Live prices for 116 Chinese models; batch cost calculators for video and images.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
List the cheapest Chinese AI models from NovAI's live price feed, ranked by a comparable cost unit (text: 1M input + 200K output; video: 5-second clip; image: per image). Use this when the user asks which model is cheapest, wants to compare costs, or is choosing a model by budget. For a batch cost estimate at list price, see https://aiapi-pro.com/video-cost-calculator (video) and https://aiapi-pro.com/image-cost-calculator (images).
max rows (default 10, max 50)
Video, Image, Chat / LLM, Audio, 3D, Embedding
only models whose comparable cost is at or below this USD figure
This tool isn't marked read-only, so it may change something on the server or in an account you connected.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http novai-prices https://aiapi-pro.com/api/mcp
List the cheapest Chinese AI models from NovAI's live price feed, ranked by a comparable cost unit (text: 1M input + 200K output; video: 5-second clip; image: per image). Use this when the user asks which model is cheapest, wants to compare costs, or is choosing a model by budget. For a batch cost estimate at list price, see https://aiapi-pro.com/video-cost-calculator (video) and https://aiapi-pro.com/image-cost-calculator (images).
| Argument | Type | Description |
|---|---|---|
| limit | integer | max rows (default 10, max 50) |
| category | string | Video, Image, Chat / LLM, Audio, 3D, Embedding |
| max_price | number | only models whose comparable cost is at or below this USD figure |
{
"type": "object",
"properties": {
"limit": {
"type": "integer",
"description": "max rows (default 10, max 50)"
},
"category": {
"type": "string",
"description": "Video, Image, Chat / LLM, Audio, 3D, Embedding"
},
"max_price": {
"type": "number",
"description": "only models whose comparable cost is at or below this USD figure"
}
}
}List the model categories available in NovAI's price feed (Chat / LLM, Video, Image, Audio, 3D, Embedding) with the number of models in each. Use this first when the category for a request is unclear, then call cheapest_models with that category. Machine-readable feed: https://aiapi-pro.com/china-ai-leaderboard.json
No arguments.
{
"type": "object",
"properties": {}
}Look up the NovAI list price of a Chinese AI model by name fragment (seedance, kimi, glm, qwen, doubao, hunyuan, minimax...). Use this when the user asks what a specific model costs, or wants a price before choosing one. Returns the provider list price, the unit (per 1M tokens / per image / per generation) and the model id. Per-minute video costs with every row sourced: https://aiapi-pro.com/video-cost-2026
| Argument | Type | Description |
|---|---|---|
| model* | string |
{
"type": "object",
"required": [
"model"
],
"properties": {
"model": {
"type": "string"
}
}
}We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Nov 20, 2026.
No readOnlyHint / destructiveHint annotations, so clients can't tell a read from a write without asking.
Fix: Add annotations to each tool, e.g. { readOnlyHint: true } for tools that only read.