Cloudflare Workers MCP server: ai-model-router
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.
Compare cost and task fit across all supported AI models for a given prompt or token count.
This tool isn't marked read-only, so it may change something on the server or in an account you connected.
Compare cost and task fit across all supported AI models for a given prompt or token count.
| Argument | Type | Description |
|---|---|---|
| prompt | string | |
| task_type | string | |
| input_tokens |
| integer |
| output_tokens | integer |
{
"type": "object",
"properties": {
"prompt": {
"type": "string"
},
"task_type": {
"type": "string"
},
"input_tokens": {
"type": "integer"
},
"output_tokens": {
"type": "integer"
}
}
}List all supported AI models with pricing and capabilities.
No arguments.
{
"type": "object",
"properties": {}
}Select the optimal AI model (GPT-4, Claude, Gemini) for a task based on type, cost, and provider preferences.
| Argument | Type | Description |
|---|---|---|
| prompt | string | Task description for auto-classification |
| task_type | string | |
| prefer_tier | string | |
| input_tokens | integer | |
| max_cost_usd | number | Max budget in USD per call |
| output_tokens | integer | |
| prefer_provider | string |
{
"type": "object",
"properties": {
"prompt": {
"type": "string",
"description": "Task description for auto-classification"
},
"task_type": {
"enum": [
"code",
"analysis",
"creative",
"summarize",
"classify",
"reason",
"vision",
"chat",
"general"
],
"type": "string"
},
"prefer_tier": {
"enum": [
"economy",
"standard",
"premium"
],
"type": "string"
},
"input_tokens": {
"type": "integer"
},
"max_cost_usd": {
"type": "number",
"description": "Max budget in USD per call"
},
"output_tokens": {
"type": "integer"
},
"prefer_provider": {
"enum": [
"openai",
"anthropic",
"google"
],
"type": "string"
}
}
}