Maxwell International Llm API

The llm API from Maxwell International — 1 operation(s) for llm.

GitHub OpenAPI

Operations 1

POST /v1/llm/chat AI assistant from the Maxwell International LLM service (model maxwell-chat)… #

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.
All 92 tools →

Call it yourself

curl for this page
This API
curl "https://apis.io/api/v1/apis/maxwellinternational-ai:maxwellinternational-ai-llm-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. By signing up you are subscribing to the APIs.io and API Evangelist newsletters — you can unsubscribe from any issue. See our Privacy Policy and Terms.

A second provider on the same verified email joins the account you already have.

OpenAPI Specification

maxwellinternational-ai-llm-api-openapi.yml Raw ↑
openapi: 3.2.0
info:
  title: Maxwell International Data (x402) Llm API
  version: 1.0.0
  description: Machine-only pay-per-call data API over x402. Prices are per request in USDC.
  x-guidance: 'Pay-per-call data for ski trips and public records, plus x402 Doctor, which tests other x402 endpoints for you. Ski: a directory of about 6,000 ski resorts worldwide, lift-ticket prices for the resorts listed at /v1/ski/coverage, a model forecast for every resort (station readings where one of 11 European met services has a station), lift status and snow reports only at about 50 resorts with their own feed (in Poland, Slovakia, Switzerland, Liechtenstein and Friuli in Italy; only while current), insider tips, and the Trip Wizard (a free map, then one paid call per trip step). Food: restaurants around ski resorts in every country listed at /v1/food/coverage (free, with per-country counts), with opening hours, website and contacts where known. Menus and prices only where read (withMenu): in Andorra, Austria, Bulgaria, Czechia, Finland, France, Germany, Italy, Liechtenstein, Norway, Poland, Slovakia, Slovenia, Spain, Sweden and Switzerland from the restaurant’s own website or, where none is published, a delivery app; in every other country only where a delivery app (Wolt, Bolt Food, Glovo, Pyszne.pl) lists the restaurant, as restaurants’ own websites are read for menus only in those 16 countries. Public data: SEC EDGAR, government registers and legislation of 13 countries and the EU, OFAC SDN, NVD CVEs, openFDA, NOAA weather (US), ECB FX, FRED, npm, RDAP domain records, crypto market quotes, US court opinions, US patents. Paid operations are GET, except doctor.payment and llm.chat (POST with a JSON body). Call one without payment to receive HTTP 402 with a PAYMENT-REQUIRED header (x402 v2): USDC on Base (eip155:8453) or Solana, settled through the Coinbase CDP facilitator. Send the same request again with a PAYMENT-SIGNATURE header. You are charged only for a 2xx answer. Missing or ambiguous parameters get a free 400 or 409 and a request with no data on file a free 404, both with charged:false. A search that runs and finds nothing is a 2xx answer (match:false) and is charged. Most routes check parameters before asking for payment. A bare path (directory probes), ski.prices without country, gov.de legislation and open data, and a POST without the fields it needs get the 402 first; after payment a request that cannot be answered still gets a free 400 (ski.prices answers if the resort id is unique). food.menu without restaurantId is a free 404. Paid answers that can look empty: a search with no matches (match:false), an RDAP lookup of an unregistered domain (registered:false) or of a registry without RDAP (rdapAvailable:false), and gov.de legislation or open data without q or id (the index of what is cached). doctor.buy and llm.chat collect the payment before they run: doctor.buy charges for the attempt, delivered or not; if the llm.chat model fails after payment, the answer (HTTP 503, llm_failed_after_payment) says charged:true and the payment is refunded by hand. A lookup of one item that is not cached yet (CVE, accession, company number, coordinates) is usually queued: retry after retryAfterSec. Priced per request (x-payment-info mode dynamic, with min and max where there is one): doctor.buy, llm.chat, trip.bundle; the 402 quotes the exact amount. Every other product has one price. Each response carries fetchedAt or generatedAt. Forecasts refresh every 6 hours, and lift status every 15 minutes where the resort has a feed. Hand-checked lift-ticket prices were read from official price lists on Oct 7-9, 2026 (rechecks from Nov 8); the others come from a weekly crawl of the resort''s price pages or from an earlier collection (operator shops, price pages); every row has its source link and read date. Public records refresh on each source''s schedule (age per family at /health). Free status and coverage endpoints are listed at /catalog.json; terms at /terms.json. Free samples: most products have one real request you can call free to check the data first (freeSampleUrl in /catalog.json, x-free-sample here, freeSample in every 402): the same answer a buyer of that request gets.'
  contact:
    name: Maxwell International
    email: accounts@maxwellinternational.ai
    url: https://api.maxwellinternational.ai/terms.json
  termsOfService: https://api.maxwellinternational.ai/terms.json
servers:
- url: https://api.maxwellinternational.ai
tags:
- name: LLM
paths:
  /v1/llm/chat:
    post:
      operationId: llm_chat
      summary: AI assistant from the Maxwell International LLM service (model maxwell-chat)…
      description: 'AI assistant from the Maxwell International LLM service (model maxwell-chat), OpenAI-style chat completion: POST {model, messages, max_tokens}. Priced before it runs: prompt tokens (yours plus ~860 of service instructions) x $1.50/M + max_tokens x $3.00/M + $0.005; max_tokens is your spend limit (short question, max_tokens 80: about $0.0066). Text only. Free model list: GET /v1/llm/models.'
      tags:
      - LLM
      parameters: []
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: object
              required:
              - messages
              properties:
                model:
                  type: string
                  description: model name from /v1/llm/models; default maxwell-chat
                messages:
                  type: array
                  description: '[{role: system|user|assistant, content: string}], 1 to 500 items'
                max_tokens:
                  type: integer
                  description: answer length cap and spend limit; default 1024, max 32000
                temperature:
                  type: number
                top_p:
                  type: number
                stop:
                  type: array
                seed:
                  type: integer
                response_format:
                  type: object
            example:
              model: maxwell-chat
              messages:
              - role: user
                content: 'In one sentence: what is x402?'
              max_tokens: 80
      x-payment-info:
        price:
          mode: dynamic
          currency: USD
          min: '0.0055'
        protocols:
        - x402: {}
      responses:
        '200':
          description: Paid response (charged)
          content:
            application/json:
              schema:
                type: object
                properties:
                  id:
                    type: string
                  object:
                    type: string
                  model:
                    type: string
                  choices:
                    type: array
                    items:
                      type: object
                      properties:
                        index:
                          type: integer
                        message:
                          type: object
                          properties:
                            role:
                              type: string
                            content:
                              type: string
                        finish_reason:
                          type: string
                  x402:
                    type: object
                    properties:
                      priceUsd:
                        type: number
                      billedInputTokens:
                        type: integer
                      maxOutputTokens:
                        type: integer
                      callId:
                        type: string
              example:
                id: llm_a16b44d392baac50b4dcfe4a
                object: chat.completion
                model: maxwell-chat
                choices:
                - index: 0
                  message: {}
                  finish_reason: stop
                x402:
                  priceUsd: 0.005895
                  billedInputTokens: 370
                  maxOutputTokens: 80
                  callId: llm_a16b44d392baac50b4dcfe4a
        '400':
          description: Missing, malformed or ambiguous parameters; not charged (charged:false). Most routes answer it before asking for payment.
        '402':
          description: Payment Required
        '404':
          description: No data on file for this request (not cached or not found); not charged (charged:false)
        '503':
          description: 'llm_failed_after_payment: the model failed after the payment was collected; charged:true, refunded by hand. Any other 503 is not charged (charged:false).'