`experiment_models`

Pack: ai-model-experiments · Connect: https://pipeworx.io/mcp (see Connect below for a single-pack URL)

No MCP client? Call it directly: GET https://gateway.pipeworx.io/v1/tools/experiment_models for the schema, then POST the same URL with its arguments for the data.

List AI models available for experiments (about 300 across Anthropic, OpenAI, Google, Meta, Mistral, DeepSeek, Qwen and more), with context window and OUR per-token prices (provider cost × 1.5 — what experiments actually bill). Filter by name/vendor search, minimum context, or max price. Use the returned model ids in experiment_create. Example: experiment_models({ search: “claude”, min_context: 100000 })

Parameters

Name	Type	Required	Description
`search`	string	no	Substring match on model id or name, e.g. “claude”, “gpt”, “llama”
`min_context`	number	no	Minimum context window in tokens
`max_price_per_mtok`	number	no	Max billed OUTPUT price in USD per million tokens
`limit`	number	no	Max models to return (default 30)

Example call

Arguments

{
  "search": "claude",
  "min_context": 100000
}

curl

curl -X POST https://gateway.pipeworx.io/ai-model-experiments/mcp \
  -H 'Content-Type: application/json' \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"experiment_models","arguments":{"search":"claude","min_context":100000}}}'

TypeScript (@pipeworx/sdk)

import { Pipeworx } from '@pipeworx/sdk';
const pipeworx = new Pipeworx();

const result = await pipeworx.call('experiment_models', {
  "search": "claude",
  "min_context": 100000
});

More examples

{
  "search": "gpt",
  "max_price_per_mtok": 0.03,
  "limit": 10
}

Connect

Add this to your MCP client config — every tool in the catalog, including this one — or use one-click install buttons:

{
  "mcpServers": {
    "pipeworx": {
      "url": "https://pipeworx.io/mcp"
    }
  }
}

Connect to just the ai-model-experiments pack

{
  "mcpServers": {
    "ai-model-experiments": {
      "url": "https://gateway.pipeworx.io/ai-model-experiments/mcp"
    }
  }
}

See Getting Started for client-specific install steps.

experiment_models