[Integrations](https://spiral.ai/integrations) › [Claude](https://spiral.ai/integrations/claude-desktop) › [Artificial Analysis model hosting comparison](https://spiral.ai/integrations/claude-desktop/artificial-analysis-model-hosting-comparison)

# How to Use Artificial Analysis model hosting comparison in Claude

Returns hosting benchmarks for one model, including output speed and latency distributions. Use it to compare hosts for the same model and inspect variation beyond the median.

|  |  |
| --- | --- |
| Model | Artificial Analysis model hosting comparison |
| 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 hosting comparison in Claude

- Use Artificial Analysis model hosting comparison for DeepSeek V3 and compare the hosts by reported latency and output speed, including the available performance distributions.
- Use Artificial Analysis model hosting comparison to look this up and give me the result as a table.
- Pull the latest numbers from Artificial Analysis model hosting comparison and tell me what changed since last week.
- Check Artificial Analysis model hosting comparison and summarize what you find in three bullet points.
- Pull the newest data from Artificial Analysis model hosting comparison and give me the result as a table.

## How to set up Artificial Analysis model hosting comparison in Claude

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

### Use the Claude connector

1. **Add Spiral to Claude**: Click Add Spiral in Claude above. Claude opens Add custom connector with Spiral and its URL filled in; check them and click Continue. Without the link: in Claude open Customize › Connectors › Add › Add custom connector and paste this URL:

```text
https://api.spiral.ai/mcp
```

2. **Keep the detected sign-in and click Add**: Claude finds Spiral's sign-in by itself: leave Sign in now and Use Claude's published identity selected.

3. **Click Connect**: The connector page opens. Connect takes you to Spiral in your browser.

### Use the Spiral skill

1. **Send Claude 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 Artificial Analysis model hosting comparison**: 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/list_model_providers",
    "input": {
      "slug": "<slug>"
    }
  }'
```

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

Setup guide in the docs: https://spiral.ai/docs/quickstarts/claude-desktop

## Artificial Analysis model hosting comparison tools and prices

- [Artificial Analysis · List model providers](https://spiral.ai/tools/alexandria/artificialanalysis-ai/benchmarks/list_model_providers) (Alexandria): $0.00873 per call.

## What can you do with Artificial Analysis model hosting comparison in Claude?

Turn Artificial Analysis records into a readable comparison for your next model evaluation. Ask your assistant to explain the returned benchmark or hosting measurements and identify candidates worth testing.

### 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.

### Investigate a hosting change

Find the measured endpoints for a model and compare their latency and output speed. Use detailed distributions to decide which hosts warrant application-level testing.

### Separate model choice from host choice

Inspect the model benchmark record and compare the hosting measurements separately. Explain which evidence concerns model capability and which concerns serving performance.

## Overview

- [Alexandria](https://spiral.ai/providers/alexandria)
- [All Claude guides](https://spiral.ai/integrations/claude-desktop)

## Artificial Analysis model hosting comparison in other agents

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

## More Claude guides

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

## Questions about Artificial Analysis model hosting comparison in Claude

**Can Claude use Artificial Analysis model hosting comparison?**

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

**How much does Artificial Analysis model hosting comparison cost in Claude?**

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

**Do I need an Alexandria account to use Artificial Analysis model hosting comparison in Claude?**

No. Spiral runs Artificial Analysis model hosting comparison 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 hosting comparison in Claude?**

About two minutes: add Spiral to Claude, then keep the detected sign-in and click Add, then click Connect.

**Does Claude wait while Artificial Analysis model hosting comparison runs?**

Artificial Analysis model hosting comparison runs in the background. Claude 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.

