API Reference

REST API and MCP server for querying models, providers, and capabilities
RESThttps://api.modelpedia.dev/v1
MCPhttps://api.modelpedia.dev/mcp
FormatJSON (append ?pretty for formatted output)

MCP Setup

claude mcp add modelpedia --transport http https://api.modelpedia.dev/mcp

Overview

GET/v1/stats
GET/v1/search
qSearch query (min 2 chars, required)
limitMax model results (default 20, max 50)

Providers

GET/v1/providers
GET/v1/providers/:id
GET/v1/providers/compare
idsComma-separated provider IDs (2-10, required)

Models

GET/v1/models
providerFilter by provider id
familyFilter by model family
creatorFilter by original creator
statusactive | deprecated | preview
capabilityreasoning | vision | tool_call | streaming | structured_output | json_mode | fine_tuning | batch
qSearch across id, name, description
sortname | context_window | price_input | price_output
orderasc (default) | desc
limitMax 500, default 100
offsetDefault 0
GET/v1/models/:provider/:id
GET/v1/models/compare
idsComma-separated provider/model IDs (2-10, required)
GET/v1/models/latest
limitMax 500, default 100
offsetDefault 0
GET/v1/models/recommend
capabilityRequired capabilities, comma-separated
model_typechat | reasoning | embed | image | tts | ...
min_context_windowMinimum context window in tokens
max_price_inputMax input price (USD per 1M tokens)
input_modalityRequired input: text | image | audio | video
output_modalityRequired output: text | image | audio | video
limitMax 500, default 100
offsetDefault 0
GET/v1/models/types

Taxonomy

GET/v1/families
GET/v1/capabilities
GET/v1/creators
GET/v1/modalities
GET/v1/tools

Pricing

GET/v1/pricing/compare
idsComma-separated provider/model IDs (optional, compares all if omitted)
min_price_inputMin input price (USD per 1M tokens)
max_price_inputMax input price (USD per 1M tokens)
sortprice_input (default) | price_output
orderasc (default) | desc
limitMax 500, default 100
offsetDefault 0

Response format

Success{ "data": ..., "meta": { "total", "limit", "offset" } }
Error{ "error": { "message", "status" } }

Conventions

Field presentKnown value
Field omittedUnknown
Field is nullNot applicable
pricing.*USD per 1M tokens
context_windowToken count
capabilities.*Boolean flags (true = supported)
modalities.*Array of: "text", "image", "audio", "video"
performance / speed1-5 scale
status"active" | "deprecated" | "preview"

Notes

AuthNone required
CORSEnabled on all endpoints
Rate limit60 requests per minute per IP (REST API only)