NovAI Prices

Official registry Productivity

Live prices for 111 Chinese AI models, with cheapest-model lookup by task.

Install

Add this to your client's MCP configuration (Claude Desktop: claude_desktop_config.json; Cursor: .cursor/mcp.json; VS Code and others use the same "mcpServers" shape).

Remote (streamable-http)
Claude Code
claude mcp add --transport http novai-prices 'https://aiapi-pro.com/api/mcp'
JSON configuration (Claude Desktop, Cursor, VS Code)
{
    "mcpServers": {
        "novai-prices": {
            "type": "http",
            "url": "https://aiapi-pro.com/api/mcp"
        }
    }
}

Documentation

From the project's README on GitHub, refreshed weekly. Links open on GitHub.

Contents
  1. novai-prices-mcp
  2. Tools
  3. Run it
  4. Why this exists
  5. Data freshness
  6. License

novai-prices-mcp

Listed in the official MCP Registry as io.github.vvvvking/novai-prices — remote streamable-http endpoint: https://aiapi-pro.com/api/mcp

An MCP server that answers one question well: which Chinese AI model is cheapest for what I'm doing right now?

It reads NovAI's live price feed (https://aiapi-pro.com/china-ai-leaderboard.json) and normalizes every model into a comparable cost unit, because every provider quotes a different one:

ModalityUnit the market quotesUnit this server uses
Chat / LLMper 1M input, per 1M output1M input + 200K output (one large coding run)
Videoper second, per generation, per 1M tokensone 5-second clip (token-billed models are converted)
Imageper image, per generationone image

Prices are the providers' list price passed through with a 1.0 multiplier and 0% platform markup — the server reports the rate card, not a sales number.

Tools

ToolWhat it does
cheapest_modelsCheapest models, optionally filtered by category and max_price
model_pricePrice lookup by name fragment (seedance, kimi, glm, qwen…)
list_categoriesCategories available in the feed

Run it

No dependencies beyond Python 3.9+:

python3 server.py
Claude Desktop / Cline / any MCP client
{
  "mcpServers": {
    "novai-prices": {
      "command": "python3",
      "args": ["/absolute/path/to/server.py"]
    }
  }
}
Example session
→ tools/call cheapest_models {"category": "video", "limit": 3}
← CogVideoX-Flash (Zhipu AI) — FREE
  PixVerse C1 Video API (PixVerse) — $0.154 per 5s clip (est.)
  PixVerse V6.0 Video API (PixVerse) — $0.203 per 5s clip (est.)
→ tools/call cheapest_models {"category": "chat / llm", "limit": 3}
← GLM-4.7-Flash — FREE
  DeepSeek V4 Flash — $0.080/1M in, $0.170/1M out ($0.11 per 1M-in/200K-out run)
  GLM-5.3-Flash — $0.080/1M in, $0.280/1M out

Why this exists

Price comparison for Chinese models is broken: one vendor quotes per second, another per token, a third per generation. Converting them by hand is error-prone, and every gateway's marketing page has an incentive to make its own numbers look good. This server just converts and sorts, and links to the machine-readable feed so the numbers can be checked.

Data freshness

The feed is regenerated daily from the live model catalog. generated_at is included in the JSON; if the upstream feed is unreachable the tool returns an error rather than stale numbers.

License

MIT

Frequently asked questions

What is NovAI Prices?

Live prices for 111 Chinese AI models, with cheapest-model lookup by task.

How do I install NovAI Prices?

It runs as a remote server. In Claude Code: claude mcp add --transport http novai-prices 'https://aiapi-pro.com/api/mcp'. For other clients, paste the JSON configuration from this page into their MCP settings.

Does NovAI Prices need an API key?

Its registry entry lists no required key or secret. Some features may still need an account with the service it connects to.

Is NovAI Prices open source?

Its code is public on GitHub, but the repository does not declare a standard license.

Who maintains NovAI Prices?

It is published by vvvvking. AI.tn lists it but does not maintain or endorse it.

From the official MCP Registry. Listing is not an endorsement: review a server's code and permissions before giving it access to your data.