`experiment_estimate`

Pack: ai-model-experiments · Endpoint: https://gateway.pipeworx.io/ai-model-experiments/mcp

Dry-run cost estimate for an experiment BEFORE creating it — cell count and estimated billed cost range (at our 1.5× pricing) for prompts × models × reps. Free to call, no side effects, does not need credit balance. Same spec shape as experiment_create. Example: experiment_estimate({ prompts: [“Summarize: …”], models: [“anthropic/claude-sonnet-4.5”, “openai/gpt-5”], reps: 2 })

Parameters

Name	Type	Required	Description
`prompts`	array	yes	Prompts to test (max 20)
`items`	string	no
`models`	array	yes	Model ids from experiment_models (max 12)
`items`	string	no
`reps`	number	no	Repetitions per prompt×model, 1-5 (default 1)
`params`	object	no	Optional {system, temperature, max_tokens}
`summary`	boolean	no	Include the AI-written comparison summary stage (default true)

Example call

Arguments

{
  "prompts": [
    "Summarize this article in one sentence."
  ],
  "models": [
    "anthropic/claude-sonnet-4.5",
    "openai/gpt-4o-mini"
  ]
}

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_estimate","arguments":{"prompts":["Summarize this article in one sentence."],"models":["anthropic/claude-sonnet-4.5","openai/gpt-4o-mini"]}}}'

TypeScript (@pipeworx/sdk)

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

const result = await pipeworx.call('experiment_estimate', {
  "prompts": [
    "Summarize this article in one sentence."
  ],
  "models": [
    "anthropic/claude-sonnet-4.5",
    "openai/gpt-4o-mini"
  ]
});

More examples

{
  "prompts": [
    "Write a haiku about AI.",
    "Translate to French: Hello world"
  ],
  "models": [
    "anthropic/claude-haiku-4.5",
    "openai/gpt-4o-mini",
    "google/gemini-2.0-flash"
  ],
  "reps": 2,
  "params": {
    "temperature": 0.7
  },
  "summary": true
}

Connect

Add this to your MCP client config, or use one-click install buttons:

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

See Getting Started for client-specific install steps.

experiment_estimate