Skip to main content
Glama
Sign In

TopxAI Models

by xyz.topxai.api
OverviewDiscussionsAdmin

Server Details

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

Ownership verified
Status
Healthy
Uptime
100.0% over the last 24 hours
Last Tested
Transport
Streamable HTTP · MCP 2025-11-25
URL
ChatGPT
–
Claude
–

TDQS

A4/5.0

Scored across 3 tools

Disambiguation4/5

ask_model and judge both invoke model inference, but their descriptions clearly separate freeform text replies from calibrated typed answers; list_models is distinct. An agent might briefly hesitate between ask_model and judge when seeking structured but non-probabilistic output, though boundaries are mostly clear.

Naming Consistency4/5

ask_model and list_models follow a verb_noun snake_case pattern, while judge is a bare verb—a minor deviation. All names are lowercase and action-oriented, keeping the set readable.

Tool Count5/5

Three tools map cleanly to listing models, freeform querying, and calibrated judging. For a narrow model-access server, each tool earns its place without excess.

Completeness4/5

The surface covers model discovery and two query modes, which is sufficient for read-only model access. Missing model-specific detail lookup or usage/cost history are minor gaps agents can work around.

Available Tools

3 tools
ask_modelAsk a modelAInspect

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.

Inputs: model (required), prompt (required), system, temperature, +3 more. Returns: error, model, route, usage, +6 more

judgeJudge with JevAInspect

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.

Inputs: state (required), questions (required), model. Returns: error, model, route, usage, +5 more

list_modelsList modelsA
Read-only
Inspect

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.

Inputs: no named parameters. Returns: models, call_fee_usd

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    • omnicall-mcp

      ColinHughes2121
      F
      license
      Not graded
      quality
      C
      maintenance
      Keyless, pay-per-call AI gateway: 248 LLMs plus image/video/voice/music generation and live crypto, DeFi, markets, web-search and research tools through one MCP server. Pay per call in USDC via x402 on Base/Solana — no API key, no signup, free tier.
      -

    • APIAny MCP

      ailingqu
      -
      license
      Not graded
      quality
      Not graded
      maintenance
      Enables discovery of public AI models with pricing, documentation context, and OpenAI-compatible integration examples. Supports both read-only queries and paid async media generation tasks.
      -
    Try in Browser
    Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

    Glama MCP Gateway

    Add one secure layer between your agents and this server.

    Resources