Model Cost Comparison Models API
The Models API from Model Cost Comparison — 1 operation(s) for models.
Work with this as data
Every API here is available over the APIs.io API and to AI agents over MCP.
MCP server
One button, every client — Claude, Cursor, VS Code and the rest.
https://apis.io/mcp
Tools for apis
7 MCP tools reach this
find_apisBrowse and filter every API in the catalog.get_api_artifactsOne API's artifacts, grouped by type.get_openapiThe primary OpenAPI for this API.find_similar_apisAPIs that look like this one.apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.resolveTurn a domain, URL or GitHub org into the provider it belongs to.find_cohortsEvery scored population of providers in the catalog.
Call it yourself
curl for this page
This API
curl "https://apis.io/api/v1/apis/modelcostcomparison-com:modelcostcomparison-com-models-api"
All apis
curl "https://apis.io/api/v1/apis?limit=25"Calls without X-API-Key need no key. Calls with it need a paid plan — get a key.
Get an API key
Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.
A second provider on the same verified email joins the account you already have.
OpenAPI Specification
openapi: 3.2.0
info:
title: Model Cost Comparison Models API
version: 1.0.0
description: 'Public machine-readable surfaces for Model Cost Comparison (61 models, 11 providers).
Developer portal: https://modelcostcomparison.com/developers
## Versioning
Stable REST operations use major-version URL paths beginning with /api/v1. Breaking changes ship under a new major path (/api/v2). Additive, non-breaking changes may appear on the current major without a path bump.
## Deprecation
Deprecated operations return Deprecation: true (RFC 9745) and a Link rel="successor-version" header pointing at the replacement. When a removal date is set, responses also include Sunset (RFC 8594).
Policy details: https://modelcostcomparison.com/developers#versioning-and-deprecation
## Errors
All API errors use RFC 9457 application/problem+json with stable `code`, human `detail`/`title`, and optional `resolution` hint. A nested `error` object mirrors `{ code, message, hint? }` for older clients.'
contact:
name: Lazige
url: https://lazige.agency
x-mcc-versioning:
strategy: url-path
current: /api/v1
description: Stable REST operations use major-version URL paths beginning with /api/v1. Breaking changes ship under a new major path (/api/v2). Additive, non-breaking changes may appear on the current major without a path bump.
deprecation: 'Deprecated operations return Deprecation: true (RFC 9745) and a Link rel="successor-version" header pointing at the replacement. When a removal date is set, responses also include Sunset (RFC 8594).'
docsPath: /developers#versioning-and-deprecation
servers:
- url: https://modelcostcomparison.com
tags:
- name: Models
paths:
/api/v1/models/advisor:
post:
operationId: mccModelAdvisorV1
summary: Recommend AI API models for a workload
description: Models-only advisor grounded in calculator prices and Artificial Analysis benchmarks. Refuses unrelated topics. Public — no API key; use server-to-server because cross-origin browser JSON requests are not supported.
requestBody:
required: true
content:
application/json:
schema:
type: object
required:
- message
properties:
message:
type: string
maxLength: 500
description: Workload / model-selection question
example: I need a support chatbot for 50k tickets/month
stream:
type: boolean
description: If true, respond as text/event-stream with token deltas ({content}) then a final {done,reply,sync,refused} event. Default JSON.
history:
type: array
maxItems: 4
items:
type: object
required:
- role
- content
properties:
role:
type: string
enum:
- user
- assistant
content:
type: string
maxLength: 2000
responses:
'200':
description: Advisor reply
content:
application/json:
schema:
$ref: '#/components/schemas/AdvisorResult'
text/event-stream:
schema:
type: string
description: 'SSE: data lines with {content} deltas, then {done,reply,sync,refused}.'
'400':
description: Invalid request
content:
application/problem+json:
schema:
$ref: '#/components/schemas/AgentError'
application/json:
schema:
$ref: '#/components/schemas/AgentError'
'405':
description: Method not allowed
content:
application/problem+json:
schema:
$ref: '#/components/schemas/AgentError'
application/json:
schema:
$ref: '#/components/schemas/AgentError'
'429':
description: Rate limited
content:
application/problem+json:
schema:
$ref: '#/components/schemas/AgentError'
application/json:
schema:
$ref: '#/components/schemas/AgentError'
'503':
description: Advisor unavailable
content:
application/problem+json:
schema:
$ref: '#/components/schemas/AgentError'
application/json:
schema:
$ref: '#/components/schemas/AgentError'
tags:
- Models
get:
operationId: mccModelAdvisorV1WrongMethod
summary: Method probe (returns 405 problem+json)
responses:
'405':
description: Only POST is supported
content:
application/problem+json:
schema:
$ref: '#/components/schemas/AgentError'
application/json:
schema:
$ref: '#/components/schemas/AgentError'
tags:
- Models
components:
schemas:
AgentError:
type: object
required:
- type
- title
- status
- detail
- code
- error
description: RFC 9457 problem details with MCC code/resolution and nested error object
properties:
type:
type: string
format: uri
title:
type: string
status:
type: integer
detail:
type: string
instance:
type: string
code:
type: string
resolution:
type: string
documentation_url:
type: string
format: uri
error:
type: object
required:
- code
- message
properties:
code:
type: string
message:
type: string
hint:
type: string
path:
type: string
AdvisorResult:
type: object
required:
- refused
- reply
- sync
properties:
refused:
type: boolean
reply:
type: string
sync:
oneOf:
- type: 'null'
- type: object
required:
- workload
- modelIds
- aaSlugs
- providers
- summaryLabel
properties:
presetId:
type: string
enum:
- support
- coding
- rag
- agent
workload:
type: object
required:
- messagesPerMonth
- avgTokensPerMessage
- inputRatio
- cachedInputRatio
properties:
messagesPerMonth:
type: number
avgTokensPerMessage:
type: number
inputRatio:
type: number
cachedInputRatio:
type: number
modelIds:
type: array
items:
type: string
aaSlugs:
type: array
items:
type: string
providers:
type: array
items:
type: string
summaryLabel:
type: string
securitySchemes:
bearerAuth:
type: http
scheme: bearer
description: CRON_SECRET for pricing refresh