Benchmark your own prompt on 100+ LLMs with real API calls; pick the cheapest model that passes.
Setup
Choose your client, copy the config, then fill in any required environment variables.
claude mcp add --transport http openmark https://openmark.ai/mcp --header 'Authorization: <AUTHORIZATION>'~/.codex/config.toml
[mcp_servers.openmark]
url = "https://openmark.ai/mcp"
http_headers = { Authorization = "<AUTHORIZATION>" }
# codex mcp add openmark --url https://openmark.ai/mcp~/.cursor/mcp.json
{
"mcpServers": {
"openmark": {
"url": "https://openmark.ai/mcp",
"headers": {
"Authorization": "<AUTHORIZATION>"
}
}
}
}.vscode/mcp.json
{
"servers": {
"openmark": {
"type": "http",
"url": "https://openmark.ai/mcp",
"headers": {
"Authorization": "<AUTHORIZATION>"
}
}
}
}~/.gemini/settings.json
{
"mcpServers": {
"openmark": {
"httpUrl": "https://openmark.ai/mcp",
"headers": {
"Authorization": "<AUTHORIZATION>"
}
}
}
}claude_desktop_config.json · Customize › Connectors › Add custom connector
{
"mcpServers": {
"openmark": {
"command": "npx",
"args": [
"-y",
"mcp-remote",
"https://openmark.ai/mcp",
"--header",
"Authorization:<AUTHORIZATION>"
]
}
}
}.trae/mcp.json
{
"mcpServers": {
"openmark": {
"url": "https://openmark.ai/mcp",
"headers": {
"Authorization": "<AUTHORIZATION>"
}
}
}
}