TokenLab Model Explorer
Generates example cURL snippets for Chat Completions and Responses endpoints.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@TokenLab Model ExplorerBrowse models for text generation tasks."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
TokenLab OpenAI Apps Model Explorer
Lightweight TokenLab Model Explorer prototype for ChatGPT/OpenAI Apps SDK. It exposes an MCP Streamable HTTP endpoint plus an interactive MCP Apps widget for:
browsing TokenLab models from
/models.jsoncomparing pricing from
/pricing.jsongenerating copyable examples for Chat Completions, Responses, Anthropic Messages, and Gemini
generateContent
This repository is intentionally small so it can be used as a public discoverability asset and a starting point for a hosted ChatGPT app.
Live MCP endpoint: https://tokenlab-model-explorer.vercel.app/mcp
Run locally
npm install
npm test
npm startThe server listens on http://localhost:8000.
MCP endpoint:
http://localhost:8000/mcpWidget preview:
http://localhost:8000/widget
For ChatGPT local testing, expose the MCP endpoint with a tunnel such as ngrok, then add the /mcp URL as a connector in ChatGPT developer mode.
The Express app is also exported as the default module, so Vercel can deploy this repository without a custom adapter.
Related MCP server: ohmytoken
Environment
TOKENLAB_API_BASE=https://api.tokenlab.sh
PORT=8000Tools
Tool | Purpose |
| Browse TokenLab models by category or search query. |
| Compare pricing metadata for up to 8 model IDs. |
| Generate cURL snippets for OpenAI-compatible and native TokenLab endpoints. |
Discovery inputs
https://api.tokenlab.sh/models.jsonhttps://api.tokenlab.sh/pricing.jsonhttps://api.tokenlab.sh/integrations.jsonhttps://docs.tokenlab.sh/openapi.json
Notes
This app does not require a TokenLab API key for discovery tools.
Inference tools should use
@tokenlab/mcp-server; this repo focuses on model exploration and endpoint examples.The widget follows the MCP Apps pattern: tools are registered with UI metadata, and the HTML resource is served as an MCP app resource.
This server cannot be deployed
Maintenance
Related MCP Connectors
Live LLM API pricing: token prices, comparisons, cheapest-model lookups. No key required.
Compare up-to-date pricing for 40+ LLMs (incl. Chinese) & estimate cost from tokens. EN/zh.
Run and compare LLMs, generate images and video, with the real yen cost returned per call.
Discover, preview, estimate, run, and retrieve reusable AI workflows.
Related MCP Servers
- AlicenseAqualityFmaintenanceProvides AI assistants with real-time access to 1000+ AI models including their latest pricing, context windows, capabilities, and specifications. Supports model search, comparison, recommendations, and live testing.3871MIT
- FlicenseNot gradedqualityDmaintenanceProvides real-time token pricing for AI models, model comparison, cost calculation, and token usage tracking for agents and developers.-
- -licenseNot gradedqualityNot gradedmaintenanceEnables 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.-
- AlicenseAqualityCmaintenanceEnables AI clients to browse Llama AI models, pricing, FAQ, and start chat sessions without API keys.3MIT