpenAI documentation search to look this up and give me the result as a table. Save the result in ./assets.
- Pull the latest numbers from OpenAI documentation search and tell me what changed since last week.
- Check OpenAI documentation search and summarize what you find in three bullet points.
- Pull the newest data from OpenAI documentation search and give me the result as a table.
- Check OpenAI documentation search every morning and tell me only when something changed.

## How to set up OpenAI documentation search in Muse Code

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

### Use Spiral's MCP server

1. **Install Muse Code**

```bash
curl -fsSL https://dev.meta.ai/install.sh | bash
```

2. **Ask Muse to add the server**: Start `muse` and ask:

```text
Add the Spiral MCP server at https://api.spiral.ai/mcp
```

3. **Sign in**: In your terminal, run:

```bash
muse mcp login spiral
```

### Use the Spiral skill

1. **Send Muse Code 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 OpenAI documentation search**: 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": "alexandria",
    "model": "developers-openai-com/developer-docs/search_docs",
    "input": {
      "query": "<query>"
    }
  }'
```

Then paste one of the prompts above: Muse Code finds OpenAI documentation search on Spiral, shows the price and runs it.

Setup guide in the docs: https://spiral.ai/docs/quickstarts/muse-code

## OpenAI documentation search tools and prices

- [OpenAI developer docs · Search docs](https://spiral.ai/tools/alexandria/developers-openai-com/developer-docs/search_docs) (Alexandria): $0.00873 per call.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| site | api, all | — | api (default): developers.openai.com and platform.openai.com hits; all: every host the server indexes. |
| limit | 1 to 50 | — | Hits requested from the server (default 10). Filtering by site can return fewer. |
| cursor |  | — | next_cursor from a previous call with the same query and limit. |

## What can you do with OpenAI documentation search in Muse Code?

Produce an OpenAI integration review tied to the project's actual requests and model choices. A coding agent can compare those choices with official specifications, reference fields, guides, and dated announcements before proposing edits.

### Plan a Chat Completions migration

Build a migration checklist from dated API changes, request and response definitions, model capabilities, retirement notices, and published billing categories. Link each proposed code change to the relevant guide.

### Write a model selection decision

Evaluate models for a document extraction application using catalog entries, specifications, endpoint definitions, lifecycle notices, billing units, and implementation guides. Include recent announcements that affect the decision.

### Check a Responses API implementation

Compare a request builder and response parser with the documented method, then read the guides for the features the application uses. Check model specifications and dated changes when behavior depends on the selected model.

### Prepare a release readiness review

Before shipping an OpenAI integration, review its selected models, documented limits, API schemas, lifecycle status, and billing assumptions. Use the changelog and guides to identify documentation changes that need engineering review.

### Maintain an internal API reference

Update an engineering reference with documented request parameters, response fields, and explanations from official guides. Add dated changelog entries when they explain a change in the reference.

### Check workload sizing assumptions

Compare candidate models' context, input, and output limits with the application's expected document sizes. Review the published token billing categories and relevant guides before building an estimate.

### Prepare retirement handoff briefs

Turn announced shutdowns into engineering handoff briefs with affected model IDs, proposed replacements, specification differences, schema checks, and billing considerations. Include migration guides and related announcements.

### Investigate request compatibility errors

Check a failing OpenAI request against the method reference and selected model's specifications. Read the relevant guide and dated announcements to identify documented compatibility changes.

## Overview

- [Alexandria](https://spiral.ai/providers/alexandria)
- [All Muse Code guides](https://spiral.ai/integrations/muse-code)

## OpenAI documentation search in other agents

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

## More Muse Code guides

- [OpenAI documentation page](https://spiral.ai/integrations/muse-code/openai-documentation-page)
- [OpenAI model catalog](https://spiral.ai/integrations/muse-code/openai-model-catalog)
- [OpenAI API endpoint reference](https://spiral.ai/integrations/muse-code/openai-api-endpoint-reference)
- [OpenAI model deprecations](https://spiral.ai/integrations/muse-code/openai-model-deprecations)
- [OpenAI API changelog](https://spiral.ai/integrations/muse-code/openai-api-changelog)
- [OpenAI model specifications](https://spiral.ai/integrations/muse-code/openai-model-specifications)

## Questions about OpenAI documentation search in Muse Code

**Can Muse Code use OpenAI documentation search?**

Yes. Add Spiral to Muse Code as an MCP server, and Muse Code can find and run OpenAI documentation search like any built-in tool.

**How much does OpenAI documentation search cost in Muse Code?**

$0.00873 per call. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Muse Code plan is separate.

**Do I need an Alexandria account to use OpenAI documentation search in Muse Code?**

No. Spiral runs OpenAI documentation search on its own Alexandria account. You sign in to Spiral once and never paste a key.

**How long does it take to set up OpenAI documentation search in Muse Code?**

About two minutes: install Muse Code, then ask Muse to add the server, then sign in.

**Does Muse Code wait while OpenAI documentation search runs?**

OpenAI documentation search runs in the background. Muse Code starts the run, checks on it and gives you the json when it's ready.

**What public material does this source cover?**

OpenAI's documentation service provides read-only search and page content. The page reader covers official guides, references, and cookbook pages.

**Does the model catalog include deprecated models?**

Yes. OpenAI explicitly includes deprecated models in its full catalog, so a listed model still needs a lifecycle check.

**How detailed are the model specifications?**

They distinguish context capacity from input and output limits. For example, GPT-6.2 Sol lists a 1,050,000-token context window, 922,000 maximum input tokens, and 128,000 maximum output tokens.

**Are API announcements dated?**

Yes. The changelog's November 17, 2026 entry identifies GPT-6.2 Astra and GPT-6.2 Sol and tags the Responses and Chat Completions APIs.

**Can an agent read a specific part of a guide?**

Yes. The documentation page reader provides Markdown content with an outline and section reads for guides, references, and cookbook pages.

