Token counting & multi-model LLM cost estimates: GPT-4o, Claude, Gemini, 25+. No API key.
Setup
Choose your client, copy the config, then fill in any required environment variables.
claude mcp add llm-cost-estimator -- npx -y llm-cost-estimator-mcp~/.codex/config.toml
[mcp_servers.llm-cost-estimator]
command = "npx"
args = ["-y", "llm-cost-estimator-mcp"]
# codex mcp add llm-cost-estimator -- npx -y llm-cost-estimator-mcp~/.cursor/mcp.json
{
"mcpServers": {
"llm-cost-estimator": {
"command": "npx",
"args": [
"-y",
"llm-cost-estimator-mcp"
]
}
}
}.vscode/mcp.json
{
"servers": {
"llm-cost-estimator": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"llm-cost-estimator-mcp"
]
}
}
}~/.gemini/settings.json
{
"mcpServers": {
"llm-cost-estimator": {
"command": "npx",
"args": [
"-y",
"llm-cost-estimator-mcp"
]
}
}
}claude_desktop_config.json
{
"mcpServers": {
"llm-cost-estimator": {
"command": "npx",
"args": [
"-y",
"llm-cost-estimator-mcp"
]
}
}
}.trae/mcp.json
{
"mcpServers": {
"llm-cost-estimator": {
"command": "npx",
"args": [
"-y",
"llm-cost-estimator-mcp"
]
}
}
}