You can access the LLM Latency & Cost Monitor programmatically from your own applications by using the Apify API. You can also choose the language preference from below. To use the Apify API, you’ll need an Apify account and your API token, found in Integrations settings in Apify Console.

Python

JavaScript

CLI

OpenAPI

HTTP

MCP

{
  "openapi": "3.0.1",
  "info": {
    "version": "1.0",
    "x-build-id": "o5YSxO5cASMAPX2hP"
  },
  "servers": [
    {
      "url": "https://api.apify.com/v2"
    }
  ],
  "paths": {
    "/acts/constant_quadruped~llm-latency-cost-monitor/run-sync-get-dataset-items": {
      "post": {
        "operationId": "run-sync-get-dataset-items-constant_quadruped-llm-latency-cost-monitor",
        "x-openai-isConsequential": false,
        "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.",
        "tags": [
          "Run Actor"
        ],
        "requestBody": {
          "required": true,
          "content": {
            "application/json": {
              "schema": {
                "$ref": "#/components/schemas/inputSchema"
              }
            }
          }
        },
        "parameters": [
          {
            "name": "token",
            "in": "query",
            "required": true,
            "schema": {
              "type": "string"
            },
            "description": "Enter your Apify token here"
          }
        ],
        "responses": {
          "200": {
            "description": "OK"
          }
        }
      }
    },
    "/acts/constant_quadruped~llm-latency-cost-monitor/runs": {
      "post": {
        "operationId": "runs-sync-constant_quadruped-llm-latency-cost-monitor",
        "x-openai-isConsequential": false,
        "summary": "Executes an Actor and returns information about the initiated run in response.",
        "tags": [
          "Run Actor"
        ],
        "requestBody": {
          "required": true,
          "content": {
            "application/json": {
              "schema": {
                "$ref": "#/components/schemas/inputSchema"
              }
            }
          }
        },
        "parameters": [
          {
            "name": "token",
            "in": "query",
            "required": true,
            "schema": {
              "type": "string"
            },
            "description": "Enter your Apify token here"
          }
        ],
        "responses": {
          "200": {
            "description": "OK",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/runsResponseSchema"
                }
              }
            }
          }
        }
      }
    },
    "/acts/constant_quadruped~llm-latency-cost-monitor/run-sync": {
      "post": {
        "operationId": "run-sync-constant_quadruped-llm-latency-cost-monitor",
        "x-openai-isConsequential": false,
        "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.",
        "tags": [
          "Run Actor"
        ],
        "requestBody": {
          "required": true,
          "content": {
            "application/json": {
              "schema": {
                "$ref": "#/components/schemas/inputSchema"
              }
            }
          }
        },
        "parameters": [
          {
            "name": "token",
            "in": "query",
            "required": true,
            "schema": {
              "type": "string"
            },
            "description": "Enter your Apify token here"
          }
        ],
        "responses": {
          "200": {
            "description": "OK"
          }
        }
      }
    }
  },
  "components": {
    "schemas": {
      "inputSchema": {
        "type": "object",
        "properties": {
          "providers": {
            "title": "Providers list",
            "type": "array",
            "description": "LLM providers to probe. Supported: OpenAI, Anthropic, Google, DeepSeek, Mistral, Groq.",
            "default": [
              "OpenAI",
              "Anthropic",
              "Google",
              "DeepSeek"
            ],
            "items": {
              "type": "string"
            }
          },
          "apiKeys": {
            "title": "API keys (optional)",
            "type": "object",
            "description": "Optional map of provider name to API key, e.g. {\"OpenAI\": \"sk-...\"}. If provided, the actor fires a minimal REAL chat request and measures end-to-end latency. If omitted, it falls back to a real unauthenticated HTTPS latency probe against each provider host. Keys are also read from env vars (OPENAI_API_KEY, ANTHROPIC_API_KEY, GOOGLE_API_KEY/GEMINI_API_KEY, DEEPSEEK_API_KEY, MISTRAL_API_KEY, GROQ_API_KEY)."
          },
          "models": {
            "title": "Model overrides (optional)",
            "type": "object",
            "description": "Optional map of provider name to model id to probe, e.g. {\"OpenAI\": \"gpt-4o-mini\"}. Defaults to a cheap reference model per provider."
          },
          "timeoutMs": {
            "title": "Per-probe timeout (ms)",
            "type": "integer",
            "description": "Hard timeout for each provider probe in milliseconds. A timed-out probe is reported with status=timeout and its real elapsed time.",
            "default": 15000
          }
        }
      },
      "runsResponseSchema": {
        "type": "object",
        "properties": {
          "data": {
            "type": "object",
            "properties": {
              "id": {
                "type": "string"
              },
              "actId": {
                "type": "string"
              },
              "userId": {
                "type": "string"
              },
              "startedAt": {
                "type": "string",
                "format": "date-time",
                "example": "2025-01-08T00:00:00.000Z"
              },
              "finishedAt": {
                "type": "string",
                "format": "date-time",
                "example": "2025-01-08T00:00:00.000Z"
              },
              "status": {
                "type": "string",
                "example": "READY"
              },
              "meta": {
                "type": "object",
                "properties": {
                  "origin": {
                    "type": "string",
                    "example": "API"
                  },
                  "userAgent": {
                    "type": "string"
                  }
                }
              },
              "stats": {
                "type": "object",
                "properties": {
                  "inputBodyLen": {
                    "type": "integer",
                    "example": 2000
                  },
                  "rebootCount": {
                    "type": "integer",
                    "example": 0
                  },
                  "restartCount": {
                    "type": "integer",
                    "example": 0
                  },
                  "resurrectCount": {
                    "type": "integer",
                    "example": 0
                  },
                  "computeUnits": {
                    "type": "integer",
                    "example": 0
                  }
                }
              },
              "options": {
                "type": "object",
                "properties": {
                  "build": {
                    "type": "string",
                    "example": "latest"
                  },
                  "timeoutSecs": {
                    "type": "integer",
                    "example": 300
                  },
                  "memoryMbytes": {
                    "type": "integer",
                    "example": 1024
                  },
                  "diskMbytes": {
                    "type": "integer",
                    "example": 2048
                  }
                }
              },
              "buildId": {
                "type": "string"
              },
              "defaultKeyValueStoreId": {
                "type": "string"
              },
              "defaultDatasetId": {
                "type": "string"
              },
              "defaultRequestQueueId": {
                "type": "string"
              },
              "buildNumber": {
                "type": "string",
                "example": "1.0.0"
              },
              "containerUrl": {
                "type": "string"
              },
              "usage": {
                "type": "object",
                "properties": {
                  "ACTOR_COMPUTE_UNITS": {
                    "type": "integer",
                    "example": 0
                  },
                  "DATASET_READS": {
                    "type": "integer",
                    "example": 0
                  },
                  "DATASET_WRITES": {
                    "type": "integer",
                    "example": 0
                  },
                  "KEY_VALUE_STORE_READS": {
                    "type": "integer",
                    "example": 0
                  },
                  "KEY_VALUE_STORE_WRITES": {
                    "type": "integer",
                    "example": 1
                  },
                  "KEY_VALUE_STORE_LISTS": {
                    "type": "integer",
                    "example": 0
                  },
                  "REQUEST_QUEUE_READS": {
                    "type": "integer",
                    "example": 0
                  },
                  "REQUEST_QUEUE_WRITES": {
                    "type": "integer",
                    "example": 0
                  },
                  "DATA_TRANSFER_INTERNAL_GBYTES": {
                    "type": "integer",
                    "example": 0
                  },
                  "DATA_TRANSFER_EXTERNAL_GBYTES": {
                    "type": "integer",
                    "example": 0
                  },
                  "PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
                    "type": "integer",
                    "example": 0
                  },
                  "PROXY_SERPS": {
                    "type": "integer",
                    "example": 0
                  }
                }
              },
              "usageTotalUsd": {
                "type": "number",
                "example": 0.00005
              },
              "usageUsd": {
                "type": "object",
                "properties": {
                  "ACTOR_COMPUTE_UNITS": {
                    "type": "integer",
                    "example": 0
                  },
                  "DATASET_READS": {
                    "type": "integer",
                    "example": 0
                  },
                  "DATASET_WRITES": {
                    "type": "integer",
                    "example": 0
                  },
                  "KEY_VALUE_STORE_READS": {
                    "type": "integer",
                    "example": 0
                  },
                  "KEY_VALUE_STORE_WRITES": {
                    "type": "number",
                    "example": 0.00005
                  },
                  "KEY_VALUE_STORE_LISTS": {
                    "type": "integer",
                    "example": 0
                  },
                  "REQUEST_QUEUE_READS": {
                    "type": "integer",
                    "example": 0
                  },
                  "REQUEST_QUEUE_WRITES": {
                    "type": "integer",
                    "example": 0
                  },
                  "DATA_TRANSFER_INTERNAL_GBYTES": {
                    "type": "integer",
                    "example": 0
                  },
                  "DATA_TRANSFER_EXTERNAL_GBYTES": {
                    "type": "integer",
                    "example": 0
                  },
                  "PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
                    "type": "integer",
                    "example": 0
                  },
                  "PROXY_SERPS": {
                    "type": "integer",
                    "example": 0
                  }
                }
              }
            }
          }
        }
      }
    }
  }
}

LLM Latency & Cost Monitor OpenAPI definition

OpenAPI is a standard for designing and describing RESTful APIs, allowing developers to define API structure, endpoints, and data formats in a machine-readable way. It simplifies API development, integration, and documentation.

OpenAPI is effective when used with AI agents and GPTs by standardizing how these systems interact with various APIs, for reliable integrations and efficient communication.

By defining machine-readable API specifications, OpenAPI allows AI models like GPTs to understand and use varied data sources, improving accuracy. This accelerates development, reduces errors, and provides context-aware responses, making OpenAPI a core component for AI applications.

You can download the OpenAPI definitions for LLM Latency & Cost Monitor from the options below:

OpenAPI.json

If you’d like to learn more about how OpenAPI powers GPTs, read our blog post.

You can also check out our other API clients:

LLM Latency & Cost Monitor API in Python

LLM Latency & Cost Monitor API in JavaScript

LLM Latency & Cost Monitor API through CLI

LLM Latency & Cost Monitor API

LLM Provider Price and Latency Monitor

george.the.developer/llm-provider-price-latency-monitor

Normalize model pricing, context length, capabilities, and provider routing data for LLM gateways, AI builders, and FinOps teams.

George Kioko

VPS Location Latency Checker

vps-labs/vps-location-latency-checker

A simple tool concept for checking website response time and basic latency signals before choosing a VPS location.

Ihor K.

Multi-Model LLM Compare - GPT, Claude, Gemini & Llama

seemuapps/multi-model-llm-compare

Run one prompt across many language models at once and get every response side by side, with token counts, cost, and latency per model in a single dataset.

Andrew

AI llm.txt File Generator API

dev00/ai-llm-txt-file-generator-api

Generate llm.txt files automatically for any website. Map website directories and convert documentation into clean markdown structured llm.txt files for LLM agents.

dev00

OpenRouter LLM Router

flamelit_arowana/openrouter-model-router

Query OpenRouter for LLM models, pricing, and routing. List available models with capabilities and cost, find the cheapest model for your task, or route prompts to specific models.

Kevin Grossi

LLM API Pricing Monitor & Tracker

devilscrapes/llm-pricing-monitor

Scrape and compare live LLM API pricing from OpenAI, Anthropic, Google, Mistral, Groq, Together AI, and DeepSeek — normalized per-million-token, export to JSON or CSV. A continuously updated LLM API pricing comparison table for cost dashboards and FinOps.

DevilScrapes

tokenmark - LLM cost analyzer

charcoal_jam/tokenmark-llm-cost-analyzer

Pay-per-event LLM cost analysis. POST a JSONL log or array of LLM call entries; get back per-day/per-model spend, top costly calls, and rule-based route recommendations. Local-first alternative: tokenmark npm package.

autobiz

Llm Benchmarks

david_flagg/llm-benchmarks

Unified LLM data — pricing, benchmarks, specs, and local deployment info for 300+ models. Compare cost, Open LLM Leaderboard scores, Arena ratings, context lengths, GGUF availability, and VRAM estimates in one dataset.

David Flagg

Bulk HTTP Latency & TTFB Monitor

andok/http-latency-monitor

Measure website response times, Time-to-First-Byte, and status codes across thousands of URLs for uptime monitoring and performance audits.

Andok

🔥 AI HTML to JSON Extractor (Fast, Free LLM for Data)

autoscaler/ai-html-to-json-extractor

Eliminate messy HTML cleanup and high LLM costs. This Actor uses a high-speed, zero-cost large language model to turn unstructured content (HTML, text, reviews, blog posts) into valid, structured JSON.