TopxAI Models

Working Security A

xyz.topxai.api/modelsv1.0.0 Domain verified

Ask Claude, GPT, Grok, GLM, Kimi or DeepSeek from your client; token price plus a $0.001 call fee.

AI & Agents

Watch Website

Registry entry

Open in the registry

{
  "_meta": {
    "io.modelcontextprotocol.registry/official": {
      "status": "active",
      "isLatest": true,
      "updatedAt": "2026-11-13T02:26:06.650343Z",
      "publishedAt": "2026-11-13T02:26:06.650343Z",
      "statusChangedAt": "2026-11-13T02:26:06.650343Z"
    }
  },
  "server": {
    "name": "xyz.topxai.api/models",
    "icons": [
      {
        "src": "https://api.topxai.xyz/apple-touch-icon.png",
        "sizes": [
          "180x180"
        ],
        "mimeType": "image/png"
      },
      {
        "src": "https://api.topxai.xyz/favicon.svg",
        "sizes": [
          "any"
        ],
        "mimeType": "image/svg+xml"
      }
    ],
    "title": "TopxAI Models",
    "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
    "remotes": [
      {
        "url": "https://api.topxai.xyz/mcp/models",
        "type": "streamable-http",
        "headers": [
          {
            "name": "Authorization",
            "value": "Bearer {api_key}",
            "format": "string",
            "isSecret": true,
            "variables": {
              "api_key": {
                "format": "string",
                "isSecret": true,
                "isRequired": true,
                "description": "TopxAI API key"
              }
            },
            "isRequired": true,
            "description": "Bearer followed by your TopxAI API key (create one at https://api.topxai.xyz/keys)"
          }
        ]
      }
    ],
    "version": "1.0.0",
    "websiteUrl": "https://api.topxai.xyz/mcp",
    "description": "Ask Claude, GPT, Grok, GLM, Kimi or DeepSeek from your client; token price plus a $0.001 call fee."
  }
}

Maintain this server? Claim it

Try it

Call this server's tools from your browser. Nothing to install.

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

Authorization (required)

Bearer followed by your TopxAI API key (create one at https://api.topxai.xyz/keys)

Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.

Tool list from our last check. Connect live to refresh it.

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.

modelstring, required

Model to ask; list_models shows the choices and prices.

promptstring, required

The user message sent to the model. Include every piece of context the model needs; it sees nothing else.

systemstring

Optional system prompt.

temperaturenumber

Optional sampling temperature.

max_cost_usdnumber

Refuse the call, before anything is billed, when its estimated cost (prompt, max_output_tokens and the call fee) exceeds this amount.

reasoning_effortstring

Optional thinking effort. Each model takes its own set and list_models shows them with the default, which applies when this is omitted. A lower effort answers sooner and costs less; the reasoning is billed as output and counts toward max_output_tokens.

max_output_tokensinteger

Upper bound on the reply, reasoning included; the reasoning itself is not returned. Below 4096 a model may stop before writing any text, and that call is still charged.

This tool isn't marked read-only, so it may change something on the server or in an account you connected.

I understand, run it anyway

Try it

Call this server's tools from your browser. Nothing to install.

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

Authorization (required)

Bearer followed by your TopxAI API key (create one at https://api.topxai.xyz/keys)

Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.

Tool list from our last check. Connect live to refresh it.

ask_model

modelstring, required

Model to ask; list_models shows the choices and prices.

promptstring, required

The user message sent to the model. Include every piece of context the model needs; it sees nothing else.

systemstring

Optional system prompt.

temperaturenumber

Optional sampling temperature.

max_cost_usdnumber

Refuse the call, before anything is billed, when its estimated cost (prompt, max_output_tokens and the call fee) exceeds this amount.

reasoning_effortstring

max_output_tokensinteger

Upper bound on the reply, reasoning included; the reasoning itself is not returned. Below 4096 a model may stop before writing any text, and that call is still charged.

This tool isn't marked read-only, so it may change something on the server or in an account you connected.

I understand, run it anyway

Tools (3)

ask_model

Argument	Type	Description
model*	string	Model to ask; list_models shows the choices and prices.
prompt*	string	The user message sent to the model. Include every piece of context the model needs; it sees nothing else.
system	string	Optional system prompt.
temperature	number	Optional sampling temperature.
max_cost_usd	number	Refuse the call, before anything is billed, when its estimated cost (prompt, max_output_tokens and the call fee) exceeds this amount.
reasoning_effort	string	Optional thinking effort. Each model takes its own set and list_models shows them with the default, which applies when this is omitted. A lower effort answers sooner and costs less; the reasoning is billed as output and counts toward max_output_tokens.
max_output_tokens	integer	Upper bound on the reply, reasoning included; the reasoning itself is not returned. Below 4096 a model may stop before writing any text, and that call is still charged.

Input schema (JSON)

{
  "type": "object",
  "required": [
    "model",
    "prompt"
  ],
  "properties": {
    "model": {
      "type": "string",
      "description": "Model to ask; list_models shows the choices and prices."
    },
    "prompt": {
      "type": "string",
      "description": "The user message sent to the model. Include every piece of context the model needs; it sees nothing else."
    },
    "system": {
      "type": "string",
      "description": "Optional system prompt."
    },
    "temperature": {
      "type": "number",
      "maximum": 2,
      "minimum": 0,
      "description": "Optional sampling temperature."
    },
    "max_cost_usd": {
      "type": "number",
      "minimum": 0,
      "description": "Refuse the call, before anything is billed, when its estimated cost (prompt, max_output_tokens and the call fee) exceeds this amount."
    },
    "reasoning_effort": {
      "type": "string",
      "description": "Optional thinking effort. Each model takes its own set and list_models shows them with the default, which applies when this is omitted. A lower effort answers sooner and costs less; the reasoning is billed as output and counts toward max_output_tokens."
    },
    "max_output_tokens": {
      "type": "integer",
      "default": 8192,
      "maximum": 65536,
      "minimum": 1,
      "description": "Upper bound on the reply, reasoning included; the reasoning itself is not returned. Below 4096 a model may stop before writing any text, and that call is still charged."
    }
  },
  "additionalProperties": false
}

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.

Argument	Type	Description
model	string	System One model.
state*	string	The text the questions are about: a ticket, a log excerpt, a document, a transcript.
questions*	object	Question id to typed question. Each question is {"type": "noul" \| "choice" \| "score", "instructions": "one question a careful reader could answer from the state alone"}. noul may add "criteria": {"true": ..., "false": ...}; choice adds "criteria": {option: description or null, ...} (a plain list of option names is accepted too); score adds "criteria": [level description, ...] with 2 to 10 ordered levels.

Input schema (JSON)

{
  "type": "object",
  "required": [
    "state",
    "questions"
  ],
  "properties": {
    "model": {
      "type": "string",
      "description": "System One model."
    },
    "state": {
      "type": "string",
      "description": "The text the questions are about: a ticket, a log excerpt, a document, a transcript."
    },
    "questions": {
      "type": "object",
      "description": "Question id to typed question. Each question is {\"type\": \"noul\" | \"choice\" | \"score\", \"instructions\": \"one question a careful reader could answer from the state alone\"}. noul may add \"criteria\": {\"true\": ..., \"false\": ...}; choice adds \"criteria\": {option: description or null, ...} (a plain list of option names is accepted too); score adds \"criteria\": [level description, ...] with 2 to 10 ordered levels.",
      "minProperties": 1,
      "additionalProperties": {
        "type": "object",
        "required": [
          "type",
          "instructions"
        ],
        "properties": {
          "type": {
            "enum": [
              "noul",
              "choice",
              "score"
            ],
            "type": "string"
          },
          "instructions": {
            "type": "string"
          }
        }
      }
    }
  },
  "additionalProperties": false
}

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.

read-only

No arguments.

Input schema (JSON)

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}

TopxAI Models

Registry entry

Try it

ask_model

TopxAI Models

Registry entry

Try it

ask_model

Install

Tools (3)

Security checkA100/100