AI
Analyze language mix and estimate token usage across OpenAI, Codex, Claude, and DeepSeek profiles
Call this tool from your code in three languages.
# 1) Upload each file first → returns { filePath }
curl -X POST 'https://api.elysiatools.com/upload/ai-token-estimator' \
-F 'file=@/path/to/textFile.ext'
# 2) Call the tool with the returned filePath values
curl -X POST 'https://api.elysiatools.com/en/api/tools/ai-token-estimator' \
-F 'inputText=请总结 this API design and list 3 risks.' \
-F 'textFile=/path/to/file.ext' \
-F 'modelProfile=All Profiles' \
-F 'countMode=raw-text'Send a POST request with your inputs as JSON. File parameters require a separate upload first.
POST https://api.elysiatools.com/en/api/tools/ai-token-estimator| Name | Type | Required | Description |
|---|---|---|---|
| inputText | textarea | No | — |
| textFile | fileupload required | No | — |
| modelProfile | select | No | — |
| countMode | select | No | — |
Add this tool to your Model Context Protocol server so AI agents can list and call it.
Add this block to your MCP client configuration:
{
"mcpServers": {
"elysiatools-ai-token-estimator": {
"name": "ai-token-estimator",
"description": "Analyze language mix and estimate token usage across OpenAI, Codex, Claude, and DeepSeek profiles",
"baseUrl": "https://api.elysiatools.com/mcp/sse?toolId=ai-token-estimator",
"command": "",
"args": [],
"env": {},
"isActive": true,
"type": "sse"
}
}
}After connecting to the SSE endpoint, list the exposed tools:
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/list"
}Invoke the tool by its id, passing arguments built from its parameters:
{
"jsonrpc": "2.0",
"id": 2,
"method": "tools/call",
"params": {
"name": "ai-token-estimator",
"arguments": {
"inputText": "请总结 this API design and list 3 risks.",
"textFile": "https://example.com/file.ext",
"modelProfile": "All Profiles",
"countMode": "raw-text"
}
}
}JSON result
{
"key": {...},
"metadata": {
"key": "value"
},
"error": "Error message (optional)",
"message": "Notification message (optional)"
}Questions or issues? Contact [email protected]