# TopxAI Models

> TopxAI Models is a paid MCP server for ai models and llm tooling. Ask Claude, GPT, Grok and other catalogue models from inside another model's chat. It runs as a hosted remote server, so there is nothing to install locally.

- **Kind:** MCP server
- **Pricing:** Paid
- **Platforms:** API
- **Website:** https://api.topxai.xyz/mcp
- **MCP Registry name:** xyz.topxai.api/models
- **Categories:** AI models and LLM tooling
- **Listing updated:** 2026-11-14

## About

The use case on the page is a second opinion: ask a different model to review a plan or answer a question without leaving your current client. Each call costs the chosen model's token price plus a flat $0.001 fee, and the reply states the exact charge.

Three tools are exposed. One lists the text models your key can ask, with prices per million tokens, supported reasoning efforts and the call fee. Another sends a prompt to a chosen model; since models reason before answering and that counts toward the output limit, the page advises leaving at least 4096 tokens or lowering reasoning effort. The third, judge, asks TypeSafe's Jev model typed questions and returns calibrated numbers rather than prose: a probability for a yes/no, a probability per option, or a value on a scale.

It authenticates with the shared TopxAI key, and failed provider calls are not billed.

## Features

- **Model listing:** Shows available text models, prices and reasoning levels.
- **Ask any model:** Sends a prompt to one chosen catalogue model and returns its reply.
- **Calibrated judging:** Returns probabilities for yes/no, choice and score questions.
- **Spend cap argument:** Calls accept a maximum cost and output token limit.
- **Reasoning control:** Choose the reasoning effort per request.

## Good for

- Get a second opinion on a migration plan
- Classify a support ticket's urgency and topic
- Compare answers across vendors
- Check model prices before choosing one

## Install

### Claude Code (Terminal)

```sh
claude mcp add --transport http models https://api.topxai.xyz/mcp/models
```

### Claude Desktop (Settings → Connectors → Add custom connector)

```sh
https://api.topxai.xyz/mcp/models
```

### Cursor (~/.cursor/mcp.json)

```json
{
  "mcpServers": {
    "models": {
      "url": "https://api.topxai.xyz/mcp/models"
    }
  }
}
```

### VS Code (.vscode/mcp.json)

```json
{
  "servers": {
    "models": {
      "type": "http",
      "url": "https://api.topxai.xyz/mcp/models"
    }
  }
}
```

### Windsurf (~/.codeium/windsurf/mcp_config.json)

```json
{
  "mcpServers": {
    "models": {
      "serverUrl": "https://api.topxai.xyz/mcp/models"
    }
  }
}
```

### Other clients (your client's MCP settings (most use this shape))

```json
{
  "mcpServers": {
    "models": {
      "type": "http",
      "url": "https://api.topxai.xyz/mcp/models"
    }
  }
}
```

## Tools

- `list_models`: List the text models this API key can ask, with their USD prices per million tokens, the reasoning efforts each takes and the call fee.
- `ask_model`: Send a prompt to one text model of the TopxAI catalogue and return its reply. The models reason before they answer and the reasoning counts toward max_output_tokens, so leave at least 4096 tokens for a full answer or pass a lower reasoning_effort. Billed at the model's token price, reasoning included, plus a $0.001 call fee; the reply reports the exact charge.
- `judge`: Ask TypeSafe's Jev (a System One model) typed questions about a piece of text and get calibrated numbers back, not prose: a probability for a yes/no question (type noul), one option with a probability per option (type choice, with criteria), or a value on a scale with a probability per anchor (type score, with anchors). Billed at Jev's input-token price plus a $0.001 call fee.

## FAQ

### What does a call cost?

Token price of the chosen model plus a $0.001 call fee.

### Why leave at least 4096 output tokens?

Reasoning counts toward the output limit.

### What does judge return?

Calibrated numbers such as probabilities, not prose.

### Is a failed call charged?

No.

### Is TopxAI Models free?

No. TopxAI Models is a paid product.

### How do I add TopxAI Models to Claude Code?

Run this command in your terminal: claude mcp add --transport http models https://api.topxai.xyz/mcp/models

### What are the best alternatives to TopxAI Models?

The closest alternatives to TopxAI Models are Claude Code Ultimate Guide, signafAIde, Toolkien, Lugh and HypePaper.

## Alternatives

- [Claude Code Ultimate Guide](https://ai-powered.com/mcp/claude-code-ultimate-guide): Claude Code Ultimate Guide is an open-source MCP server for ai models and llm tooling.
- [signafAIde](https://ai-powered.com/mcp/signafaide): signafAIde is a freemium MCP server for security.
- [Toolkien](https://ai-powered.com/mcp/toolkien): Toolkien is an open-source MCP server for ai models and llm tooling.
- [Lugh](https://ai-powered.com/mcp/lugh): Lugh is an open-source MCP server for ai models and llm tooling.
- [HypePaper](https://ai-powered.com/mcp/hypepaper): HypePaper is a freemium MCP server for ai models and llm tooling.
- [Agent Data Tools: Compact (find, describe, run)](https://ai-powered.com/mcp/agent-data-tools-compact-find-describe-run): Agent Data Tools: Compact (find, describe, run) is a freemium MCP server for developer tools.
- [Angel Agent Guard: pre-purchase check + prompt-injection scan](https://ai-powered.com/mcp/angel-agent-guard-pre-purchase-check-prompt-injection-scan): Angel Agent Guard: pre-purchase check + prompt-injection scan is a freemium MCP server for ai models and llm tooling.
- [Mizan Calibration](https://ai-powered.com/mcp/mizan-calibration): Mizan Calibration is a free MCP server for ai models and llm tooling.

---
Source: https://ai-powered.com/mcp/topxai-models
