Skip to main content
Glama
index9-org

Index9 MCP Server

by index9-org

find_models

Search and filter 300+ AI models by query, provider, pricing, context windows, and capabilities to find suitable models for specific tasks.

Instructions

Search and filter 300+ AI models. Returns ranked results with pricing, context windows, and capabilities.

Call this tool first to discover model IDs, unless the user provides one (format: 'provider/model-name').

Parameters:

  • query: Natural language search (e.g., 'fast cheap coding model')

  • provider: Filter by provider(s). Comma-separated for multiple (e.g., 'openai,anthropic')

  • min_context, max_context, max_price_per_m, capabilities: Exact filters

  • sort_by: 'relevance' (default), 'price_asc', 'price_desc', 'date_desc', 'context_desc'

  • limit, offset: Pagination

Scores: Results include a 'score' field (0-150+). Higher = more relevant. Combines semantic similarity, capability matching, and model quality signals. Use for relative ranking, not absolute measurement.

Use model IDs from results with get_model for full specs or test_model for live testing.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
queryNoNatural language search query describing desired model characteristics (e.g., 'fastest coding model under $1', 'vision model with 128k context', 'cheapest tool-calling model'). Uses semantic search with fuzzy matching. Optional - omit to use filters only.
providerNoFilter by provider name(s). Comma-separated for multiple (e.g., 'openai,anthropic'). Case-insensitive.
min_contextNoMinimum context window size in tokens (e.g., 8192, 32000, 128000). Filters out models with smaller context windows. Common values: 4096 (small), 32000 (medium), 128000+ (large).
max_contextNoMaximum context window size in tokens. Filters out models with larger context windows. Use to find smaller, faster models.
max_price_per_mNoMaximum acceptable price per million input tokens in USD (e.g., 0.5 for $0.50/M tokens). Filters out more expensive models. Note: only considers input pricing for filtering.
capabilitiesNoRequired capabilities array - model must support ALL specified capabilities (AND logic). Examples: ['vision'] for image input, ['tool_calling', 'json_mode'] for structured outputs, ['vision', 'tool_calling'] for multimodal agents. Available: vision, audio, tool_calling, json_mode, video.
sort_byNoSort order for results. Options: 'relevance' (best semantic match, default), 'price_asc' (cheapest first by input price), 'price_desc' (most expensive first), 'date_desc' (newest models first), 'context_desc' (largest context window first). Defaults to 'relevance'.relevance
limitNoMaximum number of results to return (1-100). Defaults to 10. Use higher values (20-50) for broad exploration, lower values (5-10) for focused comparisons.
offsetNoNumber of results to skip for pagination (0-based). Defaults to 0. Example: offset=10 with limit=10 returns results 11-20. Use with 'total' in response for pagination.
Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/index9-org/mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server