Free LLM Pricing API — Model Price Watch

Base URL

https://modelpricewatch.com/api/v1

All endpoints return JSON. Append the endpoint path to the base URL. No authentication required.

Endpoints

GET /models.json

All 156 models with pricing, context window, modality, and metadata.

Response schema

{
  "count": 156,
  "updated": "2026-06-24",
  "data": [
    {
      "id": "openai-gpt-5.5",
      "provider": "OpenAI",
      "model": "GPT-5.5",
      "category": "flagship",
      "input_per_mtok": 5.0,
      "output_per_mtok": 15.0,
      "cached_input_per_mtok": 1.25,
      "context_window": 400000,
      "modality": ["text", "image", "audio"],
      "released": "2025-03-15",
      "status": "Current",
      "open_source": false,
      "parameters": null,
      "blended_cost_per_mtok": 10.0,
      "pricing_url": "https://openai.com/api/pricing/",
      "last_updated": "2026-06-24",
      "detail_url": "https://modelpricewatch.com/models/openai-gpt-5.5/"
    },
    ...
  ]
}

GET /providers.json

All 24 providers with metadata, URLs, and founding info.

GET /stats.json

Aggregate statistics: total models, providers, cheapest prices, largest context window, category breakdown.

GET /price-history.json

Historical price snapshots for all tracked models. Each entry contains an array of daily snapshots with input/output prices and change events.

GET /changelog.json

Recent pricing changes detected by the scraper pipeline.

GET /best-for/{slug}.json

Use-case-specific model rankings. Available slugs: coding, chatbot, cheap-api, long-context, multimodal, reasoning, open-source, fast-inference, embedding, enterprise

GET /compare/{slug}.json

Model comparison data. Slug format: {model-a}-vs-{model-b}. Example: gpt-5.5-vs-claude-opus-4.1

Usage examples

cURL

curl https://modelpricewatch.com/api/v1/models.json | jq '.data[] | select(.category=="flagship") | {model, input_per_mtok, output_per_mtok}'

Python

import requests

resp = requests.get("https://modelpricewatch.com/api/v1/models.json")
models = resp.json()["data"]

# Find cheapest models
cheapest = sorted(models, key=lambda m: m["blended_cost_per_mtok"])[:10]
for m in cheapest:
    print(f"{m['model']:30s} ${m['blended_cost_per_mtok']}/Mtok")

JavaScript

const res = await fetch("https://modelpricewatch.com/api/v1/models.json");
const { data: models } = await res.json();

const cheapest = models
  .sort((a, b) => a.blended_cost_per_mtok - b.blended_cost_per_mtok)
  .slice(0, 10);
console.table(cheapest.map(m => ({
  model: m.model,
  provider: m.provider,
  blended: m.blended_cost_per_mtok
})));

Terms & fair use

Free — no API key, no payment, no signup
CORS enabled — safe for browser-side usage
Fair use — please cache responses. Data updates 3x daily, so a 4-hour cache TTL is ideal
No SLA — this is a free service. For production-critical integrations, mirror the data
Attribation — please link to modelpricewatch.com when displaying this data
Data freshness — pricing verified against official sources 3x daily (8am, 2pm, 8pm UTC)