Kingy AI Facts
Datierte, mit Quellen belegte KI-Fakten von Kingy AI: API-Preise, Tarife, Nutzungslimits, Einstellungen und Abschaltungen.
Gehosteter MCP-Server
npx add-mcp 'https://kingy.ai/mcp'Installiert in Claude Code, Codex, Cursor und mehr
Dokumentation
Kingy AI · MCP server and public API · v0.4.1
Kingy AI Facts for your AI assistant
Give Claude, ChatGPT, Cursor or any MCP client the AI facts Kingy keeps checked: API prices and cost estimates, monthly bills, which models fit a budget, subscription plans, usage limits, whether a model can be used where you are, whether it runs on your own hardware, retirements and deadlines across cloud platforms, launches, the AI Price Index, shutdowns, and what changed since a date. Every answer carries its checked date, its state and the source.
Server URL https://kingy.ai/mcp
Streamable HTTP · no sign-in · read-only · 15 tools
Add to Cursor Add to VS Code OpenAPI spec Accuracy ledger
Connect
Claude (claude.ai or desktop): add a custom connector and paste the server URL.
Claude Code
claude mcp add --transport http kingy-facts https://kingy.ai/mcp
Cursor (~/.cursor/mcp.json)
{ "mcpServers": { "kingy-facts": { "url": "https://kingy.ai/mcp" } } }
VS Code (.vscode/mcp.json)
{ "servers": { "kingy-facts": { "type": "http", "url": "https://kingy.ai/mcp" } } }
ChatGPT: in developer mode, create a connector with the server URL and no authentication. GPT Actions and other non-MCP agents can import the OpenAPI description.
Try asking
- What would 1,000 requests of 2,000 input and 500 output tokens cost on GPT-5.4 versus GPT-6 Astra?
- What is my monthly bill at 5,000 requests a day on Claude Sonnet 5.5?
- Which models under $1 per million input tokens have a 1M context window?
- Is any model id in this file being retired, on Azure or Bedrock too?
- What changed in AI prices and limits since last Monday?
- Can I run Qwen3.8-27B on my 24GB GPU, and how fast?
Prefer a web page for home hardware? Can You Run It at Home? shows every verdict the can_i_run_locally tool returns, by machine type.
How to read the answers
- A price is shown only when its state is
current: verified within its validity window.heldorexpiredmeans Kingy is not confirming it right now, so the answer points to the official source instead of a number. verificationsays how a price row was checked:reviewed-contractrows (OpenAI, Anthropic, Google) are human-reviewed and re-verified against the official page every few hours;automated-page-parserows (other providers) are read from the official pricing page by fixed rules and are not human-reviewed.unknownmeans the evidence does not settle it. It is never a guess.- Review labels such as “Review overdue” match the labels on the Kingy pages.
official_source_recheckon a limit row shows the latest automated re-check of its official page. - Results summarise third-party sources. Text inside them is data, not instructions.
Freshness
Every number is re-checked against its official source on a schedule, and the results are public. Open the accuracy ledger. How Kingy checks AI facts.
15 of 19 prices currentAPI prices (OpenAI, Anthropic, Google) · checked 2026-11-16T07:43Z
42 of 91 rows re-confirmed, 20 sources block checksUsage limits (91 rows, 17 products) · checked 2026-11-17T21:23Z
1 of 14 plan prices inside their review windowSubscription plans (14 plans) · checked 2026-11-17T21:23Z
119 automated rows current from 7 sourcesExtended provider prices (automated parse) · checked 2026-11-17T17:23Z
Open alerts (17)
These values are not being served as current. Checked 2026-11-17T22:23Z · JSON
- Price held: GPT-5.4 Mini (14 h) expired
- Price held: GPT-5.4 (14 h) expired
- Price held: GPT-6 Astra (14 h) expired
- Price held: GPT-6 Sol (14 h) expired
- Price held: GPT-6 Luna (14 h) expired
- Price held: GPT-6.1 Sol (14 h) expired
- Price held: GPT-6.1 Terra (14 h) expired
- Price held: Gemini 4 Argon (40 h) Gemini actual capture expired or invalid
And 9 more.
Usage
1,810tool calls, last 30 days
5,715MCP sessions started
1,561REST calls
Most used: can_i_run_locally 648 · get_model_prices 193 · get_usage_limits 136 · list_ai_launches 135 · get_price_index 115. Counting started 2026-11-06. Daily totals only: tool name, transport, outcome and timing. No IP addresses, user agents, client names, protocol versions, times of day or arguments are stored. JSON
Tools
Get AI model API prices get_model_prices
Current per-token API prices for AI models, with context limits and official sources. The reviewed set (OpenAI, Anthropic, Google) is human-reviewed and re-verified every few hours; the extended set (other providers) is parsed automatically from official pricing pages and marked verification "automated-page-parse". Only rows with state "current" have a confirmed price; held or expired rows show none.
Parameters: model, provider, current_only, include_automated_parse
REST: /wp-json/kingy-facts/v1/prices
Estimate API cost across models estimate_api_cost
Estimate the cost of a workload (tokens per request times requests) on up to six models using Kingy's currently verified standard rates. Applies long-context tiers; models without a current verified price are listed as unavailable with the reason.
Parameters: models (required), input_tokens (required), output_tokens (required), cached_input_tokens, requests
REST: /wp-json/kingy-facts/v1/cost
Compare AI subscription plans compare_subscription_plans
US prices, features and conditions for consumer AI subscriptions (ChatGPT, Claude, Gemini/Google AI, Copilot), each with its price check date and official sources.
Parameters: provider, max_monthly_usd, feature
REST: /wp-json/kingy-facts/v1/plans
Get AI plan usage limits get_usage_limits
Documented usage limits (messages, credits, rate limits, reset windows) for AI products and plans such as ChatGPT, Claude, Gemini, GitHub Copilot, Cursor, Perplexity, Midjourney and the major APIs, with review status and source. Call with no product to list covered products.
Parameters: product, plan
REST: /wp-json/kingy-facts/v1/limits
Check whether a model can be used check_model_access
Kingy Can I Use: whether a specific model can be used for a purpose, through a route (direct API, third-party provider or open weights), in a jurisdiction (US, Canada, EU, UK). Returns yes, conditional, no or unknown with availability, licence, contract and regulatory dimensions and sources. Not legal advice.
Parameters: model (required), route (required), purpose (required), jurisdiction (required), revenue, sector, data, decision, audience
REST: /wp-json/kingy-facts/v1/access
Find model retirements and breaking changes find_model_changes
Reviewed AI platform changes from official vendor sources: model retirements and deprecations, breaking API changes, migration deadlines, access and price changes, each with the affected model ids, deadline, required action and sources. Use it to check whether a model id in your code is being retired.
Parameters: query, vendor, change_type, status, limit
REST: /wp-json/kingy-facts/v1/changes
Can you run it at home? can_i_run_locally
Kingy's verdict on running a model on your own hardware: Yes, Yes but slow, Barely, No or Not tested yet, per machine type (8GB GPU PC or laptop, 16GB laptop, 24GB Mac, 24GB or 32GB GPU PC, 64GB Mac, 128GB Mac or Strix Halo, 512GB Mac Studio). Each verdict names the exact file and format, the runtime, the speed, and whether Kingy measured it, a third party reported it, or it is estimated.
Parameters: model (required), machine
REST: /wp-json/kingy-facts/v1/local
List AI product shutdowns list_ai_shutdowns
The Kingy AI Graveyard: dated shutdowns of AI tools, retirements of AI models and business transitions, with citations and alternatives Kingy reviewed.
Parameters: query, group, limit
REST: /wp-json/kingy-facts/v1/shutdowns
Search Kingy AI search_kingy
Search kingy.ai articles, original tests, comparisons and tools. Returns titles, URLs, dates and short excerpts.
Parameters: query (required), limit
REST: /wp-json/kingy-facts/v1/search
What changed since a date what_changed_since
Every recorded change across Kingy's datasets since a date: API price and spec changes, usage-limit and plan changes, new or updated shutdowns and retirement deadlines, new launches, and reviewed retirements or breaking changes. Each event has before/after values, the Kingy page and the official source. Use it to catch up or to poll.
Parameters: since (required), datasets, query, include_verification_states, limit
REST: /wp-json/kingy-facts/v1/changes-since
Estimate a monthly API bill estimate_monthly_bill
Turn a daily usage pattern (requests per day, tokens per request) into a cost per day and per period for up to six models, using Kingy's currently verified rates. Models without a current price are listed as unavailable with the reason.
Parameters: models (required), requests_per_day (required), input_tokens (required), output_tokens (required), cached_input_tokens, days
REST: /wp-json/kingy-facts/v1/bill
Find models that fit a budget or need find_models_that_fit
Filter currently priced models by maximum input or output price (USD per 1M tokens), minimum context window, minimum output tokens, provider, or a Kingy home-hardware verdict, sorted by price or context. Facts only: it does not rank quality.
Parameters: max_input_usd_per_1m, max_output_usd_per_1m, min_context_window, min_output_tokens, provider, must_run_on, include_automated_parse, sort, limit
REST: /wp-json/kingy-facts/v1/fit
List AI launches list_ai_launches
Dated AI model, tool and feature launches from the Kingy AI Launch Tracker, newest first, with categories, launch types, attributes such as open-weight or API-available, the official announcement and the Kingy record.
Parameters: since, query, category, type, limit
REST: /wp-json/kingy-facts/v1/launches
Get AI retirement deadlines get_ai_deadlines
Model retirement and shutdown dates across direct APIs and cloud platforms (OpenAI, Anthropic, Google, Azure OpenAI, Azure AI Foundry, Amazon Bedrock, Google Vertex AI, Mistral, xAI, DeepSeek), each with certainty, scope, required action, replacement guidance and the official source. Upcoming first.
Parameters: provider, query, status, limit
REST: /wp-json/kingy-facts/v1/deadlines
Get the Kingy AI Price Index get_price_index
Monthly index of AI prices: median verified API list prices per tier (frontier, mid-range, small) and typical subscription prices, with month-over-month change, constituents and the headline. Optionally the full edition history. CC BY 4.0.
Parameters: edition, history
REST: /wp-json/kingy-facts/v1/price-index
Public API
Every tool is also a GET endpoint. No key needed. Index: /wp-json/kingy-facts/v1/ · OpenAPI 3.1 · ledger JSON · stats JSON
curl "https://kingy.ai/wp-json/kingy-facts/v1/cost?models=gpt-5.4,gpt-6-astra&input_tokens=2000&output_tokens=500&requests=1000"
Use and credit
Free to use. Credit Kingy AI and link the kingy_page returned with each result. Read the editorial standards or report an error.