Free LLM Pricing API

Name: LLM Pricing Dataset (free, CC BY 4.0)
Creator: LLMCalculator.net
License: https://creativecommons.org/licenses/by/4.0/

Every model and price on this site is published as an openly-licensed dataset. No API key, no rate limit, no signup. Use it in your app, your spreadsheet, your blog post, your research paper. Licensed under CC BY 4.0 — just link back to llmcalculator.net.

Endpoints

Path	Format	Returns
GET /api/v1/models	JSON	All current models (filters: `?provider=`, `?max_input=`, `?speed=`)
GET /api/v1/models/:id	JSON	A single model by id, e.g. `gpt-4o`
POST /api/v1/calculate	JSON	Body: `{ model_id, input_tokens, output_tokens }` → cost breakdown
GET /api/v1/providers	JSON	All providers with model counts
GET /api/v1/cheapest	JSON	Cheapest models (`?sort=input\|output\|combined`, `?limit=`, `?provider=`)
POST /mcp	JSON-RPC	Model Context Protocol server for AI assistants
/llm-pricing-history	HTML / data	Historical pricing 2023–2026 (citable dataset)

CORS is open (Access-Control-Allow-Origin: *) so you can fetch from the browser.

Sample response

GET /api/v1/models

{
  "updated": "2026-06-25",
  "currency": "USD",
  "unit": "per_1m_tokens",
  "models": [
    {
      "id": "gpt-5.5",
      "provider": "openai",
      "name": "GPT-5.5",
      "input": 1.25,
      "output": 10,
      "context": 400000
    },
    {
      "id": "claude-sonnet-4-6",
      "provider": "anthropic",
      "name": "Claude Sonnet 4.6",
      "input": 3,
      "output": 15,
      "context": 1000000
    },
    {
      "id": "gemini-3-1-pro",
      "provider": "google",
      "name": "Gemini 3.1 Pro",
      "input": 1.25,
      "output": 10,
      "context": 2000000
    },
    {
      "id": "deepseek-v4-flash",
      "provider": "deepseek",
      "name": "DeepSeek V4 Flash",
      "input": 0.07,
      "output": 0.27,
      "context": 128000
    }
  ]
}

Quick examples

cURL

curl https://llmcalculator.net/api/v1/models
curl -X POST https://llmcalculator.net/api/v1/calculate \
  -H "content-type: application/json" \
  -d '{"model_id":"gpt-4o","input_tokens":50000,"output_tokens":10000}'

JavaScript

const r = await fetch("https://llmcalculator.net/api/v1/cheapest?limit=5");
const { models } = await r.json();
console.log(models[0]);

Python

import requests
r = requests.post("https://llmcalculator.net/api/v1/calculate", json={
  "model_id": "claude-sonnet-4-6",
  "input_tokens": 50000,
  "output_tokens": 10000,
})
print(r.json()["total_cost_usd"])

MCP server for AI assistants

Claude, ChatGPT, Cursor and any other Model Context Protocol client can connect to our hosted MCP server and use the LLM pricing tools directly inside the chat.

Endpoint

https://llmcalculator.net/mcp

Transport

Streamable HTTP (JSON-RPC 2.0 over POST). No auth required.

Available tools

list_models — list models, filter by provider/price
calculate_cost — compute cost for a model + token counts
compare_models — rank all models by total cost for a workload
get_cheapest_model — single cheapest model (optional provider filter)

Claude Desktop / Cursor config

{
  "mcpServers": {
    "llmcalculator": {
      "url": "https://llmcalculator.net/mcp"
    }
  }
}

Attribution

If you use this data, please credit:

Source: LLMCalculator.net — https://llmcalculator.net (CC BY 4.0)