[Integrations](https://spiral.ai/integrations) › [OpenClaw](https://spiral.ai/integrations/openclaw) › [Artificial Analysis model search](https://spiral.ai/integrations/openclaw/artificial-analysis-model-search)

# How to Use Artificial Analysis model search in OpenClaw

Returns model and reasoning-effort records with Intelligence Index scores, benchmark results, and measured performance. Use it to discover candidates and build a shortlist before inspecting individual models.

|  |  |
| --- | --- |
| Model | Artificial Analysis model 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 Artificial Analysis model search in OpenClaw

- Every morning, use Artificial Analysis model search to check Anthropic models and report changes in returned Intelligence Index scores or output speeds since the previous check.
- Every Friday, use Artificial Analysis model search to check OpenAI models and summarize which returned reasoning effort settings changed their Intelligence Index scores since last Friday.
- Every Monday at 9am: use Artificial Analysis model search to look this up and give me the result as a table.
- Pull the latest numbers from Artificial Analysis model search and tell me what changed since last week.
- Check Artificial Analysis model search and summarize what you find in three bullet points.

## How to set up Artificial Analysis model search 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 Artificial Analysis model 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": "artificialanalysis-ai/benchmarks/search_models",
    "input": {
      "slug": "<slug>"
    }
  }'
```

Then paste one of the prompts above: OpenClaw finds Artificial Analysis model search on Spiral, shows the price and runs it.

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

## Artificial Analysis model search tools and prices

- [Artificial Analysis · Search models](https://spiral.ai/tools/alexandria/artificialanalysis-ai/benchmarks/search_models) (Alexandria): $0.00873 per call.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| slug |  | — | Exact model slug at one reasoning effort (e.g. `claude-fable-5-1-high`, `deepseek-v3`) or a pasted https://artificialanalysis.ai/models/{slug} URL: returns that one row (effort siblings such as `-high`/`-low` are not matched). Implies `include_deprecated: true`; a deprecated slug matches only while the page lists deprecated rows (use get_model for it otherwise). Combines with the other filters. Pattern: ^[A-Za-z0-9./:_-]+$. |
| limit | 1 to 100 | 20 | Results per page (1-100). |
| query |  | — | Case-insensitive terms matched against model name, short name, slug and creator; every whitespace-separated term must match (substring: `deepseek-v3` also matches `deepseek-v3-0324`; use `slug` for an exact row). Punctuation is folded on both sides, so `Claude Sonnet 5.5`, `claude-sonnet-5.5` and `claude-sonnet-5-5` find the same rows. One model per call: a list of several names matches nothing. |
| cursor |  | — | Opaque `next_cursor` from the previous page. Pattern: ^[0-9]+$. |
| creator |  | — | Creator name filter, case-insensitive substring (e.g. `anthropic`, `openai`). |
| reasoning |  | — | Only reasoning (true) or non-reasoning (false) models. |

## What can you do with Artificial Analysis model search in OpenClaw?

Get a recurring brief when Artificial Analysis changes the records you follow. Compare each retrieval with your agent's saved snapshot to flag changed benchmark scores or hosting measurements.

### Build an internal model shortlist

Find candidate models, inspect their benchmark results, and compare hosting measurements before choosing which combinations to test on your application.

### Review candidates for an interactive assistant

Compare model benchmark results alongside output speed and latency. Narrow the hosting choices for candidates that deserve a trial with your conversational workload.

### Prepare a model migration review

Compare a replacement model's benchmark record with the model you use today, then assess the measured hosting options for each before running migration tests.

### Maintain an internal evaluation brief

Compare newly retrieved model and hosting records with saved snapshots. Highlight changed benchmark results or performance measurements for the team's next evaluation meeting.

### Compare reasoning effort settings

Inspect the separate reasoning-effort records for a model and compare their Intelligence Index scores, benchmark results, and measured performance.

### Check long-document model candidates

Use reported context windows to identify models worth testing with long documents, then examine their benchmark records before designing your document evaluation.

## Overview

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

## Artificial Analysis model search in other agents

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

## More OpenClaw guides

- [Artificial Analysis model hosting comparison](https://spiral.ai/integrations/openclaw/artificial-analysis-model-hosting-comparison)
- [CISA KEV CVE lookup](https://spiral.ai/integrations/openclaw/cisa-kev-cve-lookup)
- [Artificial Analysis model details](https://spiral.ai/integrations/openclaw/artificial-analysis-model-details)
- [CISA KEV recent additions](https://spiral.ai/integrations/openclaw/cisa-kev-recent-additions)
- [Artificial Analysis hosting endpoint search](https://spiral.ai/integrations/openclaw/artificial-analysis-hosting-endpoint-search)
- [CISA KEV vulnerability search](https://spiral.ai/integrations/openclaw/cisa-kev-vulnerability-search)

## Questions about Artificial Analysis model search in OpenClaw

**Can OpenClaw use Artificial Analysis model search?**

Yes. Add Spiral to OpenClaw as an MCP server, and OpenClaw can find and run Artificial Analysis model search like any built-in tool.

**How much does Artificial Analysis model search cost in OpenClaw?**

$0.00873 per call. 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 Alexandria account to use Artificial Analysis model search in OpenClaw?**

No. Spiral runs Artificial Analysis model 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 Artificial Analysis model search in OpenClaw?**

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

**Does OpenClaw wait while Artificial Analysis model search runs?**

Artificial Analysis model search runs in the background. OpenClaw starts the run, checks on it and gives you the json when it's ready.

**Does Artificial Analysis cover proprietary and open weights models?**

Yes. Artificial Analysis benchmarks both proprietary and open weights models, so its comparisons can include both deployment approaches.

**How fresh are the performance measurements?**

Artificial Analysis runs its standard API performance benchmark every six hours across several workloads. Model and benchmark records update as Artificial Analysis publishes results.

**Will the latency figures match users in every region?**

The tests run from Google Cloud Run in us-central1. The measurements therefore reflect that network path, which limits how directly they describe response times elsewhere.

**Does a model's speed describe every company hosting it?**

Model-level performance usually represents the model creator's own endpoint. Artificial Analysis also publishes per-model hosting benchmarks, which let you compare hosts individually.

**Can I inspect performance variation beyond a single speed figure?**

Artificial Analysis's detailed performance data includes quartiles and percentiles. These distributions help distinguish a typical measurement from the spread of observed results.

