AgentKernel AI model data

si.agentkernelPublished by agentkernel.siOfficial publisherv1.0.0Updated Oct 24, 2026

Live prices, rankings, licences and privacy of AI models: best model per task, costs, alternatives.

VerifiedStreamable HTTPWeb executableData & AnalyticsAI & ML

Overview

AI-generated overview

A remote MCP server that lets an assistant compare AI models by live price, performance ranking, licence and privacy, and estimate API costs.

What you can do
Rank models for a specific task by performance, with price shown but not used in the ranking, across text, coding, agents, UI, image, video, speech, music and embeddings tasks. Recommend language models for a use case and monthly budget using the published Fit Score, with optional privacy and licence filters. Look up one model's price, context window, performance, coding and agentic index with rank, licence, privacy, cost for a usage volume, and cheaper or open alternatives. Search and filter the model catalog by name, provider, licence and privacy, sorted by performance, coding, agentic index, price or context. Estimate monthly API cost at base rates for up to five models and a token volume
When to use it
Use it when choosing which AI model or provider to build on, comparing prices and capabilities, checking licence and privacy terms, or budgeting API spend before committing to a model.
Requirements
A remote streamable HTTP endpoint; no package, environment variable or header is declared. No authentication is declared. Network access to the provider's endpoint is needed.
Before you install
The catalog and prices are third-party data from the provider; verify figures against official model providers before relying on them for budgeting or procurement. No credentials are requested, and the tools described only read and compare data.

Installation

In SourceWeft

  1. Open AgentKernel AI model data in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/si.agentkernel%2Fmodels/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "agentkernel-ai-model-data": {
      "type": "http",
      "url": "https://www.agentkernel.si/mcp"
    }
  }
}

Tools

6

best_for_task

Best AI models for a task

Ranks AI models for one task by performance only (price shown, never used for the rank). Tasks cover text, coding, agents, websites/UI/games/data viz, image generation and editing, video from text or image, video editing, text to speech, transcription, music and embeddings.

Parameterstaskrequiredlimitlicense

recommend_models

Recommend models for a use case and budget

Returns the best-fitting language models for a use case and monthly API budget using the published AgentKernel Fit Score (performance, cost, context, features), with optional privacy and licence requirements.

Parametersprivacypriorityuse_caserequiredinclude_freeinput_tokensneeds_visionoutput_tokensopen_weights_onlymonthly_budget_usd

get_model

Model facts

Price, context window, performance/coding/agentic index with rank, licence, privacy, cost for a usage volume and cheaper or open alternatives for one language model.

Parametersmodelrequiredinput_tokensoutput_tokens

find_models

Search the model catalog

Searches and filters the catalog of language models by name, provider, licence and privacy, sorted by performance, coding, agentic index, price or context.

Parameterssortlimitquerylicenseprivacy

estimate_cost

Estimate API cost

Monthly API cost at base rates for up to five models and a token volume, with the volume translated into words and pages.

Parametersmodelsrequiredinput_tokensoutput_tokens

cheaper_alternative

Find a cheaper alternative

For a model you use today, finds a cheaper model at most five performance-index points lower for the same usage.

Parametersmodelrequiredinput_tokensoutput_tokens

Version history

1
  1. v1.0.0LatestOct 14, 2026

Score

83% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts

    Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.

  • LicenseNot applicable

    A hosted service is used under its provider's terms, so no license is expected here. This check is left out of the percentage.